Bonnie Webber

Jan-Christoph Klie, Bonnie Webber, Iryna Gurevych

Annotated data is an essential ingredient in natural language processing for training and evaluating machine learning models. It is therefore very desirable for the annotations to be of high quality. Recent work, however, has shown that several popular datasets contain a surprising amount of annotation errors or inconsistencies. To alleviate this issue, many methods for annotation error detection have been devised over the years. While researchers show that their approaches work well on their newly introduced datasets, they rarely compare their methods to previous work or on the same datasets. This raises strong concerns on methods' general performance and makes it difficult to asses their strengths and weaknesses. We therefore reimplement 18 methods for detecting potential annotation errors and evaluate them on 9 English datasets for text classification as well as token and span labeling. In addition, we define a uniform evaluation setup including a new formalization of the annotation error detection task, evaluation protocol and general best practices. To facilitate future research and reproducibility, we release our datasets and implementations in an easy-to-use and open source software package.

Zheng Zhao, Bonnie Webber

In the PDTB-3, several thousand implicit discourse relations were newly annotated \textit{within} individual sentences, adding to the over 15,000 implicit relations annotated \textit{across} adjacent sentences in the PDTB-2. Given that the position of the arguments to these \textit{intra-sentential implicits} is no longer as well-defined as with \textit{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.

Zheng Zhao, Yftah Ziser, Bonnie Webber et al.

We present an analysis tool based on joint matrix factorization for comparing latent representations of multilingual and monolingual models. An alternative to probing, this tool allows us to analyze multiple sets of representations in a joint manner. Using this tool, we study to what extent and how morphosyntactic features are reflected in the representations learned by multilingual pre-trained models. We conduct a large-scale empirical study of over 33 languages and 17 morphosyntactic categories. Our findings demonstrate variations in the encoding of morphosyntactic information across upper and lower layers, with category-specific differences influenced by language properties. Hierarchical clustering of the factorization outputs yields a tree structure that is related to phylogenetic trees manually crafted by linguists. Moreover, we find the factorization outputs exhibit strong associations with performance observed across different cross-lingual tasks. We release our code to facilitate future research.

Longyue Wang, Zhaopeng Tu, Yan Gu et al.

Translating literary works has perennially stood as an elusive dream in machine translation (MT), a journey steeped in intricate challenges. To foster progress in this domain, we hold a new shared task at WMT 2023, the first edition of the Discourse-Level Literary Translation. First, we (Tencent AI Lab and China Literature Ltd.) release a copyrighted and document-level Chinese-English web novel corpus. Furthermore, we put forth an industry-endorsed criteria to guide human evaluation process. This year, we totally received 14 submissions from 7 academia and industry teams. We employ both automatic and human evaluations to measure the performance of the submitted systems. The official ranking of the systems is based on the overall human judgments. In addition, our extensive analysis reveals a series of interesting findings on literary and discourse-aware MT. We release data, system outputs, and leaderboard at http://www2.statmt.org/wmt23/literary-translation-task.html.

Wanqiu Long, Bonnie Webber

Implicit discourse relation recognition is a challenging task that involves identifying the sense or senses that hold between two adjacent spans of text, in the absence of an explicit connective between them. In both PDTB-2 and PDTB-3, discourse relational senses are organized into a three-level hierarchy ranging from four broad top-level senses, to more specific senses below them. Most previous work on implicit discourse relation recognition have used the sense hierarchy simply to indicate what sense labels were available. Here we do more -- incorporating the sense hierarchy into the recognition process itself and using it to select the negative examples used in contrastive learning. With no additional effort, the approach achieves state-of-the-art performance on the task.

Wanqiu Long, Bonnie Webber

Implicit discourse relation recognition involves determining relationships that hold between spans of text that are not linked by an explicit discourse connective. In recent years, the pre-train, prompt, and predict paradigm has emerged as a promising approach for tackling this task. However, previous work solely relied on manual verbalizers for implicit discourse relation recognition, which suffer from issues of ambiguity and even incorrectness. To overcome these limitations, we leverage the prototypes that capture certain class-level semantic features and the hierarchical label structure for different classes as the verbalizer. We show that our method improves on competitive baselines. Besides, our proposed approach can be extended to enable zero-shot cross-lingual learning, facilitating the recognition of discourse relations in languages with scarce resources. These advancement validate the practicality and versatility of our approach in addressing the issues of implicit discourse relation recognition across different languages.

Zahra Bokaei, Walid Magdy, Bonnie Webber

Toxic language detection is crucial for creating safer online environments and limiting the spread of harmful content. While toxic language detection has been under-explored in Persian, the current work compares different methods for this task, including fine-tuning, data enrichment, zero-shot and few-shot learning, and cross-lingual transfer learning. What is especially compelling is the impact of cultural context on transfer learning for this task: We show that the language of a country with cultural similarities to Persian yields better results in transfer learning. Conversely, the improvement is lower when the language comes from a culturally distinct country. Warning: This paper contains examples of toxic language that may disturb some readers. These examples are included for the purpose of research on toxic detection.

Wanqiu Long, N. Siddharth, Bonnie Webber

Discourse relations play a pivotal role in establishing coherence within textual content, uniting sentences and clauses into a cohesive narrative. The Penn Discourse Treebank (PDTB) stands as one of the most extensively utilized datasets in this domain. In PDTB-3, the annotators can assign multiple labels to an example, when they believe that multiple relations are present. Prior research in discourse relation recognition has treated these instances as separate examples during training, and only one example needs to have its label predicted correctly for the instance to be judged as correct. However, this approach is inadequate, as it fails to account for the interdependence of labels in real-world contexts and to distinguish between cases where only one sense relation holds and cases where multiple relations hold simultaneously. In our work, we address this challenge by exploring various multi-label classification frameworks to handle implicit discourse relation recognition. We show that multi-label classification methods don't depress performance for single-label prediction. Additionally, we give comprehensive analysis of results and data. Our work contributes to advancing the understanding and application of discourse relations and provide a foundation for the future study

Shiran Dudy, Steven Bedrick, Bonnie Webber

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.

Laurie Burchell, Jie Chi, Tom Hosking et al.

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.

Li Liang, Zheng Zhao, Bonnie Webber

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.

Zheng Zhao, Shay B. Cohen, Bonnie Webber

It is well-known that abstractive summaries are subject to hallucination---including 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 F$_1$. Preliminary human evaluation of up-ranked vs. original summaries shows people's preference for the former.

Wanqiu Long, Xinyi Cai, James E. M. Reid et al.

Text corpora annotated with language-related properties are an important resource for the development of Language Technology. The current work contributes a new resource for Chinese Language Technology and for Chinese-English translation, in the form of a set of TED talks (some originally given in English, some in Chinese) that have been annotated with discourse relations in the style of the Penn Discourse TreeBank, adapted to properties of Chinese text that are not present in English. The resource is currently unique in annotating discourse-level properties of planned spoken monologues rather than of written text. An inter-annotator agreement study demonstrates that the annotation scheme is able to achieve highly reliable results.

Liane Guillou, Christian Hardmeier, Preslav Nakov et al.

We describe the design, the evaluation setup, and the results of the 2016 WMT shared task on cross-lingual pronoun prediction. This is a classification task in which participants are asked to provide predictions on what pronoun class label should replace a placeholder value in the target-language text, provided in lemmatised and PoS-tagged form. We provided four subtasks, for the English-French and English-German language pairs, in both directions. Eleven teams participated in the shared task; nine for the English-French subtask, five for French-English, nine for English-German, and six for German-English. Most of the submissions outperformed two strong language-model based baseline systems, with systems using deep recurrent neural networks outperforming those using other architectures for most language pairs.

Jun Quan, Deyi Xiong, Bonnie Webber et al.

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.

Jingfeng Yang, Federico Fancellu, Bonnie Webber

The availability of corpora to train semantic parsers in English has lead to significant advances in the field. Unfortunately, for languages other than English, annotation is scarce and so are developed parsers. We then ask: could a parser trained in English be applied to language that it hasn't been trained on? To answer this question we explore zero-shot cross-lingual semantic parsing where we train an available coarse-to-fine semantic parser (Liu et al., 2018) using cross-lingual word embeddings and universal dependencies in English and test it on Italian, German and Dutch. Results on the Parallel Meaning Bank - a multilingual semantic graphbank, show that Universal Dependency features significantly boost performance when used in conjunction with other lexical features but modelling the UD structure directly when encoding the input does not.

Federico Fancellu, Adam Lopez, Bonnie Webber

Negation scope has been annotated in several English and Chinese corpora, and highly accurate models for this task in these languages have been learned from these annotations. Unfortunately, annotations are not available in other languages. Could a model that detects negation scope be applied to a language that it hasn't been trained on? We develop neural models that learn from cross-lingual word embeddings or universal dependencies in English, and test them on Chinese, showing that they work surprisingly well. We find that modelling syntax is helpful even in monolingual settings and that cross-lingual word embeddings help relatively little, and we analyse cases that are still difficult for this task.

Joachim Fainberg, Ben Krause, Mihai Dobre et al.

Conversational agents are gaining popularity with the increasing ubiquity of smart devices. However, training agents in a data driven manner is challenging due to a lack of suitable corpora. This paper presents a novel method for gathering topical, unstructured conversational data in an efficient way: self-dialogues through crowd-sourcing. Alongside this paper, we include a corpus of 3.6 million words across 23 topics. We argue the utility of the corpus by comparing self-dialogues with standard two-party conversations as well as data from other corpora.

Yutong Shao, Rico Sennrich, Bonnie Webber et al.

Idiom translation is a challenging problem in machine translation because the meaning of idioms is non-compositional, and a literal (word-by-word) translation is likely to be wrong. In this paper, we focus on evaluating the quality of idiom translation of MT systems. We introduce a new evaluation method based on an idiom-specific blacklist of literal translations, based on the insight that the occurrence of any blacklisted words in the translation output indicates a likely translation error. We introduce a dataset, CIBB (Chinese Idioms Blacklists Bank), and perform an evaluation of a state-of-the-art Chinese-English neural MT system. Our evaluation confirms that a sizable number of idioms in our test set are mistranslated (46.1%), that literal translation error is a common error type, and that our blacklist method is effective at identifying literal translation errors.

Ben Krause, Marco Damonte, Mihai Dobre et al.

We present Edina, the University of Edinburgh's social bot for the Amazon Alexa Prize competition. Edina is a conversational agent whose responses utilize data harvested from Amazon Mechanical Turk (AMT) through an innovative new technique we call self-dialogues. These are conversations in which a single AMT Worker plays both participants in a dialogue. Such dialogues are surprisingly natural, efficient to collect and reflective of relevant and/or trending topics. These self-dialogues provide training data for a generative neural network as well as a basis for soft rules used by a matching score component. Each match of a soft rule against a user utterance is associated with a confidence score which we show is strongly indicative of reply quality, allowing this component to self-censor and be effectively integrated with other components. Edina's full architecture features a rule-based system backing off to a matching score, backing off to a generative neural network. Our hybrid data-driven methodology thus addresses both coverage limitations of a strictly rule-based approach and the lack of guarantees of a strictly machine-learning approach.

Federico Fancellu, Siva Reddy, Adam Lopez et al.

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$\lnot$ 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.