Accurate prediction of suitable discourse connectives (however, furthermore, etc.) is a key component of any system aimed at building coherent and fluent discourses from shorter sentences and passages. As an example, a dialog system might assemble a long and informative answer by sampling passages extracted from different documents retrieved from the Web. We formulate the task of discourse connective prediction and release a dataset of 2.9M sentence pairs separated by discourse connectives for this task. Then, we evaluate the hardness of the task for human raters, apply a recently proposed decomposable attention (DA) model to this task and observe that the automatic predictor has a higher F1 than human raters (32 vs. 30). Nevertheless, under specific conditions the raters still outperform the DA model, suggesting that there is headroom for future improvements.
In this paper, we present an approach to exploit phrase tables generated by statistical machine translation in order to map French discourse connectives to discourse relations. Using this approach, we created ConcoLeDisCo, a lexicon of French discourse connectives and their PDTB relations. When evaluated against LEXCONN, ConcoLeDisCo achieves a recall of 0.81 and an Average Precision of 0.68 for the Concession and Condition relations.
Discourse connectives (e.g. however, because) are terms that can explicitly convey a discourse relation within a text. While discourse connectives have been shown to be an effective clue to automatically identify discourse relations, they are not always used to convey such relations, thus they should first be disambiguated between discourse-usage non-discourse-usage. In this paper, we investigate the applicability of features proposed for the disambiguation of English discourse connectives for French. Our results with the French Discourse Treebank (FDTB) show that syntactic and lexical feature…
We present DiscoSense, a benchmark for commonsense reasoning via understanding a wide variety of discourse connectives. We generate compelling distractors in DiscoSense using Conditional Adversarial Filtering, an extension of Adversarial Filtering that employs conditional generation. We show that state-of-the-art pre-trained language models struggle to perform well on DiscoSense, which makes this dataset ideal for evaluating next-generation commonsense reasoning systems.
East China Normal University（华东师范大学）；Shanghai Transsion Co., Ltd.（上海传音控股股份有限公司）
Due to the absence of connectives, implicit discourse relation recognition (IDRR) is still a challenging and crucial task in discourse analysis. Most of the current work adopted multi-task learning to aid IDRR through explicit discourse relation recognition (EDRR) or utilized dependencies between discourse relation labels to constrain model predictions. But these methods still performed poorly on fine-grained IDRR and even utterly misidentified on most of the few-shot discourse relation classes. To address these problems, we propose a novel Prompt-based Connective Prediction (PCP) method for I…
Michigan State University（密歇根州立大学）；University of Chicago（芝加哥大学）
As pre-trained language models (LMs) continue to dominate NLP, it is increasingly important that we understand the depth of language capabilities in these models. In this paper, we target pre-trained LMs' competence in pragmatics, with a focus on pragmatics relating to discourse connectives. We formulate cloze-style tests using a combination of naturally-occurring data and controlled inputs drawn from psycholinguistics. We focus on testing models' ability to use pragmatic cues to predict discourse connectives, models' ability to understand implicatures relating to connectives, and the extent t…
Dept. of Language Science and Technology（语言科学与技术系）；Saarland University（萨尔兰大学）
Implicit discourse relation classification is one of the most difficult steps in discourse parsing. The difficulty stems from the fact that the coherence relation must be inferred based on the content of the discourse relational arguments. Therefore, an effective encoding of the relational arguments is of crucial importance. We here propose a new model for implicit discourse relation classification, which consists of a classifier, and a sequence-to-sequence model which is trained to generate a representation of the discourse relational arguments by trying to predict the relational arguments in…
In this paper we present GumDrop, Georgetown University's entry at the DISRPT 2019 Shared Task on automatic discourse unit segmentation and connective detection. Our approach relies on model stacking, creating a heterogeneous ensemble of classifiers, which feed into a metalearner for each final task. The system encompasses three trainable component stacks: one for sentence splitting, one for discourse unit segmentation and one for connective detection. The flexibility of each ensemble allows the system to generalize well to datasets of different sizes and with varying levels of homogeneity.
In implicit discourse relation classification, we want to predict the relation between adjacent sentences in the absence of any overt discourse connectives. This is challenging even for humans, leading to shortage of annotated data, a fact that makes the task even more difficult for supervised machine learning approaches. In the current study, we perform implicit discourse relation classification without relying on any labeled implicit relation. We sidestep the lack of data through explicitation of implicit relations to reduce the task to two sub-problems: language modeling and explicit discou…
This paper describes our submission to the DISRPT2021 Shared Task on Discourse Unit Segmentation, Connective Detection, and Relation Classification. Our system, called DisCoDisCo, is a Transformer-based neural classifier which enhances contextualized word embeddings (CWEs) with hand-crafted features, relying on tokenwise sequence tagging for discourse segmentation and connective detection, and a feature-rich, encoder-less sentence pair classifier for relation classification. Our results for the first two tasks outperform SOTA scores from the previous 2019 shared task, and results on relation c…
MOE Key Laboratory of Computational Linguistics, Peking University（北京大学教育部计算语言学重点实验室）；School of Electronics Engineering and Computer Science, Peking University（北京大学电子工程与计算机科学学院）
In recent years, more research has been devoted to studying the subtask of the complete shallow discourse parsing, such as indentifying discourse connective and arguments of connective. There is a need to design a full discourse parser to pull these subtasks together. So we develop a discourse parser turning the free text into discourse relations. The parser includes connective identifier, arguments identifier, sense classifier and non-explicit identifier, which connects with each other in pipeline. Each component applies the maximum entropy model with abundant lexical and syntax features extr…
Implicit discourse relation classification is one of the most challenging and important tasks in discourse parsing, due to the lack of connective as strong linguistic cues. A principle bottleneck to further improvement is the shortage of training data (ca.~16k instances in the PDTB). Shi et al. (2017) proposed to acquire additional data by exploiting connectives in translation: human translators mark discourse relations which are implicit in the source language explicitly in the translation. Using back-translations of such explicitated connectives improves discourse relation parsing performanc…
The Chinese University of Hong Kong（香港中文大学）；University of California, Santa Cruz（加利福尼亚大学圣克鲁兹分校）
Discourse relation identification has been an active area of research for many years, and the challenge of identifying implicit relations remains largely an unsolved task, especially in the context of an open-domain dialogue system. Previous work primarily relies on a corpora of formal text which is inherently non-dialogic, i.e., news and journals. This data however is not suitable to handle the nuances of informal dialogue nor is it capable of navigating the plethora of valid topics present in open-domain dialogue. In this paper, we designed a novel discourse relation identification pipeline …
Implicit discourse relation classification is of great challenge due to the lack of connectives as strong linguistic cues, which motivates the use of annotated implicit connectives to improve the recognition. We propose a feature imitation framework in which an implicit relation network is driven to learn from another neural network with access to connectives, and thus encouraged to extract similarly salient features for accurate classification. We develop an adversarial model to enable an adaptive imitation scheme through competition between the implicit network and a rival feature discrimina…
Huazhong University of Science and Technology（华中科技大学）
A discourse containing one or more sentences describes daily issues and events for people to communicate their thoughts and opinions. As sentences are normally consist of multiple text segments, correct understanding of the theme of a discourse should take into consideration of the relations in between text segments. Although sometimes a connective exists in raw texts for conveying relations, it is more often the cases that no connective exists in between two text segments but some implicit relation does exist in between them. The task of implicit discourse relation recognition (IDRR) is to de…
The automatic identification of discourse relations is still a challenging task in natural language processing. Discourse connectives, such as "since" or "but", are the most informative cues to identify explicit relations; however discourse parsers typically use a closed inventory of such connectives. As a result, discourse relations signaled by markers outside these inventories (i.e. AltLexes) are not detected as effectively. In this paper, we propose a novel method to leverage parallel corpora in text simplification and lexical resources to automatically identify alternative lexicalizations …
University of Chinese Academy of Sciences（中国科学院大学）；Tencent Inc.（腾讯公司）；Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）
Current event-centric knowledge graphs highly rely on explicit connectives to mine relations between events. Unfortunately, due to the sparsity of connectives, these methods severely undermine the coverage of EventKGs. The lack of high-quality labelled corpora further exacerbates that problem. In this paper, we propose a knowledge projection paradigm for event relation extraction: projecting discourse knowledge to narratives by exploiting the commonalities between them. Specifically, we propose Multi-tier Knowledge Projection Network (MKPNet), which can leverage multi-tier discourse knowledge …
A fundamental requirement of any task-oriented dialogue system is the ability to generate object descriptions that refer to objects in the task domain. The subproblem of content selection for object descriptions in task-oriented dialogue has been the focus of much previous work and a large number of models have been proposed. In this paper, we use the annotated COCONUT corpus of task-oriented design dialogues to develop feature sets based on Dale and Reiters (1995) incremental model, Brennan and Clarks (1996) conceptual pact model, and Jordans (2000b) intentional influences model, and use thes…
The Hong Kong University of Science and Technology（香港科技大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
Implicit discourse relation classification is one of the most difficult parts in shallow discourse parsing as the relation prediction without explicit connectives requires the language understanding at both the text span level and the sentence level. Previous studies mainly focus on the interactions between two arguments. We argue that a powerful contextualized representation module, a bilateral multi-perspective matching module, and a global information fusion module are all important to implicit discourse analysis. We propose a novel model to combine these modules together. Extensive experim…
University of Michigan（密歇根大学）；Yahoo! Labs（雅虎实验室）；Columbia University（哥伦比亚大学）；The New Yorker（《纽约客》）
The New Yorker publishes a weekly captionless cartoon. More than 5,000 readers submit captions for it. The editors select three of them and ask the readers to pick the funniest one. We describe an experiment that compares a dozen automatic methods for selecting the funniest caption. We show that negative sentiment, human-centeredness, and lexical centrality most strongly match the funniest captions, followed by positive sentiment. These results are useful for understanding humor and also in the design of more engaging conversational agents in text and multimodal (vision+text) systems. As part …
Dublin City University（都柏林城市大学）；Huawei Technologies（华为技术）
In this paper, a novel approach is proposed to automatically construct parallel discourse corpus for dialogue machine translation. Firstly, the parallel subtitle data and its corresponding monolingual movie script data are crawled and collected from Internet. Then tags such as speaker and discourse boundary from the script data are projected to its subtitle data via an information retrieval approach in order to map monolingual discourse to bilingual texts. We not only evaluate the mapping results, but also integrate speaker information into the translation. Experiments show our proposed method…
Universidad Nacional de Educación a Distancia (UNED)（国家远程教育大学（UNED））；Université d’Avignon et des Pays de Vaucluse（阿维尼翁及沃克吕兹大学）；Ecole Polytechnique de Montréal（蒙特利尔高等理工学院）；Universitat de Barcelona（巴塞罗那大学）
At present, automatic discourse analysis is a relevant research topic in the field of NLP. However, discourse is one of the phenomena most difficult to process. Although discourse parsers have been already developed for several languages, this tool does not exist for Catalan. In order to implement this kind of parser, the first step is to develop a discourse segmenter. In this article we present the first discourse segmenter for texts in Catalan. This segmenter is based on Rhetorical Structure Theory (RST) for Spanish, and uses lexical and syntactic information to translate rules valid for Spa…
Thales DIS (Digital Identity and Security)（泰雷兹数字身份与安全公司）；CONACyT – CentroGeo（墨西哥国家科学技术委员会-地理信息学研究中心）；Universidade Fédérale do Ceará（塞阿拉联邦大学）；Polytechnique Montréal（蒙特利尔综合理工学院）
In this article, we describe some discursive segmentation methods as well as a preliminary evaluation of the segmentation quality. Although our experiment were carried for documents in French, we have developed three discursive segmentation models solely based on resources simultaneously available in several languages: marker lists and a statistic POS labeling. We have also carried out automatic evaluations of these systems against the Annodis corpus, which is a manually annotated reference. The results obtained are very encouraging.
Discourse Relations Classification and Cross-Framework Discourse Relation Classification Through the Lens of Cognitive Dimensions: An Empirical Investigation
Implicit discourse relation recognition is a challenging task as the relation prediction without explicit connectives in discourse parsing needs understanding of text spans and cannot be easily derived from surface features from the input sentence pairs. Thus, properly representing the text is very crucial to this task. In this paper, we propose a model augmented with different grained text representations, including character, subword, word, sentence, and sentence pair levels. The proposed deeper model is evaluated on the benchmark treebank and achieves state-of-the-art accuracy with greater …
Laboratoire Informatique d’Avignon, UAPV（阿维尼翁信息学实验室（UAPV））；Institut Universitari de Lingüística Aplicada, UPF（庞培法布拉大学应用语言学大学院（UPF））；Djibouti Institute of Science and Information Technologies – CERD（吉布提科学与信息技术研究所 – CERD）
Multilingual discourse parsing is a very prominent research topic. The first stage for discourse parsing is discourse segmentation. The study reported in this article addresses a review of two on-line available discourse segmenters (for English and Portuguese). We evaluate the possibility of developing similar discourse segmenters for Spanish, French and African languages.
Implicit discourse relation recognition is a challenging task due to the absence of the necessary informative clue from explicit connectives. The prediction of relations requires a deep understanding of the semantic meanings of sentence pairs. As implicit discourse relation recognizer has to carefully tackle the semantic similarity of the given sentence pairs and the severe data sparsity issue exists in the meantime, it is supposed to be beneficial from mastering the entire training data. Thus in this paper, we propose a novel memory mechanism to tackle the challenges for further performance i…
Tel Aviv University（特拉维夫大学）；Google AI（谷歌人工智能）；Allen Institute for AI（艾伦人工智能研究所）
Sentence fusion is the task of joining several independent sentences into a single coherent text. Current datasets for sentence fusion are small and insufficient for training modern neural models. In this paper, we propose a method for automatically-generating fusion examples from raw text and present DiscoFuse, a large scale dataset for discourse-based sentence fusion. We author a set of rules for identifying a diverse set of discourse phenomena in raw text, and decomposing the text into two independent sentences. We apply our approach on two document collections: Wikipedia and Sports article…
So far and trying to reach human capabilities, research in automatic summarization has been based on hypothesis that are both enabling and limiting. Some of these limitations are: how to take into account and reflect (in the generated summary) the implicit information conveyed in the text, the author intention, the reader intention, the context influence, the general world knowledge. Thus, if we want machines to mimic human abilities, then they will need access to this same large variety of knowledge. The implicit is affecting the orientation and the argumentation of the text and consequently …
This paper presents an analysis of temporal anaphora in sentences which contain quantification over events, within the framework of Discourse Representation Theory. The analysis in (Partee 1984) of quantified sentences, introduced by a temporal connective, gives the wrong truth-conditions when the temporal connective in the subordinate clause is "before" or "after". This problem has been previously analyzed in (de Swart 1991) as an instance of the proportion problem, and given a solution from a Generalized Quantifier approach. By using a careful distinction between the different notions of ref…
IRIT (CNRS)（法国国家科学研究中心信息与电信技术研究所）；IRIT (University of Toulouse)（图卢兹大学信息与电信技术研究所）
Discourse markers ({\it by contrast}, {\it happily}, etc.) are words or phrases that are used to signal semantic and/or pragmatic relationships between clauses or sentences. Recent work has fruitfully explored the prediction of discourse markers between sentence pairs in order to learn accurate sentence representations, that are useful in various classification tasks. In this work, we take another perspective: using a model trained to predict discourse markers between sentence pairs, we predict plausible markers between sentence pairs with a known semantic relation (provided by existing classi…
Many complex discourse-level tasks can aid domain experts in their work but require costly expert annotations for data creation. To speed up and ease annotations, we investigate the viability of automatically generated annotation suggestions for such tasks. As an example, we choose a task that is particularly hard for both humans and machines: the segmentation and classification of epistemic activities in diagnostic reasoning texts. We create and publish a new dataset covering two domains and carefully analyse the suggested annotations. We find that suggestions have positive effects on annotat…
Discourse parsing could not yet take full advantage of the neural NLP revolution, mostly due to the lack of annotated datasets. We propose a novel approach that uses distant supervision on an auxiliary task (sentiment classification), to generate abundant data for RST-style discourse structure prediction. Our approach combines a neural variant of multiple-instance learning, using document-level supervision, with an optimal CKY-style tree generation algorithm. In a series of experiments, we train a discourse parser (for only structure prediction) on our automatically generated dataset and compa…
Synapse Développement（突触开发公司）；IRIT, University of Toulouse（图卢兹大学IRIT研究所）；IRIT, CNRS（法国国家科学研究中心IRIT研究所）
Current state of the art systems in NLP heavily rely on manually annotated datasets, which are expensive to construct. Very little work adequately exploits unannotated data -- such as discourse markers between sentences -- mainly because of data sparseness and ineffective extraction methods. In the present work, we propose a method to automatically discover sentence pairs with relevant discourse markers, and apply it to massive amounts of data. Our resulting dataset contains 174 discourse markers with at least 10k examples each, even for rare markers such as coincidentally or amazingly We use …
Language Technologies Institute（语言技术研究所）；Carnegie Mellon University（卡内基梅隆大学）
Identifying the salience (i.e. importance) of discourse units is an important task in language understanding. While events play important roles in text documents, little research exists on analyzing their saliency status. This paper empirically studies the Event Salience task and proposes two salience detection models based on content similarities and discourse relations. The first is a feature based salience model that incorporates similarities among discourse units. The second is a neural model that captures more complex relations between discourse units. Tested on our new large-scale event …
We study the problem of automatic fact-checking, paying special attention to the impact of contextual and discourse information. We address two related tasks: (i) detecting check-worthy claims, and (ii) fact-checking claims. We develop supervised systems based on neural networks, kernel-based support vector machines, and combinations thereof, which make use of rich input representations in terms of discourse cues and contextual features. For the check-worthiness estimation task, we focus on political debates, and we model the target claim in the context of the full intervention of a participan…
Abstractive conversation summarization has received much attention recently. However, these generated summaries often suffer from insufficient, redundant, or incorrect content, largely due to the unstructured and complex characteristics of human-human interactions. To this end, we propose to explicitly model the rich structures in conversations for more precise and accurate conversation summarization, by first incorporating discourse relations between utterances and action triples ("who-doing-what") in utterances through structured graphs to better encode conversations, and then designing a mu…
Long-form answers, consisting of multiple sentences, can provide nuanced and comprehensive answers to a broader set of questions. To better understand this complex and understudied task, we study the functional structure of long-form answers collected from three datasets, ELI5, WebGPT and Natural Questions. Our main goal is to understand how humans organize information to craft complex answers. We develop an ontology of six sentence-level functional roles for long-form answers, and annotate 3.9k sentences in 640 answer paragraphs. Different answer collection methods manifest in different disco…
The Ohio State University（俄亥俄州立大学）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）
This paper presents a data-driven study focusing on analyzing and predicting sentence deletion -- a prevalent but understudied phenomenon in document simplification -- on a large English text simplification corpus. We inspect various document and discourse factors associated with sentence deletion, using a new manually annotated sentence alignment corpus we collected. We reveal that professional editors utilize different strategies to meet readability standards of elementary and middle schools. To predict whether a sentence will be deleted during simplification to a certain level, we harness a…
