Large Language Models (LLMs) such as GPT & Llama have demonstrated significant achievements in summarization tasks but struggle with factual inaccuracies, a critical issue in clinical NLP applications where errors could lead to serious consequences. To counter the high costs and limited availability of expert-annotated data for factual alignment, this study introduces an innovative pipeline that utilizes >100B parameter GPT variants like GPT-3.5 & GPT-4 to act as synthetic experts to generate high-quality synthetics feedback aimed at enhancing factual consistency in clinical note summarization. Our research primarily focuses on edit feedback generated by these synthetic feedback experts without additional human annotations, mirroring and optimizing the practical scenario in which medical professionals refine AI system outputs. Although such 100B+ parameter GPT variants have proven to demonstrate expertise in various clinical NLP tasks, such as the Medical Licensing Examination, there is scant research on their capacity to act as synthetic feedback experts and deliver expert-level edit feedback for improving the generation quality of weaker (<10B parameter) LLMs like GPT-2 (1.5B) & Llama 2 (7B) in clinical domain. So in this work, we leverage 100B+ GPT variants to act as synthetic feedback experts offering expert-level edit feedback, that is used to reduce hallucinations and align weaker (<10B parameter) LLMs with medical facts using two distinct alignment algorithms (DPO & SALT), endeavoring to narrow the divide between AI-generated content and factual accuracy. This highlights the substantial potential of LLM-based synthetic edits in enhancing the alignment of clinical factuality.

Understanding context is key to understanding human language, an ability which Large Language Models (LLMs) have been increasingly seen to demonstrate to an impressive extent. However, though the evaluation of LLMs encompasses various domains within the realm of Natural Language Processing, limited attention has been paid to probing their linguistic capability of understanding contextual features. This paper introduces a context understanding benchmark by adapting existing datasets to suit the evaluation of generative models. This benchmark comprises of four distinct tasks and nine datasets, all featuring prompts designed to assess the models’ ability to understand context. First, we evaluate the performance of LLMs under the in-context learning pretraining scenario. Experimental results indicate that pre-trained dense models struggle with understanding more nuanced contextual features when compared to state-of-the-art fine-tuned models. Second, as LLM compression holds growing significance in both research and real-world applications, we assess the context understanding of quantized models under in-context-learning settings. We find that 3-bit post-training quantization leads to varying degrees of performance reduction on our benchmark. We conduct an extensive analysis of these scenarios to substantiate our experimental results.

We introduce NoteChat, a novel cooperative multi-agent framework leveraging Large Language Models (LLMs) to generate patient-physician dialogues. NoteChat embodies the principle that an ensemble of role-specific LLMs, through structured role-play and strategic prompting, can perform their assigned roles more effectively. The synergy among these role-playing LLMs results in a cohesive and efficient dialogue generation. Evaluation on MTS-dialogue, a benchmark dataset for patient-physician dialogues-note pairs, shows that models trained with the augmented synthetic patient-physician dialogues by NoteChat outperforms other state-of-the-art models for generating clinical notes. Our comprehensive automatic and human evaluation demonstrates that NoteChat substantially surpasses state-of-the-art models like ChatGPT and GPT-4 up to 22.78% by domain experts in generating superior synthetic patient-physician dialogues based on clinical notes. NoteChat has the potential to engage patients directly and help clinical documentation, a leading cause of physician burnout.

The advancement in healthcare has shifted focus toward patient-centric approaches, particularly in self-care and patient education, facilitated by access to Electronic Health Records (EHR). However, medical jargon in EHRs poses significant challenges in patient comprehension. To address this, we introduce a new task of automatically generating lay definitions, aiming to simplify complex medical terms into patient-friendly lay language. We first created the README dataset, an extensive collection of over 50,000 unique (medical term, lay definition) pairs and 300,000 mentions, each offering context-aware lay definitions manually annotated by domain experts. We have also engineered a data-centric Human-AI pipeline that synergizes data filtering, augmentation, and selection to improve data quality. We then used README as the training data for models and leveraged a Retrieval-Augmented Generation method to reduce hallucinations and improve the quality of model outputs. Our extensive automatic and human evaluations demonstrate that open-source mobile-friendly models, when fine-tuned with high-quality data, are capable of matching or even surpassing the performance of state-of-the-art closed-source large language models like ChatGPT. This research represents a significant stride in closing the knowledge gap in patient education and advancing patient-centric healthcare solutions.

In this work, we study in-context teaching(ICT), where a teacher provides in-context example rationales to teach a student to reasonover unseen cases. Human teachers are usually required to craft in-context demonstrations, which are costly and have high variance. We ask whether a large language model (LLM) can serve as a more effective in-context teacher for itself or otherLLMs, compared to humans. Inspired by the Encoding Specificity Hypothesis from human episodic memory, we hypothesize thatin-context exemplars crafted by the teacher should match the training data of the student. This hypothesis motivates us to propose Self-Explain where an LLM’s self-elicited explanations are used as in-context demonstrations for prompting it as they are generalized fromthe model’s training examples. Self-Explain is shown to significantly outperform using human-crafted exemplars and other baselines.Furthermore, we reveal that for ICT, rationales from different teacher LLMs or human experts that more resemble the student LLM’s self-explanations are better in-context demonstrations. This supports our encoding specificity hypothesis. We then propose Teach-Back that aligns a teacher LLM with the student to enhance the ICT performance. For example, Teach-Back enables a 7B model to teach the much larger GPT-3.5 in context, surpassing human teachers by around 5% in test accuracy on medical question answering.

Reference resolution is an important problem, one that is essential to understand and successfully handle contexts of different kinds. This context includes both previous turns and context that pertains to non-conversational entities, such as entities on the user’s screen or those running in the background. While LLMs have been shown to be extremely powerful for a variety of tasks, their use in reference resolution, particularly for non-conversational entities, remains underutilized. This paper demonstrates how LLMs can be used to create an effective system to resolve references of various types, by showing how reference resolution can be converted into a language modeling problem, despite involving forms of entities like those on screen that are not traditionally conducive to being reduced to a text-only modality. We demonstrate large improvements over an existing system with similar functionality across different types of references, with our smallest model obtaining absolute gains of over 5% for on-screen references. We also benchmark against GPT-3.5 and GPT-4, with our smallest model achieving performance comparable to that of GPT-4, and our larger models substantially outperforming it.

Opioid related aberrant behaviors (ORABs) present novel risk factors for opioid overdose. This paper introduces a novel biomedical natural language processing benchmark dataset named ODD, for ORAB Detection Dataset. ODD is an expert-annotated dataset designed to identify ORABs from patients’ EHR notes and classify them into nine categories; 1) Confirmed Aberrant Behavior, 2) Suggested Aberrant Behavior, 3) Opioids, 4) Indication, 5) Diagnosed opioid dependency, 6) Benzodiazepines, 7) Medication Changes, 8) Central Nervous System-related, and 9) Social Determinants of Health. We explored two state-of-the-art natural language processing models (fine-tuning and prompt-tuning approaches) to identify ORAB. Experimental results show that the prompt-tuning models outperformed the fine-tuning models in most categories and the gains were especially higher among uncommon categories (Suggested Aberrant Behavior, Confirmed Aberrant Behaviors, Diagnosed Opioid Dependence, and Medication Change). Although the best model achieved the highest 88.17% on macro average area under precision recall curve, uncommon classes still have a large room for performance improvement. ODD is publicly available.

Wikipedia (Wiki) is one of the most widely used and publicly available resources for natural language processing (NLP) applications. Wikipedia Revision History (WikiRevHist) shows the order in which edits were made to any Wiki page since its first modification. While the most up-to-date Wiki has been widely used as a training source, WikiRevHist can also be valuable resources for NLP applications. However, there are insufficient tools available to process WikiRevHist without having substantial computing resources, making additional customization, and spending extra time adapting others’ works. Therefore, we report Blocks Architecture (BloArk), an efficiency-focused data processing architecture that reduces running time, computing resource requirements, and repeated works in processing WikiRevHist dataset. BloArk consists of three parts in its infrastructure: blocks, segments, and warehouses. On top of that, we build the core data processing pipeline: builder and modifier. The BloArk builder transforms the original WikiRevHist dataset from XML syntax into JSON Lines (JSONL) format for improving the concurrent and storage efficiency. The BloArk modifier takes previously-built warehouses to operate incremental modifications for improving the utilization of existing databases and reducing the cost of reusing others’ works. In the end, BloArk can scale up easily in both processing Wikipedia Revision History and incrementally modifying existing dataset for downstream NLP use cases. The source code, documentations, and example usages are publicly available online and open-sourced under GPL-2.0 license.

In-context learning with Large Language Models (LLMs) has emerged as a promising avenue of research in Dialog State Tracking (DST). However, the best-performing in-context learning methods involve retrieving and adding similar examples to the prompt, requiring access to labeled training data. Procuring such training data for a wide range of domains and applications is time-consuming, expensive, and, at times, infeasible. While zero-shot learning requires no training data, it significantly lags behind the few-shot setup. Thus, ‘Can we efficiently generate synthetic data for any dialogue schema to enable few-shot prompting?' Addressing this question, we propose , a data generation framework tailored for DST, utilizing LLMs. Our approach only requires the dialogue schema and a few hand-crafted dialogue templates to synthesize natural, coherent, and free-flowing dialogues with DST annotations. Few-shot learning using data from results in 4-5% improvement in Joint Goal Accuracy over the zero-shot baseline on MultiWOZ 2.1 and 2.4. Remarkably, our few-shot learning approach recovers nearly 98% of the performance compared to the few-shot setup using human-annotated training data.

The advancement of natural language processing (NLP) systems in healthcare hinges on language models’ ability to interpret the intricate information contained within clinical notes. This process often requires integrating information from various time points in a patient’s medical history. However, most earlier clinical language models were pretrained with a context length limited to roughly one clinical document. In this study, We introduce ClinicalMamba, a specialized version of the Mamba language model, pretrained on a vast corpus of longitudinal clinical notes to address the unique linguistic characteristics and information processing needs of the medical domain. ClinicalMamba models, with 130 million and 2.8 billion parameters, demonstrate superior performance in modeling clinical language across extended text lengths compared to Mamba and other clinical models based on longformer and Llama. With few-shot learning, ClinicalMamba achieves notable benchmarks in speed and performance, outperforming existing clinical language models and large language models like GPT-4 in longitudinal clinical tasks.

This paper presents our team’s participation in the MEDIQA-ClinicalNLP 2024 shared task B. We present a novel approach to diagnosing clinical dermatology cases by integrating large multimodal models, specifically leveraging the capabilities of GPT-4V under a retriever and a re-ranker framework. Our investigation reveals that GPT-4V, when used as a retrieval agent, can accurately retrieve the correct skin condition 85% of the time using dermatological images and brief patient histories. Additionally, we empirically show that Naive Chain-of-Thought (CoT) works well for retrieval while Medical Guidelines Grounded CoT is required for accurate dermatological diagnosis. Further, we introduce a Multi-Agent Conversation (MAC) framework and show it’s superior performance and potential over the best CoT strategy. The experiments suggest that using naive CoT for retrieval and multi-agent conversation for critique-based diagnosis, GPT-4V can lead to an early and accurate diagnosis of dermatological conditions. The implications of this work extend to improving diagnostic workflows, supporting dermatological education, and enhancing patient care by providing a scalable, accessible, and accurate diagnostic tool.

This study examines the effect of prompt engineering on the performance of Large Language Models (LLMs) in clinical note generation. We introduce an Automatic Prompt Optimization (APO) framework to refine initial prompts and compare the outputs of medical experts, non-medical experts, and APO-enhanced GPT3.5 and GPT4. Results highlight GPT4-APO’s superior performance in standardizing prompt quality across clinical note sections. A human-in-the-loop approach shows that experts maintain content quality post-APO, with a preference for their own modifications, suggesting the value of expert customization. We recommend a two-phase optimization process, leveraging APO-GPT4 for consistency and expert input for personalization.

Large language models (LLMs) have shown remarkable abilities in generating natural texts for various tasks across different domains. However, applying LLMs to clinical settings still poses significant challenges, as it requires specialized knowledge, vocabulary, as well as reliability. In this work, we propose a novel method of instruction fine-tuning for adapting LLMs to the clinical domain, which leverages the instruction-following capabilities of LLMs and the availability of diverse real-world data sources. We generate instructions, inputs, and outputs covering a wide spectrum of clinical services, from primary cares to nursing, radiology, physician, and social work, and use them to fine-tune LLMs. We evaluated the fine-tuned LLM, LlamaCare, on various clinical tasks, such as generating discharge summaries, predicting mortality and length of stay, and more. Using both automatic and human metrics, we demonstrated that LlamaCare surpasses other LLM baselines in predicting clinical outcomes and producing more accurate and coherent clinical texts. We also discuss the challenges and limitations of LLMs that need to be addressed before they can be widely adopted in clinical settings.

Prior research on Twitter (now X) data has provided positive evidence of its utility in developing supplementary health surveillance systems. In this study, we present a new framework to surveil public health, focusing on mental health (MH) outcomes. We hypothesize that locally posted tweets are indicative of local MH outcomes and collect tweets posted from 765 neighborhoods (census block groups) in the USA. We pair these tweets from each neighborhood with the corresponding MH outcome reported by the Center for Disease Control (CDC) to create a benchmark dataset, LocalTweets. With LocalTweets, we present the first population-level evaluation task for Twitter-based MH surveillance systems. We then develop an efficient and effective method, LocalHealth, for predicting MH outcomes based on LocalTweets. When used with GPT3.5, LocalHealth achieves the highest F1-score and accuracy of 0.7429 and 79.78%, respectively, a 59% improvement in F1-score over the GPT3.5 in zero-shot setting. We also utilize LocalHealth to extrapolate CDC’s estimates to proxy unreported neighborhoods, achieving an F1-score of 0.7291. Our work suggests that Twitter data can be effectively leveraged to simulate neighborhood-level MH outcomes.

Visual Word Sense Disambiguation (VWSD) is a task to find the image that most accurately depicts the correct sense of the target word for the given context. Previously, image-text matching models often suffered from recognizing polysemous words. This paper introduces an unsupervised VWSD approach that uses gloss information of an external lexical knowledge-base, especially the sense definitions. Specifically, we suggest employing Bayesian inference to incorporate the sense definitions when sense information of the answer is not provided. In addition, to ameliorate the out-of-dictionary (OOD) issue, we propose a context-aware definition generation with GPT-3. Experimental results show that the VWSD performance significantly increased with our Bayesian inference-based approach. In addition, our context-aware definition generation achieved prominent performance improvement in OOD examples exhibiting better performance than the existing definition generation method.

The potential choices for news article headlines are enormous, and finding the right balance between conveying the essential message and capturing the reader’s attention is key to effective headlining. However, presenting the same news headline to all readers is a suboptimal strategy, because it does not take into account the different preferences and interests of diverse readers, who may be confused about why a particular article has been recommended to them and do not see a clear connection between their interests and the recommended article. In this paper, we present a novel framework that addresses these challenges by incorporating user profiling to generate personalized headlines, and a combination of automated and human evaluation methods to determine user preference for personalized headlines. Our framework utilizes a learnable relevance function to assign personalized signature phrases to users based on their reading histories, which are then used to personalize headline generation. Through extensive evaluation, we demonstrate the effectiveness of our proposed framework in generating personalized headlines that meet the needs of a diverse audience. Our framework has the potential to improve the efficacy of news recommendations and facilitate creation of personalized content.

Voice assistants help users make phone calls, send messages, create events, navigate and do a lot more. However assistants have limited capacity to understand their users’ context. In this work, we aim to take a step in this direction. Our work dives into a new experience for users to refer to phone numbers, addresses, email addresses, urls, and dates on their phone screens. We focus on reference understanding, which is particularly interesting when, similar to visual grounding, there are multiple similar texts on screen. We collect a dataset and propose a lightweight general purpose model for this novel experience. Since consuming pixels directly is expensive, our system is designed to rely only on text extracted from the UI. Our model is modular, offering flexibility, better interpretability and efficient run time memory.

Is the output softmax layer, which is adopted by most language models (LMs), always the best way to compute the next word probability? Given so many attention layers in a modern transformer-based LM, are the pointer networks redundant nowadays? In this study, we discover that the answers to both questions are no. This is because the softmax bottleneck sometimes prevents the LMs from predicting the desired distribution and the pointer networks can be used to break the bottleneck efficiently. Based on the finding, we propose several softmax alternatives by simplifying the pointer networks and accelerating the word-by-word rerankers. In GPT-2, our proposals are significantly better and more efficient than mixture of softmax, a state-of-the-art softmax alternative. In summarization experiments, without very significantly decreasing its training/testing speed, our best method based on T5-Small improves factCC score by 2 points in CNN/DM and XSUM dataset, and improves MAUVE scores by 30% in BookSum paragraph-level dataset.

Large language models (LLMs) can generate natural language texts for various domains and tasks, but their potential for clinical text mining, a domain with scarce, sensitive, and imbalanced medical data, is under-explored. We investigate whether LLMs can augment clinical data for detecting Alzheimer’s Disease (AD)-related signs and symptoms from electronic health records (EHRs), a challenging task that requires high expertise. We create a novel pragmatic taxonomy for AD sign and symptom progression based on expert knowledge and generated three datasets: (1) a gold dataset annotated by human experts on longitudinal EHRs of AD patients; (2) a silver dataset created by the data-to-label method, which labels sentences from a public EHR collection with AD-related signs and symptoms; and (3) a bronze dataset created by the label-to-data method which generates sentences with AD-related signs and symptoms based on the label definition. We train a system to detect AD-related signs and symptoms from EHRs. We find that the silver and bronze datasets improves the system performance, outperforming the system using only the gold dataset. This shows that LLMs can generate synthetic clinical data for a complex task by incorporating expert knowledge, and our label-to-data method can produce datasets that are free of sensitive information, while maintaining acceptable quality.

In the context of a voice assistant system, steering refers to the phenomenon in which a user issues a follow-up command attempting to direct or clarify a previous turn. We propose STEER, a steering detection model that predicts whether a follow-up turn is a user’s attempt to steer the previous command. Constructing a training dataset for steering use cases poses challenges due to the cold-start problem. To overcome this, we developed heuristic rules to sample opt-in usage data, approximating positive and negative samples without any annotation. Our experimental results show promising performance in identifying steering intent, with over 95% accuracy on our sampled data. Moreover, STEER, in conjunction with our sampling strategy, aligns effectively with real-world steering scenarios, as evidenced by its strong zero-shot performance on a human-graded evaluation set. In addition to relying solely on user transcripts as input, we introduce STEER+, an enhanced version of the model. STEER+ utilizes a semantic parse tree to provide more context on out-of-vocabulary words, such as named entities that often occur at the sentence boundary. This further improves model performance, reducing error rate in domains where entities frequently appear, such as messaging. Lastly, we present a data analysis that highlights the improvement in user experience when voice assistants support steering use cases.

This paper presents UMASS_BioNLP team participation in the MEDIQA-Chat 2023 shared task for Task-A and Task-C. We focus especially on Task-C and propose a novel LLMs cooperation system named a doctor-patient loop to generate high-quality conversation data sets. The experiment results demonstrate that our approaches yield reasonable performance as evaluated by automatic metrics such as ROUGE, medical concept recall, BLEU, and Self-BLEU. Furthermore, we conducted a comparative analysis between our proposed method and ChatGPT and GPT-4. This analysis also investigates the potential of utilizing cooperation LLMs to generate high-quality datasets.

A patient portal allows discharged patients to access their personalized discharge instructions in electronic health records (EHRs). However, many patients have difficulty understanding or memorizing their discharge instructions (Zhao et al., 2017). In this paper, we present PaniniQA, a patient-centric interactive question answering system designed to help patients understand their discharge instructions. PaniniQA first identifies important clinical content from patients’ discharge instructions and then formulates patient-specific educational questions. In addition, PaniniQA is also equipped with answer verification functionality to provide timely feedback to correct patients’ misunderstandings. Our comprehensive automatic & human evaluation results demonstrate our PaniniQA is capable of improving patients’ mastery of their medical instructions through effective interactions.1

Answering how-to questions remains a major challenge in question answering research. A vast number of narrow, long-tail questions cannot be readily answered using a search engine. Moreover, there is little to no annotated data available to develop such systems. This paper makes a first attempt at generating coherent, long-form answers for how-to questions. We propose new architectures, consisting of passage retrieval, subtopic planning and narrative generation, to consolidate multiple relevant passages into a coherent, explanatory answer. Our subtopic planning module aims to produce a set of relevant, diverse subtopics that serve as the backbone for answer generation to improve topic coherence. We present extensive experiments on a WikiHow dataset repurposed for long-form question answering. Empirical results demonstrate that generating narratives to answer how-to questions is a challenging task. Nevertheless, our architecture incorporated with subtopic planning can produce high-quality, diverse narratives evaluated using automatic metrics and human assessment.

Suicide is an important public health concern and one of the leading causes of death worldwide. Suicidal behaviors, including suicide attempts (SA) and suicide ideations (SI), are leading risk factors for death by suicide. Information related to patients’ previous and current SA and SI are frequently documented in the electronic health record (EHR) notes. Accurate detection of such documentation may help improve surveillance and predictions of patients’ suicidal behaviors and alert medical professionals for suicide prevention efforts. In this study, we first built Suicide Attempt and Ideation Events (ScAN) dataset, a subset of the publicly available MIMIC III dataset spanning over 12k+ EHR notes with 19k+ annotated SA and SI events information. The annotations also contain attributes such as method of suicide attempt. We also provide a strong baseline model ScANER (Suicide Attempt and Ideation Events Retriever), a multi-task RoBERTa-based model with a retrieval module to extract all the relevant suicidal behavioral evidences from EHR notes of an hospital-stay and, and a prediction module to identify the type of suicidal behavior (SA and SI) concluded during the patient’s stay at the hospital. ScANER achieved a macro-weighted F1-score of 0.83 for identifying suicidal behavioral evidences and a macro F1-score of 0.78 and 0.60 for classification of SA and SI for the patient’s hospital-stay, respectively. ScAN and ScANER are publicly available.

We propose novel AI-empowered chat bots for learning as conversation where a user does not read a passage but gains information and knowledge through conversation with a teacher bot. Our information acquisition-oriented dialogue system employs a novel adaptation of reinforced self-play so that the system can be transferred to various domains without in-domain dialogue data, and can carry out conversations both informative and attentive to users.

This paper proposes a new natural language processing (NLP) application for identifying medical jargon terms potentially difficult for patients to comprehend from electronic health record (EHR) notes. We first present a novel and publicly available dataset with expert-annotated medical jargon terms from 18K+ EHR note sentences (MedJ). Then, we introduce a novel medical jargon extraction (MedJEx) model which has been shown to outperform existing state-of-the-art NLP models. First, MedJEx improved the overall performance when it was trained on an auxiliary Wikipedia hyperlink span dataset, where hyperlink spans provide additional Wikipedia articles to explain the spans (or terms), and then fine-tuned on the annotated MedJ data. Secondly, we found that a contextualized masked language model score was beneficial for detecting domain-specific unfamiliar jargon terms. Moreover, our results show that training on the auxiliary Wikipedia hyperlink span datasets improved six out of eight biomedical named entity recognition benchmark datasets. MedJEx is publicly available.

Automatic International Classification of Diseases (ICD) coding aims to assign multiple ICD codes to a medical note with average length of 3,000+ tokens. This task is challenging due to a high-dimensional space of multi-label assignment (tens of thousands of ICD codes) and the long-tail challenge: only a few codes (common diseases) are frequently assigned while most codes (rare diseases) are infrequently assigned. This study addresses the long-tail challenge by adapting a prompt-based fine-tuning technique with label semantics, which has been shown to be effective under few-shot setting. To further enhance the performance in medical domain, we propose a knowledge-enhanced longformer by injecting three domain-specific knowledge: hierarchy, synonym, and abbreviation with additional pretraining using contrastive learning. Experiments on MIMIC-III-full, a benchmark dataset of code assignment, show that our proposed method outperforms previous state-of-the-art method in 14.5% in marco F1 (from 10.3 to 11.8, P<0.001). To further test our model on few-shot setting, we created a new rare diseases coding dataset, MIMIC-III-rare50, on which our model improves marco F1 from 17.1 to 30.4 and micro F1 from 17.2 to 32.6 compared to previous method.

Pre-trained language models (LMs) have been deployed as the state-of-the-art natural language processing (NLP) approaches for multiple clinical applications. Model generalisability is important in clinical domain due to the low available resources. In this study, we evaluated transfer learning techniques for an important clinical application: detecting suicide attempt (SA) and suicide ideation (SI) in electronic health records (EHRs). Using the annotation guideline provided by the authors of ScAN, we annotated two EHR datasets from different hospitals. We then fine-tuned ScANER, a publicly available SA and SI detection model, to evaluate five different parameter efficient transfer learning techniques, such as adapter-based learning and soft-prompt tuning, on the two datasets. Without any fine-tuning, ScANER achieve macro F1-scores of 0.85 and 0.87 for SA and SI evidence detection across the two datasets. We observed that by fine-tuning less than ~2% of ScANER’s parameters, we were able to further improve the macro F1-score for SA-SI evidence detection by 3% and 5% for the two EHR datasets. Our results show that parameter-efficient transfer learning methods can help improve the performance of publicly available clinical models on new hospital datasets with few annotations.

An after-visit summary (AVS) is a summary note given to patients after their clinical visit. It recaps what happened during their clinical visit and guides patients’ disease self-management. Studies have shown that a majority of patients found after-visit summaries useful. However, many physicians face excessive workloads and do not have time to write clear and informative summaries. In this paper, we study the problem of automatic generation of after-visit summaries and examine whether those summaries can convey the gist of clinical visits. We report our findings on a new clinical dataset that contains a large number of electronic health record (EHR) notes and their associated summaries. Our results suggest that generation of lay language after-visit summaries remains a challenging task. Crucially, we introduce a feedback mechanism that alerts physicians when an automatic summary fails to capture the important details of the clinical notes or when it contains hallucinated facts that are potentially detrimental to the summary quality. Automatic and human evaluation demonstrates the effectiveness of our approach in providing writing feedback and supporting physicians.

Models pre-trained on large-scale regular text corpora often do not work well for user-generated data where the language styles differ significantly from the mainstream text. Here we present Context-Aware Rule Injection (CARI), an innovative method for formality style transfer (FST) by injecting multiple rules into an end-to-end BERT-based encoder and decoder model. CARI is able to learn to select optimal rules based on context. The intrinsic evaluation showed that CARI achieved the new highest performance on the FST benchmark dataset. Our extrinsic evaluation showed that CARI can greatly improve the regular pre-trained models’ performance on several tweet sentiment analysis tasks. Our contributions are as follows: 1.We propose a new method, CARI, to integrate rules for pre-trained language models. CARI is context-aware and can trained end-to-end with the downstream NLP applications. 2.We have achieved new state-of-the-art results for FST on the benchmark GYAFC dataset. 3.We are the first to evaluate FST methods with extrinsic evaluation and specifically on sentiment classification tasks. We show that CARI outperformed existing rule-based FST approaches for sentiment classification.

Anaphora and ellipses are two common phenomena in dialogues. Without resolving referring expressions and information omission, dialogue systems may fail to generate consistent and coherent responses. Traditionally, anaphora is resolved by coreference resolution and ellipses by query rewrite. In this work, we propose a novel joint learning framework of modeling coreference resolution and query rewriting for complex, multi-turn dialogue understanding. Given an ongoing dialogue between a user and a dialogue assistant, for the user query, our joint learning model first predicts coreference links between the query and the dialogue context, and then generates a self-contained rewritten user query. To evaluate our model, we annotate a dialogue based coreference resolution dataset, MuDoCo, with rewritten queries. Results show that the performance of query rewrite can be substantially boosted (+2.3% F1) with the aid of coreference modeling. Furthermore, our joint model outperforms the state-of-the-art coreference resolution model (+2% F1) on this dataset.

Conversational Machine Comprehension (CMC), a research track in conversational AI, expects the machine to understand an open-domain natural language text and thereafter engage in a multi-turn conversation to answer questions related to the text. While most of the research in Machine Reading Comprehension (MRC) revolves around single-turn question answering (QA), multi-turn CMC has recently gained prominence, thanks to the advancement in natural language understanding via neural language models such as BERT and the introduction of large-scale conversational datasets such as CoQA and QuAC. The rise in interest has, however, led to a flurry of concurrent publications, each with a different yet structurally similar modeling approach and an inconsistent view of the surrounding literature. With the volume of model submissions to conversational datasets increasing every year, there exists a need to consolidate the scattered knowledge in this domain to streamline future research. This literature review attempts at providing a holistic overview of CMC with an emphasis on the common trends across recently published models, specifically in their approach to tackling conversational history. The review synthesizes a generic framework for CMC models while highlighting the differences in recent approaches and intends to serve as a compendium of CMC for future researchers.

We address the problem of calibrating prediction confidence for output entities of interest in natural language processing (NLP) applications. It is important that NLP applications such as named entity recognition and question answering produce calibrated confidence scores for their predictions, especially if the applications are to be deployed in a safety-critical domain such as healthcare. However the output space of such structured prediction models are often too large to directly adapt binary or multi-class calibration methods. In this study, we propose a general calibration scheme for output entities of interest in neural network based structured prediction models. Our proposed method can be used with any binary class calibration scheme and a neural network model. Additionally, we show that our calibration method can also be used as an uncertainty-aware, entity-specific decoding step to improve the performance of the underlying model at no additional training cost or data requirements. We show that our method outperforms current calibration techniques for Named Entity Recognition, Part-of-speech tagging and Question Answering systems. We also observe an improvement in model performance from our decoding step across several tasks and benchmark datasets. Our method improves the calibration and model performance on out-of-domain test scenarios as well.

CodaLab is an open-source web-based platform for collaborative computational research. Although CodaLab has gained popularity in the research community, its interface has limited support for creating reusable tools that can be easily applied to new datasets and composed into pipelines. In clinical domain, natural language processing (NLP) on medical notes generally involves multiple steps, like tokenization, named entity recognition, etc. Since these steps require different tools which are usually scattered in different publications, it is not easy for researchers to use them to process their own datasets. In this paper, we present BENTO, a workflow management platform with a graphic user interface (GUI) that is built on top of CodaLab, to facilitate the process of building clinical NLP pipelines. BENTO comes with a number of clinical NLP tools that have been pre-trained using medical notes and expert annotations and can be readily used for various clinical NLP tasks. It also allows researchers and developers to create their custom tools (e.g., pre-trained NLP models) and use them in a controlled and reproducible way. In addition, the GUI interface enables researchers with limited computer background to compose tools into NLP pipelines and then apply the pipelines on their own datasets in a “what you see is what you get” (WYSIWYG) way. Although BENTO is designed for clinical NLP applications, the underlying architecture is flexible to be tailored to any other domains.

Curriculum learning methods typically rely on heuristics to estimate the difficulty of training examples or the ability of the model. In this work, we propose replacing difficulty heuristics with learned difficulty parameters. We also propose Dynamic Data selection for Curriculum Learning via Ability Estimation (DDaCLAE), a strategy that probes model ability at each training epoch to select the best training examples at that point. We show that models using learned difficulty and/or ability outperform heuristic-based curriculum learning models on the GLUE classification tasks.

One of the fundamental goals of artificial intelligence is to build computer-based expert systems. Inferring clinical diagnoses to generate a clinical assessment during a patient encounter is a crucial step towards building a medical diagnostic system. Previous works were mainly based on either medical domain-specific knowledge, or patients’ prior diagnoses and clinical encounters. In this paper, we propose a novel model for automated clinical assessment generation (MCAG). MCAG is built on an innovative graph neural network, where rich clinical knowledge is incorporated into an end-to-end corpus-learning system. Our evaluation results against physician generated gold standard show that MCAG significantly improves the BLEU and rouge score compared with competitive baseline models. Further, physicians’ evaluation showed that MCAG could generate high-quality assessments.

We consider a new perspective on dialog state tracking (DST), the task of estimating a user’s goal through the course of a dialog. By formulating DST as a semantic parsing task over hierarchical representations, we can incorporate semantic compositionality, cross-domain knowledge sharing and co-reference. We present TreeDST, a dataset of 27k conversations annotated with tree-structured dialog states and system acts. We describe an encoder-decoder framework for DST with hierarchical representations, which leads to ~20% improvement over state-of-the-art DST approaches that operate on a flat meaning space of slot-value pairs.

Incorporating Item Response Theory (IRT) into NLP tasks can provide valuable information about model performance and behavior. Traditionally, IRT models are learned using human response pattern (RP) data, presenting a significant bottleneck for large data sets like those required for training deep neural networks (DNNs). In this work we propose learning IRT models using RPs generated from artificial crowds of DNN models. We demonstrate the effectiveness of learning IRT models using DNN-generated data through quantitative and qualitative analyses for two NLP tasks. Parameters learned from human and machine RPs for natural language inference and sentiment analysis exhibit medium to large positive correlations. We demonstrate a use-case for latent difficulty item parameters, namely training set filtering, and show that using difficulty to sample training data outperforms baseline methods. Finally, we highlight cases where human expectation about item difficulty does not match difficulty as estimated from the machine RPs.

Classical Chinese poetry is a jewel in the treasure house of Chinese culture. Previous poem generation models only allow users to employ keywords to interfere the meaning of generated poems, leaving the dominion of generation to the model. In this paper, we propose a novel task of generating classical Chinese poems from vernacular, which allows users to have more control over the semantic of generated poems. We adapt the approach of unsupervised machine translation (UMT) to our task. We use segmentation-based padding and reinforcement learning to address under-translation and over-translation respectively. According to experiments, our approach significantly improve the perplexity and BLEU compared with typical UMT models. Furthermore, we explored guidelines on how to write the input vernacular to generate better poems. Human evaluation showed our approach can generate high-quality poems which are comparable to amateur poems.

abstract In this article, we describe our approach for the Bacteria Biotopes relation extraction (BB-rel) subtask in the BioNLP Shared Task 2019. This task aims to promote the development of text mining systems that extract relationships between Microorganism, Habitat and Phenotype entities. In this paper, we propose a novel approach for dependency graph construction based on lexical chains, so one dependency graph can represent one or multiple sentences. After that, we propose a neural network model which consists of the bidirectional long short-term memories and an attention graph convolution neural network to learn relation extraction features from the graph. Our approach is able to extract both intra- and inter-sentence relations, and meanwhile utilize syntax information. The results show that our approach achieved the best F1 (66.3%) in the official evaluation participated by 7 teams.

Sentence simplification aims to simplify the content and structure of complex sentences, and thus make them easier to interpret for human readers, and easier to process for downstream NLP applications. Recent advances in neural machine translation have paved the way for novel approaches to the task. In this paper, we adapt an architecture with augmented memory capacities called Neural Semantic Encoders (Munkhdalai and Yu, 2017) for sentence simplification. Our experiments demonstrate the effectiveness of our approach on different simplification datasets, both in terms of automatic evaluation measures and human judgments.

Interpreting the performance of deep learning models beyond test set accuracy is challenging. Characteristics of individual data points are often not considered during evaluation, and each data point is treated equally. In this work we examine the impact of a test set question’s difficulty to determine if there is a relationship between difficulty and performance. We model difficulty using well-studied psychometric methods on human response patterns. Experiments on Natural Language Inference (NLI) and Sentiment Analysis (SA) show that the likelihood of answering a question correctly is impacted by the question’s difficulty. In addition, as DNNs are trained on larger datasets easy questions start to have a higher probability of being answered correctly than harder questions.

Recurrent neural networks (RNNs) process input text sequentially and model the conditional transition between word tokens. In contrast, the advantages of recursive networks include that they explicitly model the compositionality and the recursive structure of natural language. However, the current recursive architecture is limited by its dependence on syntactic tree. In this paper, we introduce a robust syntactic parsing-independent tree structured model, Neural Tree Indexers (NTI) that provides a middle ground between the sequential RNNs and the syntactic treebased recursive models. NTI constructs a full n-ary tree by processing the input text with its node function in a bottom-up fashion. Attention mechanism can then be applied to both structure and node function. We implemented and evaluated a binary tree model of NTI, showing the model achieved the state-of-the-art performance on three different NLP tasks: natural language inference, answer sentence selection, and sentence classification, outperforming state-of-the-art recurrent and recursive neural networks.

We present a memory augmented neural network for natural language understanding: Neural Semantic Encoders. NSE is equipped with a novel memory update rule and has a variable sized encoding memory that evolves over time and maintains the understanding of input sequences through read, compose and write operations. NSE can also access 1 multiple and shared memories. In this paper, we demonstrated the effectiveness and the flexibility of NSE on five different natural language tasks: natural language inference, question answering, sentence classification, document sentiment analysis and machine translation where NSE achieved state-of-the-art performance when evaluated on publically available benchmarks. For example, our shared-memory model showed an encouraging result on neural machine translation, improving an attention-based baseline by approximately 1.0 BLEU.