Recent data-driven conversational models are able to return fluent, consistent, and informative responses to many kinds of requests and utterances in task-oriented scenarios. However, these responses are typically limited to just the immediate local topic instead of being wider-ranging and proactively taking the conversation further, for example making suggestions to help customers achieve their goals. This inadequacy reflects a lack of understanding of the interlocutor’s situation and implicit goal. To address the problem, we introduce a task of proactive response selection based on situational information. We present a manually-curated dataset of 1.7k English conversation examples that include situational background information plus for each conversation a set of responses, only some of which are acceptable in the situation. A responsive and informed conversation system should select the appropriate responses and avoid inappropriate ones; doing so demonstrates the ability to adequately understand the initiating request and situation. Our benchmark experiments show that this is not an easy task even for strong neural models, offering opportunities for future research.

Collecting labeled data for Named Entity Recognition (NER) tasks is challenging due to the high cost of manual annotations. Instead, researchers have proposed few-shot self-training and rule-augmentation techniques to minimize the reliance on large datasets. However, inductive biases and restricted logical language lexicon, respectively, can limit the ability of these models to perform well. In this work, we propose CoAug, a co-augmentation framework that allows us to improve few-shot models and rule-augmentation models by bootstrapping predictions from each model. By leveraging rules and neural model predictions to train our models, we complement the benefits of each and achieve the best of both worlds. In our experiments, we show that our best CoAug model can outperform strong weak-supervision-based NER models at least by 6.5 F1 points.

Hallucination is a well-known phenomenon in text generated by large language models (LLMs). The existence of hallucinatory responses is found in almost all application scenarios e.g., summarization, question-answering (QA) etc. For applications requiring high reliability (e.g., customer-facing assistants), the potential existence of hallucination in LLM-generated text is a critical problem. The amount of hallucination can be reduced by leveraging information retrieval to provide relevant background information to the LLM. However, LLMs can still generate hallucinatory content for various reasons (e.g., prioritizing its parametric knowledge over the context, failure to capture the relevant information from the context, etc.). Detecting hallucinations through automated methods is thus paramount. To facilitate research in this direction, we introduce a sophisticated dataset, DelucionQA, that captures hallucinations made by retrieval-augmented LLMs for a domain-specific QA task. Furthermore, we propose a set of hallucination detection methods to serve as baselines for future works from the research community. Analysis and case study are also provided to share valuable insights on hallucination phenomena in the target scenario.

Prompting pre-trained language models leads to promising results across natural language processing tasks but is less effective when applied in low-resource domains, due to the domain gap between the pre-training data and the downstream task. In this work, we bridge this gap with a novel and lightweight prompting methodology called SwitchPrompt for the adaptation of language models trained on datasets from the general domain to diverse low-resource domains. Using domain-specific keywords with a trainable gated prompt, SwitchPrompt offers domain-oriented prompting, that is, effective guidance on the target domains for general-domain language models. Our few-shot experiments on three text classification benchmarks demonstrate the efficacy of the general-domain pre-trained language models when used with SwitchPrompt. They often even outperform their domain-specific counterparts trained with baseline state-of-the-art prompting methods by up to 10.7% performance increase in accuracy. This result indicates that SwitchPrompt effectively reduces the need for domain-specific language model pre-training.

Advances of open-domain conversational systems have been achieved through the creation of numerous conversation datasets. However, many of the commonly used datasets contain little or no information about the conversational situation, such as relevant objects/people, their properties, and relationships. This absence leads to underspecification of the problem space and typically results in undesired dialogue system behavior. This position paper discusses the current state of the field associated with processing situational information. An analysis of response generation using three datasets shows that explicitly provided situational information can improve the coherence and specificity of generated responses, but further experiments reveal that generation systems can be misled by irrelevant information. Our conclusions from this evaluation provide insights into the problem and directions for future research.

Explanations accompanying a recommendation can assist users in understanding the decision made by recommendation systems, which in turn increases a user’s confidence and trust in the system. Recently, research has focused on generating natural language explanations in a human-readable format. Thus far, the proposed approaches leverage item reviews written by users, which are often subjective, sparse in language, and unable to account for new items that have not been purchased or reviewed before. Instead, we aim to generate fact-grounded recommendation explanations that are objectively described with item features while implicitly considering a user’s preferences, based on the user’s purchase history. To achieve this, we propose a knowledge graph (KG) approach to natural language explainable recommendation. Our approach draws on user-item features through a novel collaborative filtering-based KG representation to produce fact-grounded, personalized explanations, while jointly learning user-item representations for recommendation scoring. Experimental results show that our approach consistently outperforms previous state-of-the-art models on natural language explainable recommendation metrics.

Systems for knowledge-intensive tasks such as open-domain question answering (QA) usually consist of two stages: efficient retrieval of relevant documents from a large corpus and detailed reading of the selected documents. This is usually done through two separate models, a retriever that encodes the query and finds nearest neighbors, and a reader based on Transformers. These two components are usually modeled separately, which necessitates a cumbersome implementation and is awkward to optimize in an end-to-end fashion. In this paper, we revisit this design and eschew the separate architecture and training in favor of a single Transformer that performs retrieval as attention (RAA), and end-to-end training solely based on supervision from the end QA task. We demonstrate for the first time that an end-to-end trained single Transformer can achieve both competitive retrieval and QA performance on in-domain datasets, matching or even slightly outperforming state-of-the-art dense retrievers and readers. Moreover, end-to-end adaptation of our model significantly boosts its performance on out-of-domain datasets in both supervised and unsupervised settings, making our model a simple and adaptable end-to-end solution for knowledge-intensive tasks.

Generative question answering (QA) models generate answers to questions either solely based on the parameters of the model (the closed-book setting) or additionally retrieving relevant evidence (the open-book setting). Generative QA models can answer some relatively complex questions, but the mechanism through which they do so is still poorly understood. We perform several studies aimed at better understanding the multi-hop reasoning capabilities of generative QA models. First, we decompose multi-hop questions into multiple corresponding single-hop questions, and find marked inconsistency in QA models’ answers on these pairs of ostensibly identical question chains. Second, we find that models lack zero-shot multi-hop reasoning ability: when trained only on single-hop questions, models generalize poorly to multi-hop questions. Finally, we demonstrate that it is possible to improve models’ zero-shot multi-hop reasoning capacity through two methods that approximate real multi-hop natural language (NL) questions by training on either concatenation of single-hop questions or logical forms (SPARQL). In sum, these results demonstrate that multi-hop reasoning does not emerge naturally in generative QA models, but can be encouraged by advances in training or modeling techniques. Code is available at https://github.com/jzbjyb/multihop.

Named entity recognition (NER) is well studied for the general domain, and recent systems have achieved human-level performance for identifying common entity types. However, the NER performance is still moderate for specialized domains that tend to feature complicated contexts and jargonistic entity types. To address these challenges, we propose explicitly connecting entity mentions based on both global coreference relations and local dependency relations for building better entity mention representations. In our experiments, we incorporate entity mention relations by Graph Neural Networks and show that our system noticeably improves the NER performance on two datasets from different domains. We further show that the proposed lightweight system can effectively elevate the NER performance to a higher level even when only a tiny amount of labeled data is available, which is desirable for domain-specific NER.

Recent works have shown that language models (LM) capture different types of knowledge regarding facts or common sense. However, because no model is perfect, they still fail to provide appropriate answers in many cases. In this paper, we ask the question, “How can we know when language models know, with confidence, the answer to a particular query?” We examine this question from the point of view of calibration, the property of a probabilistic model’s predicted probabilities actually being well correlated with the probabilities of correctness. We examine three strong generative models—T5, BART, and GPT-2—and study whether their probabilities on QA tasks are well calibrated, finding the answer is a relatively emphatic no. We then examine methods to calibrate such models to make their confidence scores correlate better with the likelihood of correctness through fine-tuning, post-hoc probability modification, or adjustment of the predicted outputs or inputs. Experiments on a diverse range of datasets demonstrate the effectiveness of our methods. We also perform analysis to study the strengths and limitations of these methods, shedding light on further improvements that may be made in methods for calibrating LMs. We have released the code at https://github.com/jzbjyb/lm-calibration.

Natural language processing covers a wide variety of tasks predicting syntax, semantics, and information content, and usually each type of output is generated with specially designed architectures. In this paper, we provide the simple insight that a great variety of tasks can be represented in a single unified format consisting of labeling spans and relations between spans, thus a single task-independent model can be used across different tasks. We perform extensive experiments to test this insight on 10 disparate tasks spanning dependency parsing (syntax), semantic role labeling (semantics), relation extraction (information content), aspect based sentiment analysis (sentiment), and many others, achieving performance comparable to state-of-the-art specialized models. We further demonstrate benefits of multi-task learning, and also show that the proposed method makes it easy to analyze differences and similarities in how the model handles different tasks. Finally, we convert these datasets into a unified format to build a benchmark, which provides a holistic testbed for evaluating future models for generalized natural language analysis.

Recent work has presented intriguing results examining the knowledge contained in language models (LMs) by having the LM fill in the blanks of prompts such as “Obama is a __ by profession”. These prompts are usually manually created, and quite possibly sub-optimal; another prompt such as “Obama worked as a __ ” may result in more accurately predicting the correct profession. Because of this, given an inappropriate prompt, we might fail to retrieve facts that the LM does know, and thus any given prompt only provides a lower bound estimate of the knowledge contained in an LM. In this paper, we attempt to more accurately estimate the knowledge contained in LMs by automatically discovering better prompts to use in this querying process. Specifically, we propose mining-based and paraphrasing-based methods to automatically generate high-quality and diverse prompts, as well as ensemble methods to combine answers from different prompts. Extensive experiments on the LAMA benchmark for extracting relational knowledge from LMs demonstrate that our methods can improve accuracy from 31.1% to 39.6%, providing a tighter lower bound on what LMs know. We have released the code and the resulting LM Prompt And Query Archive (LPAQA) at https://github.com/jzbjyb/LPAQA.

Language models (LMs) have proven surprisingly successful at capturing factual knowledge by completing cloze-style fill-in-the-blank questions such as “Punta Cana is located in _.” However, while knowledge is both written and queried in many languages, studies on LMs’ factual representation ability have almost invariably been performed on English. To assess factual knowledge retrieval in LMs in different languages, we create a multilingual benchmark of cloze-style probes for typologically diverse languages. To properly handle language variations, we expand probing methods from single- to multi-word entities, and develop several decoding algorithms to generate multi-token predictions. Extensive experimental results provide insights about how well (or poorly) current state-of-the-art LMs perform at this task in languages with more or fewer available resources. We further propose a code-switching-based method to improve the ability of multilingual LMs to access knowledge, and verify its effectiveness on several benchmark languages. Benchmark data and code have be released at https://x-factr.github.io.

This paper introduces open-domain event detection, a new event detection paradigm to address issues of prior work on restricted domains and event annotation. The goal is to detect all kinds of events regardless of domains. Given the absence of training data, we propose a distant supervision method that is able to generate high-quality training data. Using a manually annotated event corpus as gold standard, our experiments show that despite no direct supervision, the model outperforms supervised models. This result indicates that the distant supervision enables robust event detection in various domains, while obviating the need for human annotation of events.

We present a novel approach to automated question generation that improves upon prior work both from a technology perspective and from an assessment perspective. Our system is aimed at engaging language learners by generating multiple-choice questions which utilize specific inference steps over multiple sentences, namely coreference resolution and paraphrase detection. The system also generates correct answers and semantically-motivated phrase-level distractors as answer choices. Evaluation by human annotators indicates that our approach requires a larger number of inference steps, which necessitate deeper semantic understanding of texts than a traditional single-sentence approach.

Event coreference is an important task for full text analysis. However, previous work uses a variety of approaches, sources and evaluation, making the literature confusing and the results incommensurate. We provide a description of the differences to facilitate future research. Second, we present a supervised method for event coreference resolution that uses a rich feature set and propagates information alternatively between events and their arguments, adapting appropriately for each type of argument.

In the task of event coreference resolution, recent work has shown the need to perform not only full coreference but also partial coreference of events. We show that subevents can form a particular hierarchical event structure. This paper examines a novel two-stage approach to finding and improving subevent structures. First, we introduce a multiclass logistic regression model that can detect subevent relations in addition to full coreference. Second, we propose a method to improve subevent structure based on subevent clusters detected by the model. Using a corpus in the Intelligence Community domain, we show that the method achieves over 3.2 BLANC F1 gain in detecting subevent relations against the logistic regression model.