Asli Celikyilmaz


2022

pdf
CONFIT: Toward Faithful Dialogue Summarization with Linguistically-Informed Contrastive Fine-tuning
Xiangru Tang | Arjun Nair | Borui Wang | Bingyao Wang | Jai Desai | Aaron Wade | Haoran Li | Asli Celikyilmaz | Yashar Mehdad | Dragomir Radev
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Factual inconsistencies in generated summaries severely limit the practical applications of abstractive dialogue summarization. Although significant progress has been achieved by using pre-trained neural language models, substantial amounts of hallucinated content are found during the human evaluation. In this work, we first devised a typology of factual errors to better understand the types of hallucinations generated by current models and conducted human evaluation on popular dialog summarization dataset. We further propose a training strategy that improves the factual consistency and overall quality of summaries via a novel contrastive fine-tuning, called CONFIT. To tackle top factual errors from our annotation, we introduce additional contrastive loss with carefully designed hard negative samples and self-supervised dialogue-specific loss to capture the key information between speakers. We show that our model significantly reduces all kinds of factual errors on both SAMSum dialogue summarization and AMI meeting summarization. On both datasets, we achieve significant improvements over state-of-the-art baselines using both automatic metrics, ROUGE and BARTScore, and human evaluation.

pdf
Investigating Crowdsourcing Protocols for Evaluating the Factual Consistency of Summaries
Xiangru Tang | Alexander Fabbri | Haoran Li | Ziming Mao | Griffin Adams | Borui Wang | Asli Celikyilmaz | Yashar Mehdad | Dragomir Radev
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Current pre-trained models applied for summarization are prone to factual inconsistencies that misrepresent the source text. Evaluating the factual consistency of summaries is thus necessary to develop better models. However, the human evaluation setup for evaluating factual consistency has not been standardized. To determine the factors that affect the reliability of the human evaluation, we crowdsource evaluations for factual consistency across state-of-the-art models on two news summarization datasets using the rating-based Likert Scale and ranking-based Best-Worst Scaling. Our analysis reveals that the ranking-based Best-Worst Scaling offers a more reliable measure of summary quality across datasets and that the reliability of Likert ratings highly depends on the target dataset and the evaluation design. To improve crowdsourcing reliability, we extend the scale of the Likert rating and present a scoring algorithm for Best-Worst Scaling that we call value learning. Our crowdsourcing guidelines will be publicly available to facilitate future work on factual consistency in summarization.

2021

pdf
GO FIGURE: A Meta Evaluation of Factuality in Summarization
Saadia Gabriel | Asli Celikyilmaz | Rahul Jha | Yejin Choi | Jianfeng Gao
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf
An Exploratory Study on Long Dialogue Summarization: What Works and What’s Next
Yusen Zhang | Ansong Ni | Tao Yu | Rui Zhang | Chenguang Zhu | Budhaditya Deb | Asli Celikyilmaz | Ahmed Hassan Awadallah | Dragomir Radev
Findings of the Association for Computational Linguistics: EMNLP 2021

Dialogue summarization helps readers capture salient information from long conversations in meetings, interviews, and TV series. However, real-world dialogues pose a great challenge to current summarization models, as the dialogue length typically exceeds the input limits imposed by recent transformer-based pre-trained models, and the interactive nature of dialogues makes relevant information more context-dependent and sparsely distributed than news articles. In this work, we perform a comprehensive study on long dialogue summarization by investigating three strategies to deal with the lengthy input problem and locate relevant information: (1) extended transformer models such as Longformer, (2) retrieve-then-summarize pipeline models with several dialogue utterance retrieval methods, and (3) hierarchical dialogue encoding models such as HMNet. Our experimental results on three long dialogue datasets (QMSum, MediaSum, SummScreen) show that the retrieve-then-summarize pipeline models yield the best performance. We also demonstrate that the summary quality can be further improved with a stronger retrieval model and pretraining on proper external summarization datasets.

pdf
Contrastive Multi-document Question Generation
Woon Sang Cho | Yizhe Zhang | Sudha Rao | Asli Celikyilmaz | Chenyan Xiong | Jianfeng Gao | Mengdi Wang | Bill Dolan
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume

Multi-document question generation focuses on generating a question that covers the common aspect of multiple documents. Such a model is useful in generating clarifying options. However, a naive model trained only using the targeted (‘positive’) document set may generate too generic questions that cover a larger scope than delineated by the document set. To address this challenge, we introduce the contrastive learning strategy where given ‘positive’ and ‘negative’ sets of documents, we generate a question that is closely related to the ‘positive’ set but is far away from the ‘negative’ set. This setting allows generated questions to be more specific and related to the target document set. To generate such specific questions, we propose Multi-Source Coordinated Question Generator (MSCQG), a novel framework that includes a supervised learning (SL) stage and a reinforcement learning (RL) stage. In the SL stage, a single-document question generator is trained. In the RL stage, a coordinator model is trained to find optimal attention weights to align multiple single-document generators, by optimizing a reward designed to promote specificity of generated questions. We also develop an effective auxiliary objective, named Set-induced Contrastive Regularization (SCR) that improves the coordinator’s contrastive learning during the RL stage. We show that our model significantly outperforms several strong baselines, as measured by automatic metrics and human evaluation. The source repository is publicly available at ‘www.github.com/woonsangcho/contrast_qgen’.

pdf
AREDSUM: Adaptive Redundancy-Aware Iterative Sentence Ranking for Extractive Document Summarization
Keping Bi | Rahul Jha | Bruce Croft | Asli Celikyilmaz
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume

Redundancy-aware extractive summarization systems score the redundancy of the sentences to be included in a summary either jointly with their salience information or separately as an additional sentence scoring step. Previous work shows the efficacy of jointly scoring and selecting sentences with neural sequence generation models. It is, however, not well-understood if the gain is due to better encoding techniques or better redundancy reduction approaches. Similarly, the contribution of salience versus diversity components on the created summary is not studied well. Building on the state-of-the-art encoding methods for summarization, we present two adaptive learning models: AREDSUM-SEQ that jointly considers salience and novelty during sentence selection; and a two-step AREDSUM-CTX that scores salience first, then learns to balance salience and redundancy, enabling the measurement of the impact of each aspect. Empirical results on CNN/DailyMail and NYT50 datasets show that by modeling diversity explicitly in a separate step, AREDSUM-CTX achieves significantly better performance than AREDSUM-SEQ as well as state-of-the-art extractive summarization baselines.

pdf
Discourse Understanding and Factual Consistency in Abstractive Summarization
Saadia Gabriel | Antoine Bosselut | Jeff Da | Ari Holtzman | Jan Buys | Kyle Lo | Asli Celikyilmaz | Yejin Choi
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume

We introduce a general framework for abstractive summarization with factual consistency and distinct modeling of the narrative flow in an output summary. Our work addresses current limitations of models for abstractive summarization that often hallucinate information or generate summaries with coherence issues. To generate abstractive summaries with factual consistency and narrative flow, we propose Cooperative Generator-Discriminator Networks (Co-opNet), a novel transformer-based framework where the generator works with a discriminator architecture to compose coherent long-form summaries. We explore four different discriminator objectives which each capture a different aspect of coherence, including whether salient spans of generated abstracts are hallucinated or appear in the input context, and the likelihood of sentence adjacency in generated abstracts. We measure the ability of Co-opNet to learn these objectives with arXiv scientific papers, using the abstracts as a proxy for gold long-form scientific article summaries. Empirical results from automatic and human evaluations demonstrate that Co-opNet learns to summarize with considerably improved global coherence compared to competitive baselines.

pdf
Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization
Yichen Jiang | Asli Celikyilmaz | Paul Smolensky | Paul Soulos | Sudha Rao | Hamid Palangi | Roland Fernandez | Caitlin Smith | Mohit Bansal | Jianfeng Gao
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Abstractive summarization, the task of generating a concise summary of input documents, requires: (1) reasoning over the source document to determine the salient pieces of information scattered across the long document, and (2) composing a cohesive text by reconstructing these salient facts into a shorter summary that faithfully reflects the complex relations connecting these facts. In this paper, we adapt TP-Transformer (Schlag et al., 2019), an architecture that enriches the original Transformer (Vaswani et al., 2017) with the explicitly compositional Tensor Product Representation (TPR), for the task of abstractive summarization. The key feature of our model is a structural bias that we introduce by encoding two separate representations for each token to represent the syntactic structure (with role vectors) and semantic content (with filler vectors) separately. The model then binds the role and filler vectors into the TPR as the layer output. We argue that the structured intermediate representations enable the model to take better control of the contents (salient facts) and structures (the syntax that connects the facts) when generating the summary. Empirically, we show that our TP-Transformer outperforms the Transformer and the original TP-Transformer significantly on several abstractive summarization datasets based on both automatic and human evaluations. On several syntactic and semantic probing tasks, we demonstrate the emergent structural information in the role vectors and the performance gain by information specificity of the role vectors and improved syntactic interpretability in the TPR layer outputs.(Code and models are available at https://github.com/jiangycTarheel/TPT-Summ)

pdf
QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization
Ming Zhong | Da Yin | Tao Yu | Ahmad Zaidi | Mutethia Mutuma | Rahul Jha | Ahmed Hassan Awadallah | Asli Celikyilmaz | Yang Liu | Xipeng Qiu | Dragomir Radev
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Meetings are a key component of human collaboration. As increasing numbers of meetings are recorded and transcribed, meeting summaries have become essential to remind those who may or may not have attended the meetings about the key decisions made and the tasks to be completed. However, it is hard to create a single short summary that covers all the content of a long meeting involving multiple people and topics. In order to satisfy the needs of different types of users, we define a new query-based multi-domain meeting summarization task, where models have to select and summarize relevant spans of meetings in response to a query, and we introduce QMSum, a new benchmark for this task. QMSum consists of 1,808 query-summary pairs over 232 meetings in multiple domains. Besides, we investigate a locate-then-summarize method and evaluate a set of strong summarization baselines on the task. Experimental results and manual analysis reveal that QMSum presents significant challenges in long meeting summarization for future research. Dataset is available at https://github.com/Yale-LILY/QMSum.

pdf
Structural Biases for Improving Transformers on Translation into Morphologically Rich Languages
Paul Soulos | Sudha Rao | Caitlin Smith | Eric Rosen | Asli Celikyilmaz | R. Thomas McCoy | Yichen Jiang | Coleman Haley | Roland Fernandez | Hamid Palangi | Jianfeng Gao | Paul Smolensky
Proceedings of the 4th Workshop on Technologies for MT of Low Resource Languages (LoResMT2021)

Machine translation has seen rapid progress with the advent of Transformer-based models. These models have no explicit linguistic structure built into them, yet they may still implicitly learn structured relationships by attending to relevant tokens. We hypothesize that this structural learning could be made more robust by explicitly endowing Transformers with a structural bias, and we investigate two methods for building in such a bias. One method, the TP-Transformer, augments the traditional Transformer architecture to include an additional component to represent structure. The second method imbues structure at the data level by segmenting the data with morphological tokenization. We test these methods on translating from English into morphologically rich languages, Turkish and Inuktitut, and consider both automatic metrics and human evaluations. We find that each of these two approaches allows the network to achieve better performance, but this improvement is dependent on the size of the dataset. In sum, structural encoding methods make Transformers more sample-efficient, enabling them to perform better from smaller amounts of data.

pdf
EmailSum: Abstractive Email Thread Summarization
Shiyue Zhang | Asli Celikyilmaz | Jianfeng Gao | Mohit Bansal
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)

Recent years have brought about an interest in the challenging task of summarizing conversation threads (meetings, online discussions, etc.). Such summaries help analysis of the long text to quickly catch up with the decisions made and thus improve our work or communication efficiency. To spur research in thread summarization, we have developed an abstractive Email Thread Summarization (EmailSum) dataset, which contains human-annotated short (<30 words) and long (<100 words) summaries of 2,549 email threads (each containing 3 to 10 emails) over a wide variety of topics. We perform a comprehensive empirical study to explore different summarization techniques (including extractive and abstractive methods, single-document and hierarchical models, as well as transfer and semisupervised learning) and conduct human evaluations on both short and long summary generation tasks. Our results reveal the key challenges of current abstractive summarization models in this task, such as understanding the sender’s intent and identifying the roles of sender and receiver. Furthermore, we find that widely used automatic evaluation metrics (ROUGE, BERTScore) are weakly correlated with human judgments on this email thread summarization task. Hence, we emphasize the importance of human evaluation and the development of better metrics by the community.

pdf
The First Workshop on Evaluations and Assessments of Neural Conversation Systems
Wei Wei | Bo Dai | Tuo Zhao | Lihong Li | Diyi Yang | Yun-Nung Chen | Y-Lan Boureau | Asli Celikyilmaz | Alborz Geramifard | Aman Ahuja | Haoming Jiang
The First Workshop on Evaluations and Assessments of Neural Conversation Systems

2020

pdf
A Recipe for Creating Multimodal Aligned Datasets for Sequential Tasks
Angela Lin | Sudha Rao | Asli Celikyilmaz | Elnaz Nouri | Chris Brockett | Debadeepta Dey | Bill Dolan
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Many high-level procedural tasks can be decomposed into sequences of instructions that vary in their order and choice of tools. In the cooking domain, the web offers many, partially-overlapping, text and video recipes (i.e. procedures) that describe how to make the same dish (i.e. high-level task). Aligning instructions for the same dish across different sources can yield descriptive visual explanations that are far richer semantically than conventional textual instructions, providing commonsense insight into how real-world procedures are structured. Learning to align these different instruction sets is challenging because: a) different recipes vary in their order of instructions and use of ingredients; and b) video instructions can be noisy and tend to contain far more information than text instructions. To address these challenges, we use an unsupervised alignment algorithm that learns pairwise alignments between instructions of different recipes for the same dish. We then use a graph algorithm to derive a joint alignment between multiple text and multiple video recipes for the same dish. We release the Microsoft Research Multimodal Aligned Recipe Corpus containing ~150K pairwise alignments between recipes across 4262 dishes with rich commonsense information.

pdf
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations
Asli Celikyilmaz | Tsung-Hsien Wen
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations

pdf
PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Tracking
Hannah Rashkin | Asli Celikyilmaz | Yejin Choi | Jianfeng Gao
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

We propose the task of outline-conditioned story generation: given an outline as a set of phrases that describe key characters and events to appear in a story, the task is to generate a coherent narrative that is consistent with the provided outline. This task is challenging as the input only provides a rough sketch of the plot, and thus, models need to generate a story by interweaving the key points provided in the outline. This requires the model to keep track of the dynamic states of the latent plot, conditioning on the input outline while generating the full story. We present PlotMachines, a neural narrative model that learns to transform an outline into a coherent story by tracking the dynamic plot states. In addition, we enrich PlotMachines with high-level discourse structure so that the model can learn different writing styles corresponding to different parts of the narrative. Comprehensive experiments over three fiction and non-fiction datasets demonstrate that large-scale language models, such as GPT-2 and Grover, despite their impressive generation performance, are not sufficient in generating coherent narratives for the given outline, and dynamic plot state tracking is important for composing narratives with tighter, more consistent plots.

pdf
Substance over Style: Document-Level Targeted Content Transfer
Allison Hegel | Sudha Rao | Asli Celikyilmaz | Bill Dolan
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Existing language models excel at writing from scratch, but many real-world scenarios require rewriting an existing document to fit a set of constraints. Although sentence-level rewriting has been fairly well-studied, little work has addressed the challenge of rewriting an entire document coherently. In this work, we introduce the task of document-level targeted content transfer and address it in the recipe domain, with a recipe as the document and a dietary restriction (such as vegan or dairy-free) as the targeted constraint. We propose a novel model for this task based on the generative pre-trained language model (GPT-2) and train on a large number of roughly-aligned recipe pairs. Both automatic and human evaluations show that our model out-performs existing methods by generating coherent and diverse rewrites that obey the constraint while remaining close to the original document. Finally, we analyze our model’s rewrites to assess progress toward the goal of making language generation more attuned to constraints that are substantive rather than stylistic.

pdf
The Amazing World of Neural Language Generation
Yangfeng Ji | Antoine Bosselut | Thomas Wolf | Asli Celikyilmaz
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts

Neural Language Generation (NLG) – using neural network models to generate coherent text – is among the most promising methods for automated text creation. Recent years have seen a paradigm shift in neural text generation, caused by the advances in deep contextual language modeling (e.g., LSTMs, GPT, GPT2) and transfer learning (e.g., ELMo, BERT). While these tools have dramatically improved the state of NLG, particularly for low resources tasks, state-of-the-art NLG models still face many challenges: a lack of diversity in generated text, commonsense violations in depicted situations, difficulties in making use of factual information, and difficulties in designing reliable evaluation metrics. In this tutorial, we will present an overview of the current state-of-the-art in neural network architectures, and how they shaped recent research directions in text generation. We will discuss how and why these models succeed/fail at generating coherent text, and provide insights on several applications.

pdf
Artemis: A Novel Annotation Methodology for Indicative Single Document Summarization
Rahul Jha | Keping Bi | Yang Li | Mahdi Pakdaman | Asli Celikyilmaz | Ivan Zhiboedov | Kieran McDonald
Proceedings of the First Workshop on Evaluation and Comparison of NLP Systems

We describe Artemis (Annotation methodology for Rich, Tractable, Extractive, Multi-domain, Indicative Summarization), a novel hierarchical annotation process that produces indicative summaries for documents from multiple domains. Current summarization evaluation datasets are single-domain and focused on a few domains for which naturally occurring summaries can be easily found, such as news and scientific articles. These are not sufficient for training and evaluation of summarization models for use in document management and information retrieval systems, which need to deal with documents from multiple domains. Compared to other annotation methods such as Relative Utility and Pyramid, Artemis is more tractable because judges don’t need to look at all the sentences in a document when making an importance judgment for one of the sentences, while providing similarly rich sentence importance annotations. We describe the annotation process in detail and compare it with other similar evaluation systems. We also present analysis and experimental results over a sample set of 532 annotated documents.

pdf
Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI
Tsung-Hsien Wen | Asli Celikyilmaz | Zhou Yu | Alexandros Papangelis | Mihail Eric | Anuj Kumar | Iñigo Casanueva | Rushin Shah
Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI

pdf
RMM: A Recursive Mental Model for Dialogue Navigation
Homero Roman Roman | Yonatan Bisk | Jesse Thomason | Asli Celikyilmaz | Jianfeng Gao
Findings of the Association for Computational Linguistics: EMNLP 2020

Language-guided robots must be able to both ask humans questions and understand answers. Much existing work focuses only on the latter. In this paper, we go beyond instruction following and introduce a two-agent task where one agent navigates and asks questions that a second, guiding agent answers. Inspired by theory of mind, we propose the Recursive Mental Model (RMM). The navigating agent models the guiding agent to simulate answers given candidate generated questions. The guiding agent in turn models the navigating agent to simulate navigation steps it would take to generate answers. We use the progress agents make towards the goal as a reinforcement learning reward signal to directly inform not only navigation actions, but also both question and answer generation. We demonstrate that RMM enables better generalization to novel environments. Interlocutor modelling may be a way forward for human-agent RMM where robots need to both ask and answer questions.

pdf
Proceedings of the First Workshop on Advances in Language and Vision Research
Xin Wang | Jesse Thomason | Ronghang Hu | Xinlei Chen | Peter Anderson | Qi Wu | Asli Celikyilmaz | Jason Baldridge | William Yang Wang
Proceedings of the First Workshop on Advances in Language and Vision Research

2019

pdf
Robust Navigation with Language Pretraining and Stochastic Sampling
Xiujun Li | Chunyuan Li | Qiaolin Xia | Yonatan Bisk | Asli Celikyilmaz | Jianfeng Gao | Noah A. Smith | Yejin Choi
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Core to the vision-and-language navigation (VLN) challenge is building robust instruction representations and action decoding schemes, which can generalize well to previously unseen instructions and environments. In this paper, we report two simple but highly effective methods to address these challenges and lead to a new state-of-the-art performance. First, we adapt large-scale pretrained language models to learn text representations that generalize better to previously unseen instructions. Second, we propose a stochastic sampling scheme to reduce the considerable gap between the expert actions in training and sampled actions in test, so that the agent can learn to correct its own mistakes during long sequential action decoding. Combining the two techniques, we achieve a new state of the art on the Room-to-Room benchmark with 6% absolute gain over the previous best result (47% -> 53%) on the Success Rate weighted by Path Length metric.

pdf
Learning Compressed Sentence Representations for On-Device Text Processing
Dinghan Shen | Pengyu Cheng | Dhanasekar Sundararaman | Xinyuan Zhang | Qian Yang | Meng Tang | Asli Celikyilmaz | Lawrence Carin
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Vector representations of sentences, trained on massive text corpora, are widely used as generic sentence embeddings across a variety of NLP problems. The learned representations are generally assumed to be continuous and real-valued, giving rise to a large memory footprint and slow retrieval speed, which hinders their applicability to low-resource (memory and computation) platforms, such as mobile devices. In this paper, we propose four different strategies to transform continuous and generic sentence embeddings into a binarized form, while preserving their rich semantic information. The introduced methods are evaluated across a wide range of downstream tasks, where the binarized sentence embeddings are demonstrated to degrade performance by only about 2% relative to their continuous counterparts, while reducing the storage requirement by over 98%. Moreover, with the learned binary representations, the semantic relatedness of two sentences can be evaluated by simply calculating their Hamming distance, which is more computational efficient compared with the inner product operation between continuous embeddings. Detailed analysis and case study further validate the effectiveness of proposed methods.

pdf
Towards Generating Long and Coherent Text with Multi-Level Latent Variable Models
Dinghan Shen | Asli Celikyilmaz | Yizhe Zhang | Liqun Chen | Xin Wang | Jianfeng Gao | Lawrence Carin
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Variational autoencoders (VAEs) have received much attention recently as an end-to-end architecture for text generation with latent variables. However, previous works typically focus on synthesizing relatively short sentences (up to 20 words), and the posterior collapse issue has been widely identified in text-VAEs. In this paper, we propose to leverage several multi-level structures to learn a VAE model for generating long, and coherent text. In particular, a hierarchy of stochastic layers between the encoder and decoder networks is employed to abstract more informative and semantic-rich latent codes. Besides, we utilize a multi-level decoder structure to capture the coherent long-term structure inherent in long-form texts, by generating intermediate sentence representations as high-level plan vectors. Extensive experimental results demonstrate that the proposed multi-level VAE model produces more coherent and less repetitive long text compared to baselines as well as can mitigate the posterior-collapse issue.

pdf
Sentence Mover’s Similarity: Automatic Evaluation for Multi-Sentence Texts
Elizabeth Clark | Asli Celikyilmaz | Noah A. Smith
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

For evaluating machine-generated texts, automatic methods hold the promise of avoiding collection of human judgments, which can be expensive and time-consuming. The most common automatic metrics, like BLEU and ROUGE, depend on exact word matching, an inflexible approach for measuring semantic similarity. We introduce methods based on sentence mover’s similarity; our automatic metrics evaluate text in a continuous space using word and sentence embeddings. We find that sentence-based metrics correlate with human judgments significantly better than ROUGE, both on machine-generated summaries (average length of 3.4 sentences) and human-authored essays (average length of 7.5). We also show that sentence mover’s similarity can be used as a reward when learning a generation model via reinforcement learning; we present both automatic and human evaluations of summaries learned in this way, finding that our approach outperforms ROUGE.

pdf
COMET: Commonsense Transformers for Automatic Knowledge Graph Construction
Antoine Bosselut | Hannah Rashkin | Maarten Sap | Chaitanya Malaviya | Asli Celikyilmaz | Yejin Choi
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

We present the first comprehensive study on automatic knowledge base construction for two prevalent commonsense knowledge graphs: ATOMIC (Sap et al., 2019) and ConceptNet (Speer et al., 2017). Contrary to many conventional KBs that store knowledge with canonical templates, commonsense KBs only store loosely structured open-text descriptions of knowledge. We posit that an important step toward automatic commonsense completion is the development of generative models of commonsense knowledge, and propose COMmonsEnse Transformers (COMET) that learn to generate rich and diverse commonsense descriptions in natural language. Despite the challenges of commonsense modeling, our investigation reveals promising results when implicit knowledge from deep pre-trained language models is transferred to generate explicit knowledge in commonsense knowledge graphs. Empirical results demonstrate that COMET is able to generate novel knowledge that humans rate as high quality, with up to 77.5% (ATOMIC) and 91.7% (ConceptNet) precision at top 1, which approaches human performance for these resources. Our findings suggest that using generative commonsense models for automatic commonsense KB completion could soon be a plausible alternative to extractive methods.

pdf
Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing
Hao Fu | Chunyuan Li | Xiaodong Liu | Jianfeng Gao | Asli Celikyilmaz | Lawrence Carin
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

Variational autoencoders (VAE) with an auto-regressive decoder have been applied for many natural language processing (NLP) tasks. VAE objective consists of two terms, the KL regularization term and the reconstruction term, balanced by a weighting hyper-parameter 𝛽. One notorious training difficulty is that the KL term tends to vanish. In this paper we study different scheduling schemes for 𝛽, and show that KL vanishing is caused by the lack of good latent codes in training decoder at the beginning of optimization. To remedy the issue, we propose a cyclical annealing schedule, which simply repeats the process of increasing 𝛽 multiple times. This new procedure allows us to learn more meaningful latent codes progressively by leveraging the results of previous learning cycles as warm re-restart. The effectiveness of cyclical annealing schedule is validated on a broad range of NLP tasks, including language modeling, dialog response generation and semi-supervised text classification.

pdf
Proceedings of the Workshop on Methods for Optimizing and Evaluating Neural Language Generation
Antoine Bosselut | Asli Celikyilmaz | Marjan Ghazvininejad | Srinivasan Iyer | Urvashi Khandelwal | Hannah Rashkin | Thomas Wolf
Proceedings of the Workshop on Methods for Optimizing and Evaluating Neural Language Generation

2018

pdf
Discourse-Aware Neural Rewards for Coherent Text Generation
Antoine Bosselut | Asli Celikyilmaz | Xiaodong He | Jianfeng Gao | Po-Sen Huang | Yejin Choi
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)

In this paper, we investigate the use of discourse-aware rewards with reinforcement learning to guide a model to generate long, coherent text. In particular, we propose to learn neural rewards to model cross-sentence ordering as a means to approximate desired discourse structure. Empirical results demonstrate that a generator trained with the learned reward produces more coherent and less repetitive text than models trained with cross-entropy or with reinforcement learning with commonly used scores as rewards.

pdf
Deep Communicating Agents for Abstractive Summarization
Asli Celikyilmaz | Antoine Bosselut | Xiaodong He | Yejin Choi
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)

We present deep communicating agents in an encoder-decoder architecture to address the challenges of representing a long document for abstractive summarization. With deep communicating agents, the task of encoding a long text is divided across multiple collaborating agents, each in charge of a subsection of the input text. These encoders are connected to a single decoder, trained end-to-end using reinforcement learning to generate a focused and coherent summary. Empirical results demonstrate that multiple communicating encoders lead to a higher quality summary compared to several strong baselines, including those based on a single encoder or multiple non-communicating encoders.

pdf
Deep Learning for Dialogue Systems
Yun-Nung Chen | Asli Celikyilmaz | Dilek Hakkani-Tür
Proceedings of the 27th International Conference on Computational Linguistics: Tutorial Abstracts

2017

pdf
Deep Learning for Dialogue Systems
Yun-Nung Chen | Asli Celikyilmaz | Dilek Hakkani-Tür
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts

In the past decade, goal-oriented spoken dialogue systems have been the most prominent component in today's virtual personal assistants. The classic dialogue systems have rather complex and/or modular pipelines. The advance of deep learning technologies has recently risen the applications of neural models to dialogue modeling. However, how to successfully apply deep learning based approaches to a dialogue system is still challenging. Hence, this tutorial is designed to focus on an overview of the dialogue system development while describing most recent research for building dialogue systems and summarizing the challenges, in order to allow researchers to study the potential improvements of the state-of-the-art dialogue systems. The tutorial material is available at http://deepdialogue.miulab.tw.

pdf
Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning
Baolin Peng | Xiujun Li | Lihong Li | Jianfeng Gao | Asli Celikyilmaz | Sungjin Lee | Kam-Fai Wong
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

Building a dialogue agent to fulfill complex tasks, such as travel planning, is challenging because the agent has to learn to collectively complete multiple subtasks. For example, the agent needs to reserve a hotel and book a flight so that there leaves enough time for commute between arrival and hotel check-in. This paper addresses this challenge by formulating the task in the mathematical framework of options over Markov Decision Processes (MDPs), and proposing a hierarchical deep reinforcement learning approach to learning a dialogue manager that operates at different temporal scales. The dialogue manager consists of: (1) a top-level dialogue policy that selects among subtasks or options, (2) a low-level dialogue policy that selects primitive actions to complete the subtask given by the top-level policy, and (3) a global state tracker that helps ensure all cross-subtask constraints be satisfied. Experiments on a travel planning task with simulated and real users show that our approach leads to significant improvements over three baselines, two based on handcrafted rules and the other based on flat deep reinforcement learning.

pdf
End-to-End Task-Completion Neural Dialogue Systems
Xiujun Li | Yun-Nung Chen | Lihong Li | Jianfeng Gao | Asli Celikyilmaz
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

One of the major drawbacks of modularized task-completion dialogue systems is that each module is trained individually, which presents several challenges. For example, downstream modules are affected by earlier modules, and the performance of the entire system is not robust to the accumulated errors. This paper presents a novel end-to-end learning framework for task-completion dialogue systems to tackle such issues.Our neural dialogue system can directly interact with a structured database to assist users in accessing information and accomplishing certain tasks. The reinforcement learning based dialogue manager offers robust capabilities to handle noises caused by other components of the dialogue system. Our experiments in a movie-ticket booking domain show that our end-to-end system not only outperforms modularized dialogue system baselines for both objective and subjective evaluation, but also is robust to noises as demonstrated by several systematic experiments with different error granularity and rates specific to the language understanding module.

2016

pdf
Task Completion Platform: A self-serve multi-domain goal oriented dialogue platform
Paul Crook | Alex Marin | Vipul Agarwal | Khushboo Aggarwal | Tasos Anastasakos | Ravi Bikkula | Daniel Boies | Asli Celikyilmaz | Senthilkumar Chandramohan | Zhaleh Feizollahi | Roman Holenstein | Minwoo Jeong | Omar Khan | Young-Bum Kim | Elizabeth Krawczyk | Xiaohu Liu | Danko Panic | Vasiliy Radostev | Nikhil Ramesh | Jean-Phillipe Robichaud | Alexandre Rochette | Logan Stromberg | Ruhi Sarikaya
Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations

2014

pdf
Resolving Referring Expressions in Conversational Dialogs for Natural User Interfaces
Asli Celikyilmaz | Zhaleh Feizollahi | Dilek Hakkani-Tur | Ruhi Sarikaya
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

2013

pdf
Semi-Supervised Semantic Tagging of Conversational Understanding using Markov Topic Regression
Asli Celikyilmaz | Dilek Hakkani-Tur | Gokhan Tur | Ruhi Sarikaya
Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf
Learning to Relate Literal and Sentimental Descriptions of Visual Properties
Mark Yatskar | Svitlana Volkova | Asli Celikyilmaz | Bill Dolan | Luke Zettlemoyer
Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

2012

pdf
Mining Search Query Logs for Spoken Language Understanding
Dilek Hakkani-Tür | Gokhan Tür | Asli Celikyilmaz
NAACL-HLT Workshop on Future directions and needs in the Spoken Dialog Community: Tools and Data (SDCTD 2012)

pdf
A Joint Model for Discovery of Aspects in Utterances
Asli Celikyilmaz | Dilek Hakkani-Tur
Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

2011

pdf
Discovery of Topically Coherent Sentences for Extractive Summarization
Asli Celikyilmaz | Dilek Hakkani-Tür
Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies

2010

pdf
LDA Based Similarity Modeling for Question Answering
Asli Celikyilmaz | Dilek Hakkani-Tur | Gokhan Tur
Proceedings of the NAACL HLT 2010 Workshop on Semantic Search

pdf
A Graph-Based Semi-Supervised Learning for Question Semantic Labeling
Asli Celikyilmaz | Dilek Hakkani-Tur
Proceedings of the NAACL HLT 2010 Workshop on Semantic Search

pdf
A Hybrid Hierarchical Model for Multi-Document Summarization
Asli Celikyilmaz | Dilek Hakkani-Tur
Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics

2009

pdf
Investigation of Question Classifier in Question Answering
Zhiheng Huang | Marcus Thint | Asli Celikyilmaz
Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing

pdf
Accurate Semantic Class Classifier for Coreference Resolution
Zhiheng Huang | Guangping Zeng | Weiqun Xu | Asli Celikyilmaz
Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing

pdf
A Graph-based Semi-Supervised Learning for Question-Answering
Asli Celikyilmaz | Marcus Thint | Zhiheng Huang
Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP

Search
Co-authors