Walter Chang


2021

pdf bib
UCSD-Adobe at MEDIQA 2021: Transfer Learning and Answer Sentence Selection for Medical Summarization
Khalil Mrini | Franck Dernoncourt | Seunghyun Yoon | Trung Bui | Walter Chang | Emilia Farcas | Ndapa Nakashole
Proceedings of the 20th Workshop on Biomedical Language Processing

In this paper, we describe our approach to question summarization and multi-answer summarization in the context of the 2021 MEDIQA shared task (Ben Abacha et al., 2021). We propose two kinds of transfer learning for the abstractive summarization of medical questions. First, we train on HealthCareMagic, a large question summarization dataset collected from an online healthcare service platform. Second, we leverage the ability of the BART encoder-decoder architecture to model both generation and classification tasks to train on the task of Recognizing Question Entailment (RQE) in the medical domain. We show that both transfer learning methods combined achieve the highest ROUGE scores. Finally, we cast the question-driven extractive summarization of multiple relevant answer documents as an Answer Sentence Selection (AS2) problem. We show how we can preprocess the MEDIQA-AnS dataset such that it can be trained in an AS2 setting. Our AS2 model is able to generate extractive summaries achieving high ROUGE scores.

pdf bib
Joint Summarization-Entailment Optimization for Consumer Health Question Understanding
Khalil Mrini | Franck Dernoncourt | Walter Chang | Emilia Farcas | Ndapa Nakashole
Proceedings of the Second Workshop on Natural Language Processing for Medical Conversations

Understanding the intent of medical questions asked by patients, or Consumer Health Questions, is an essential skill for medical Conversational AI systems. We propose a novel data-augmented and simple joint learning approach combining question summarization and Recognizing Question Entailment (RQE) in the medical domain. Our data augmentation approach enables to use just one dataset for joint learning. We show improvements on both tasks across four biomedical datasets in accuracy (+8%), ROUGE-1 (+2.5%) and human evaluation scores. Human evaluation shows joint learning generates faithful and informative summaries. Finally, we release our code, the two question summarization datasets extracted from a large-scale medical dialogue dataset, as well as our augmented datasets.

pdf bib
Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning
Jianguo Zhang | Trung Bui | Seunghyun Yoon | Xiang Chen | Zhiwei Liu | Congying Xia | Quan Hung Tran | Walter Chang | Philip Yu
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

In this work, we focus on a more challenging few-shot intent detection scenario where many intents are fine-grained and semantically similar. We present a simple yet effective few-shot intent detection schema via contrastive pre-training and fine-tuning. Specifically, we first conduct self-supervised contrastive pre-training on collected intent datasets, which implicitly learns to discriminate semantically similar utterances without using any labels. We then perform few-shot intent detection together with supervised contrastive learning, which explicitly pulls utterances from the same intent closer and pushes utterances across different intents farther. Experimental results show that our proposed method achieves state-of-the-art performance on three challenging intent detection datasets under 5-shot and 10-shot settings.

pdf bib
StreamHover: Livestream Transcript Summarization and Annotation
Sangwoo Cho | Franck Dernoncourt | Tim Ganter | Trung Bui | Nedim Lipka | Walter Chang | Hailin Jin | Jonathan Brandt | Hassan Foroosh | Fei Liu
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

With the explosive growth of livestream broadcasting, there is an urgent need for new summarization technology that enables us to create a preview of streamed content and tap into this wealth of knowledge. However, the problem is nontrivial due to the informal nature of spoken language. Further, there has been a shortage of annotated datasets that are necessary for transcript summarization. In this paper, we present StreamHover, a framework for annotating and summarizing livestream transcripts. With a total of over 500 hours of videos annotated with both extractive and abstractive summaries, our benchmark dataset is significantly larger than currently existing annotated corpora. We explore a neural extractive summarization model that leverages vector-quantized variational autoencoder to learn latent vector representations of spoken utterances and identify salient utterances from the transcripts to form summaries. We show that our model generalizes better and improves performance over strong baselines. The results of this study provide an avenue for future research to improve summarization solutions for efficient browsing of livestreams.

pdf bib
A Context-Dependent Gated Module for Incorporating Symbolic Semantics into Event Coreference Resolution
Tuan Lai | Heng Ji | Trung Bui | Quan Hung Tran | Franck Dernoncourt | Walter Chang
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Event coreference resolution is an important research problem with many applications. Despite the recent remarkable success of pre-trained language models, we argue that it is still highly beneficial to utilize symbolic features for the task. However, as the input for coreference resolution typically comes from upstream components in the information extraction pipeline, the automatically extracted symbolic features can be noisy and contain errors. Also, depending on the specific context, some features can be more informative than others. Motivated by these observations, we propose a novel context-dependent gated module to adaptively control the information flows from the input symbolic features. Combined with a simple noisy training method, our best models achieve state-of-the-art results on two datasets: ACE 2005 and KBP 2016.

pdf bib
MadDog: A Web-based System for Acronym Identification and Disambiguation
Amir Pouran Ben Veyseh | Franck Dernoncourt | Walter Chang | Thien Huu Nguyen
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations

Acronyms and abbreviations are the short-form of longer phrases and they are ubiquitously employed in various types of writing. Despite their usefulness to save space in writing and reader’s time in reading, they also provide challenges for understanding the text especially if the acronym is not defined in the text or if it is used far from its definition in long texts. To alleviate this issue, there are considerable efforts both from the research community and software developers to build systems for identifying acronyms and finding their correct meanings in the text. However, none of the existing works provide a unified solution capable of processing acronyms in various domains and to be publicly available. Thus, we provide the first web-based acronym identification and disambiguation system which can process acronyms from various domains including scientific, biomedical, and general domains. The web-based system is publicly available at http://iq.cs.uoregon.edu:5000 and a demo video is available at https://youtu.be/IkSh7LqI42M. The system source code is also available at https://github.com/amirveyseh/MadDog.

pdf bib
A Gradually Soft Multi-Task and Data-Augmented Approach to Medical Question Understanding
Khalil Mrini | Franck Dernoncourt | Seunghyun Yoon | Trung Bui | Walter Chang | Emilia Farcas | Ndapa Nakashole
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Users of medical question answering systems often submit long and detailed questions, making it hard to achieve high recall in answer retrieval. To alleviate this problem, we propose a novel Multi-Task Learning (MTL) method with data augmentation for medical question understanding. We first establish an equivalence between the tasks of question summarization and Recognizing Question Entailment (RQE) using their definitions in the medical domain. Based on this equivalence, we propose a data augmentation algorithm to use just one dataset to optimize for both tasks, with a weighted MTL loss. We introduce gradually soft parameter-sharing: a constraint for decoder parameters to be close, that is gradually loosened as we move to the highest layer. We show through ablation studies that our proposed novelties improve performance. Our method outperforms existing MTL methods across 4 datasets of medical question pairs, in ROUGE scores, RQE accuracy and human evaluation. Finally, we show that our method fares better than single-task learning under 4 low-resource settings.

2020

pdf bib
Understanding Points of Correspondence between Sentences for Abstractive Summarization
Logan Lebanoff | John Muchovej | Franck Dernoncourt | Doo Soon Kim | Lidan Wang | Walter Chang | Fei Liu
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop

Fusing sentences containing disparate content is a remarkable human ability that helps create informative and succinct summaries. Such a simple task for humans has remained challenging for modern abstractive summarizers, substantially restricting their applicability in real-world scenarios. In this paper, we present an investigation into fusing sentences drawn from a document by introducing the notion of points of correspondence, which are cohesive devices that tie any two sentences together into a coherent text. The types of points of correspondence are delineated by text cohesion theory, covering pronominal and nominal referencing, repetition and beyond. We create a dataset containing the documents, source and fusion sentences, and human annotations of points of correspondence between sentences. Our dataset bridges the gap between coreference resolution and summarization. It is publicly shared to serve as a basis for future work to measure the success of sentence fusion systems.

pdf bib
Variational Hierarchical Dialog Autoencoder for Dialog State Tracking Data Augmentation
Kang Min Yoo | Hanbit Lee | Franck Dernoncourt | Trung Bui | Walter Chang | Sang-goo Lee
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Recent works have shown that generative data augmentation, where synthetic samples generated from deep generative models complement the training dataset, benefit NLP tasks. In this work, we extend this approach to the task of dialog state tracking for goaloriented dialogs. Due to the inherent hierarchical structure of goal-oriented dialogs over utterances and related annotations, the deep generative model must be capable of capturing the coherence among different hierarchies and types of dialog features. We propose the Variational Hierarchical Dialog Autoencoder (VHDA) for modeling the complete aspects of goal-oriented dialogs, including linguistic features and underlying structured annotations, namely speaker information, dialog acts, and goals. The proposed architecture is designed to model each aspect of goal-oriented dialogs using inter-connected latent variables and learns to generate coherent goal-oriented dialogs from the latent spaces. To overcome training issues that arise from training complex variational models, we propose appropriate training strategies. Experiments on various dialog datasets show that our model improves the downstream dialog trackers’ robustness via generative data augmentation. We also discover additional benefits of our unified approach to modeling goal-oriented dialogs – dialog response generation and user simulation, where our model outperforms previous strong baselines.

pdf bib
Learning to Fuse Sentences with Transformers for Summarization
Logan Lebanoff | Franck Dernoncourt | Doo Soon Kim | Lidan Wang | Walter Chang | Fei Liu
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

The ability to fuse sentences is highly attractive for summarization systems because it is an essential step to produce succinct abstracts. However, to date, summarizers can fail on fusing sentences. They tend to produce few summary sentences by fusion or generate incorrect fusions that lead the summary to fail to retain the original meaning. In this paper, we explore the ability of Transformers to fuse sentences and propose novel algorithms to enhance their ability to perform sentence fusion by leveraging the knowledge of points of correspondence between sentences. Through extensive experiments, we investigate the effects of different design choices on Transformer’s performance. Our findings highlight the importance of modeling points of correspondence between sentences for effective sentence fusion.

pdf bib
A Cascade Approach to Neural Abstractive Summarization with Content Selection and Fusion
Logan Lebanoff | Franck Dernoncourt | Doo Soon Kim | Walter Chang | Fei Liu
Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing

We present an empirical study in favor of a cascade architecture to neural text summarization. Summarization practices vary widely but few other than news summarization can provide a sufficient amount of training data enough to meet the requirement of end-to-end neural abstractive systems which perform content selection and surface realization jointly to generate abstracts. Such systems also pose a challenge to summarization evaluation, as they force content selection to be evaluated along with text generation, yet evaluation of the latter remains an unsolved problem. In this paper, we present empirical results showing that the performance of a cascaded pipeline that separately identifies important content pieces and stitches them together into a coherent text is comparable to or outranks that of end-to-end systems, whereas a pipeline architecture allows for flexible content selection. We finally discuss how we can take advantage of a cascaded pipeline in neural text summarization and shed light on important directions for future research.

pdf bib
Rethinking Self-Attention: Towards Interpretability in Neural Parsing
Khalil Mrini | Franck Dernoncourt | Quan Hung Tran | Trung Bui | Walter Chang | Ndapa Nakashole
Findings of the Association for Computational Linguistics: EMNLP 2020

Attention mechanisms have improved the performance of NLP tasks while allowing models to remain explainable. Self-attention is currently widely used, however interpretability is difficult due to the numerous attention distributions. Recent work has shown that model representations can benefit from label-specific information, while facilitating interpretation of predictions. We introduce the Label Attention Layer: a new form of self-attention where attention heads represent labels. We test our novel layer by running constituency and dependency parsing experiments and show our new model obtains new state-of-the-art results for both tasks on both the Penn Treebank (PTB) and Chinese Treebank. Additionally, our model requires fewer self-attention layers compared to existing work. Finally, we find that the Label Attention heads learn relations between syntactic categories and show pathways to analyze errors.

pdf bib
Scene Graph Modification Based on Natural Language Commands
Xuanli He | Quan Hung Tran | Gholamreza Haffari | Walter Chang | Zhe Lin | Trung Bui | Franck Dernoncourt | Nhan Dam
Findings of the Association for Computational Linguistics: EMNLP 2020

Structured representations like graphs and parse trees play a crucial role in many Natural Language Processing systems. In recent years, the advancements in multi-turn user interfaces necessitate the need for controlling and updating these structured representations given new sources of information. Although there have been many efforts focusing on improving the performance of the parsers that map text to graphs or parse trees, very few have explored the problem of directly manipulating these representations. In this paper, we explore the novel problem of graph modification, where the systems need to learn how to update an existing scene graph given a new user’s command. Our novel models based on graph-based sparse transformer and cross attention information fusion outperform previous systems adapted from the machine translation and graph generation literature. We further contribute our large graph modification datasets to the research community to encourage future research for this new problem.

2019

pdf bib
Analyzing Sentence Fusion in Abstractive Summarization
Logan Lebanoff | John Muchovej | Franck Dernoncourt | Doo Soon Kim | Seokhwan Kim | Walter Chang | Fei Liu
Proceedings of the 2nd Workshop on New Frontiers in Summarization

While recent work in abstractive summarization has resulted in higher scores in automatic metrics, there is little understanding on how these systems combine information taken from multiple document sentences. In this paper, we analyze the outputs of five state-of-the-art abstractive summarizers, focusing on summary sentences that are formed by sentence fusion. We ask assessors to judge the grammaticality, faithfulness, and method of fusion for summary sentences. Our analysis reveals that system sentences are mostly grammatical, but often fail to remain faithful to the original article.

pdf bib
Scoring Sentence Singletons and Pairs for Abstractive Summarization
Logan Lebanoff | Kaiqiang Song | Franck Dernoncourt | Doo Soon Kim | Seokhwan Kim | Walter Chang | Fei Liu
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

When writing a summary, humans tend to choose content from one or two sentences and merge them into a single summary sentence. However, the mechanisms behind the selection of one or multiple source sentences remain poorly understood. Sentence fusion assumes multi-sentence input; yet sentence selection methods only work with single sentences and not combinations of them. There is thus a crucial gap between sentence selection and fusion to support summarizing by both compressing single sentences and fusing pairs. This paper attempts to bridge the gap by ranking sentence singletons and pairs together in a unified space. Our proposed framework attempts to model human methodology by selecting either a single sentence or a pair of sentences, then compressing or fusing the sentence(s) to produce a summary sentence. We conduct extensive experiments on both single- and multi-document summarization datasets and report findings on sentence selection and abstraction.

2018

pdf bib
A Comparison Study of Human Evaluated Automated Highlighting Systems
Sasha Spala | Franck Dernoncourt | Walter Chang | Carl Dockhorn
Proceedings of the 32nd Pacific Asia Conference on Language, Information and Computation

pdf bib
PhotoshopQuiA: A Corpus of Non-Factoid Questions and Answers for Why-Question Answering
Andrei Dulceanu | Thang Le Dinh | Walter Chang | Trung Bui | Doo Soon Kim | Manh Chien Vu | Seokhwan Kim
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

pdf bib
A Repository of Corpora for Summarization
Franck Dernoncourt | Mohammad Ghassemi | Walter Chang
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

pdf bib
Edit me: A Corpus and a Framework for Understanding Natural Language Image Editing
Ramesh Manuvinakurike | Jacqueline Brixey | Trung Bui | Walter Chang | Doo Soon Kim | Ron Artstein | Kallirroi Georgila
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

pdf bib
DialEdit: Annotations for Spoken Conversational Image Editing
Ramesh Manuvirakurike | Jacqueline Brixey | Trung Bui | Walter Chang | Ron Artstein | Kallirroi Georgila
Proceedings 14th Joint ACL - ISO Workshop on Interoperable Semantic Annotation

pdf bib
Conversational Image Editing: Incremental Intent Identification in a New Dialogue Task
Ramesh Manuvinakurike | Trung Bui | Walter Chang | Kallirroi Georgila
Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue

We present “conversational image editing”, a novel real-world application domain combining dialogue, visual information, and the use of computer vision. We discuss the importance of dialogue incrementality in this task, and build various models for incremental intent identification based on deep learning and traditional classification algorithms. We show how our model based on convolutional neural networks outperforms models based on random forests, long short term memory networks, and conditional random fields. By training embeddings based on image-related dialogue corpora, we outperform pre-trained out-of-the-box embeddings, for intention identification tasks. Our experiments also provide evidence that incremental intent processing may be more efficient for the user and could save time in accomplishing tasks.

pdf bib
A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents
Arman Cohan | Franck Dernoncourt | Doo Soon Kim | Trung Bui | Seokhwan Kim | Walter Chang | Nazli Goharian
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)

Neural abstractive summarization models have led to promising results in summarizing relatively short documents. We propose the first model for abstractive summarization of single, longer-form documents (e.g., research papers). Our approach consists of a new hierarchical encoder that models the discourse structure of a document, and an attentive discourse-aware decoder to generate the summary. Empirical results on two large-scale datasets of scientific papers show that our model significantly outperforms state-of-the-art models.

pdf bib
A Web-based Framework for Collecting and Assessing Highlighted Sentences in a Document
Sasha Spala | Franck Dernoncourt | Walter Chang | Carl Dockhorn
Proceedings of the 27th International Conference on Computational Linguistics: System Demonstrations

Automatically highlighting a text aims at identifying key portions that are the most important to a reader. In this paper, we present a web-based framework designed to efficiently and scalably crowdsource two independent but related tasks: collecting highlight annotations, and comparing the performance of automated highlighting systems. The first task is necessary to understand human preferences and train supervised automated highlighting systems. The second task yields a more accurate and fine-grained evaluation than existing automated performance metrics.

2016

pdf bib
Automatic Annotation of Structured Facts in Images
Mohamed Elhoseiny | Scott Cohen | Walter Chang | Brian Price | Ahmed Elgammal
Proceedings of the 5th Workshop on Vision and Language