Bonnie Webber


2021

pdf bib
Refocusing on Relevance : Personalization in NLGNLG
Shiran Dudy | Steven Bedrick | Bonnie Webber
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Many NLG tasks such as summarization, dialogue response, or open domain question answering, focus primarily on a source text in order to generate a target response. This standard approach falls short, however, when a user’s intent or context of work is not easily recoverable based solely on that source text a scenario that we argue is more of the rule than the exception. In this work, we argue that NLG systems in general should place a much higher level of emphasis on making use of additional context, and suggest that relevance (as used in Information Retrieval) be thought of as a crucial tool for designing user-oriented text-generating tasks. We further discuss possible harms and hazards around such personalization, and argue that value-sensitive design represents a crucial path forward through these challenges.

pdf bib
Revisiting Shallow Discourse Parsing in the PDTB-3 : Handling Intra-sentential ImplicitsPDTB-3: Handling Intra-sentential Implicits
Zheng Zhao | Bonnie Webber
Proceedings of the 2nd Workshop on Computational Approaches to Discourse

In the PDTB-3, several thousand implicit discourse relations were newly annotated within individual sentences, adding to the over 15,000 implicit relations annotated across adjacent sentences in the PDTB-2. Given that the position of the arguments to these intra-sentential implicits is no longer as well-defined as with inter-sentential implicits, a discourse parser must identify both their location and their sense. That is the focus of the current work. The paper provides a comprehensive analysis of our results, showcasing model performance under different scenarios, pointing out limitations and noting future directions.

2020

pdf bib
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Bonnie Webber | Trevor Cohn | Yulan He | Yang Liu
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

pdf bib
Reducing Quantity Hallucinations in Abstractive Summarization
Zheng Zhao | Shay B. Cohen | Bonnie Webber
Findings of the Association for Computational Linguistics: EMNLP 2020

It is well-known that abstractive summaries are subject to hallucinationincluding material that is not supported by the original text. While summaries can be made hallucination-free by limiting them to general phrases, such summaries would fail to be very informative. Alternatively, one can try to avoid hallucinations by verifying that any specific entities in the summary appear in the original text in a similar context. This is the approach taken by our system, Herman. The system learns to recognize and verify quantity entities (dates, numbers, sums of money, etc.) in a beam-worth of abstractive summaries produced by state-of-the-art models, in order to up-rank those summaries whose quantity terms are supported by the original text. Experimental results demonstrate that the ROUGE scores of such up-ranked summaries have a higher Precision than summaries that have not been up-ranked, without a comparable loss in Recall, resulting in higher F1. Preliminary human evaluation of up-ranked vs. original summaries shows people’s preference for the former.

pdf bib
Querent Intent in Multi-Sentence Questions
Laurie Burchell | Jie Chi | Tom Hosking | Nina Markl | Bonnie Webber
Proceedings of the 14th Linguistic Annotation Workshop

Multi-sentence questions (MSQs) are sequences of questions connected by relations which, unlike sequences of standalone questions, need to be answered as a unit. Following Rhetorical Structure Theory (RST), we recognise that different question discourse relations between the subparts of MSQs reflect different speaker intents, and consequently elicit different answering strategies. Correctly identifying these relations is therefore a crucial step in automatically answering MSQs. We identify five different types of MSQs in English, and define five novel relations to describe them. We extract over 162,000 MSQs from Stack Exchange to enable future research. Finally, we implement a high-precision baseline classifier based on surface features.

pdf bib
Extending Implicit Discourse Relation Recognition to the PDTB-3PDTB-3
Li Liang | Zheng Zhao | Bonnie Webber
Proceedings of the First Workshop on Computational Approaches to Discourse

The PDTB-3 contains many more Implicit discourse relations than the previous PDTB-2. This is in part because implicit relations have now been annotated within sentences as well as between them. In addition, some now co-occur with explicit discourse relations, instead of standing on their own. Here we show that while this can complicate the problem of identifying the location of implicit discourse relations, it can in turn simplify the problem of identifying their senses. We present data to support this claim, as well as methods that can serve as a non-trivial baseline for future state-of-the-art recognizers for implicit discourse relations.

2019

pdf bib
GECOR : An End-to-End Generative Ellipsis and Co-reference Resolution Model for Task-Oriented DialogueGECOR: An End-to-End Generative Ellipsis and Co-reference Resolution Model for Task-Oriented Dialogue
Jun Quan | Deyi Xiong | Bonnie Webber | Changjian Hu
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Ellipsis and co-reference are common and ubiquitous especially in multi-turn dialogues. In this paper, we treat the resolution of ellipsis and co-reference in dialogue as a problem of generating omitted or referred expressions from the dialogue context. We therefore propose a unified end-to-end Generative Ellipsis and CO-reference Resolution model (GECOR) in the context of dialogue. The model can generate a new pragmatically complete user utterance by alternating the generation and copy mode for each user utterance. A multi-task learning framework is further proposed to integrate the GECOR into an end-to-end task-oriented dialogue. In order to train both the GECOR and the multi-task learning framework, we manually construct a new dataset on the basis of the public dataset CamRest676 with both ellipsis and co-reference annotation. On this dataset, intrinsic evaluations on the resolution of ellipsis and co-reference show that the GECOR model significantly outperforms the sequence-to-sequence (seq2seq) baseline model in terms of EM, BLEU and F1 while extrinsic evaluations on the downstream dialogue task demonstrate that our multi-task learning framework with GECOR achieves a higher success rate of task completion than TSCP, a state-of-the-art end-to-end task-oriented dialogue model.

pdf bib
Classifying Author Intention for Writer Feedback in Related Work
Arlene Casey | Bonnie Webber | Dorota Glowacka
Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)

The ability to produce high-quality publishable material is critical to academic success but many Post-Graduate students struggle to learn to do so. While recent years have seen an increase in tools designed to provide feedback on aspects of writing, one aspect that has so far been neglected is the Related Work section of academic research papers. To address this, we have trained a supervised classifier on a corpus of 94 Related Work sections and evaluated it against a manually annotated gold standard. The classifier uses novel features pertaining to citation types and co-reference, along with patterns found from studying Related Works. We show that these novel features contribute to classifier performance with performance being favourable compared to other similar works that classify author intentions and consider feedback for academic writing.

2018

pdf bib
Getting to Hearer-old : Charting Referring Expressions Across Time
Ieva Staliūnaitė | Hannah Rohde | Bonnie Webber | Annie Louis
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

When a reader is first introduced to an entity, its referring expression must describe the entity. For entities that are widely known, a single word or phrase often suffices. This paper presents the first study of how expressions that refer to the same entity develop over time. We track thousands of person and organization entities over 20 years of New York Times (NYT). As entities move from hearer-new (first introduction to the NYT audience) to hearer-old (common knowledge) status, we show empirically that the referring expressions along this trajectory depend on the type of the entity, and exhibit linguistic properties related to becoming common knowledge (e.g., shorter length, less use of appositives, more definiteness). These properties can also be used to build a model to predict how long it will take for an entity to reach hearer-old status. Our results reach 10-30 % absolute improvement over a majority-class baseline.

2017

pdf bib
Universal Dependencies to Logical Form with Negation ScopeUniversal Dependencies to Logical Form with Negation Scope
Federico Fancellu | Siva Reddy | Adam Lopez | Bonnie Webber
Proceedings of the Workshop Computational Semantics Beyond Events and Roles

Many language technology applications would benefit from the ability to represent negation and its scope on top of widely-used linguistic resources. In this paper, we investigate the possibility of obtaining a first-order logic representation with negation scope marked using Universal Dependencies. To do so, we enhance UDepLambda, a framework that converts dependency graphs to logical forms. The resulting UDepLambda is able to handle phenomena related to scope by means of an higher-order type theory, relevant not only to negation but also to universal quantification and other complex semantic phenomena. The initial conversion we did for English is promising, in that one can represent the scope of negation also in the presence of more complex phenomena such as universal quantifiers.Universal Dependencies. To do so, we enhance UDepLambda, a framework that converts dependency graphs to logical forms. The resulting UDepLambda\\lnot\n \n\nis able to handle phenomena related to scope by means of an higher-order type theory, relevant not only to negation but also to universal quantification and other complex semantic phenomena. The initial conversion we did for English is promising, in that one can represent the scope of negation also in the presence of more complex phenomena such as universal quantifiers.

pdf bib
Proceedings of the Third Workshop on Discourse in Machine Translation
Bonnie Webber | Andrei Popescu-Belis | Jörg Tiedemann
Proceedings of the Third Workshop on Discourse in Machine Translation

pdf bib
Detecting negation scope is easy, except when it is n’t
Federico Fancellu | Adam Lopez | Bonnie Webber | Hangfeng He
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers

Several corpora have been annotated with negation scopethe set of words whose meaning is negated by a cue like the word notleading to the development of classifiers that detect negation scope with high accuracy. We show that for nearly all of these corpora, this high accuracy can be attributed to a single fact : they frequently annotate negation scope as a single span of text delimited by punctuation. For negation scopes not of this form, detection accuracy is low and under-sampling the easy training examples does not substantially improve accuracy. We demonstrate that this is partly an artifact of annotation guidelines, and we argue that future negation scope annotation efforts should focus on these more difficult cases.

pdf bib
Discourse Relations and Conjoined VPs : Automated Sense RecognitionVPs: Automated Sense Recognition
Valentina Pyatkin | Bonnie Webber
Proceedings of the Student Research Workshop at the 15th Conference of the European Chapter of the Association for Computational Linguistics

Sense classification of discourse relations is a sub-task of shallow discourse parsing. Discourse relations can occur both across sentences (inter-sentential) and within sentences (intra-sentential), and more than one discourse relation can hold between the same units. Using a newly available corpus of discourse-annotated intra-sentential conjoined verb phrases, we demonstrate a sequential classification pipeline for their multi-label sense classification. We assess the importance of each feature used in the classification, the feature scope, and what is lost in moving from gold standard manual parses to the output of an off-the-shelf parser.inter-sentential) and within sentences (intra-sentential), and more than one discourse relation can hold between the same units. Using a newly available corpus of discourse-annotated intra-sentential conjoined verb phrases, we demonstrate a sequential classification pipeline for their multi-label sense classification. We assess the importance of each feature used in the classification, the feature scope, and what is lost in moving from gold standard manual parses to the output of an off-the-shelf parser.