Cross-document event coreference resolution (CDCR) is an NLP task in which mentions of events need to be identified and clustered throughout a collection of documents. CDCR aims to benefit downstream multi-document applications, but despite recent progress on corpora and system development, downstream improvements from applying CDCR have not been shown yet. We make the observation that every CDCR system to date was developed, trained, and tested only on a single respective corpus. This raises strong concerns on their generalizability -- a must-have for downstream applications where the magnitude of domains or event mentions is likely to exceed those found in a curated corpus. To investigate this assumption, we define a uniform evaluation setup involving three CDCR corpora: ECB+, the Gun Violence Corpus and the Football Coreference Corpus (which we reannotate on token level to make our analysis possible). We compare a corpus-independent, feature-based system against a recent neural system developed for ECB+. Whilst being inferior in absolute numbers, the feature-based system shows more consistent performance across all corpora whereas the neural system is hit-and-miss. Via model introspection, we find that the importance of event actions, event time, etc. for resolving coreference in practice varies greatly between the corpora. Additional analysis shows that several systems overfit on the structure of the ECB+ corpus. We conclude with recommendations on how to achieve generally applicable CDCR systems in the future -- the most important being that evaluation on multiple CDCR corpora is strongly necessary. To facilitate future research, we release our dataset, annotation guidelines, and system implementation to the public.
Technische Universität Darmstadt（达姆施塔特工业大学）；Heidelberg University（海德堡大学）；Queen Mary University of London（伦敦玛丽女王大学）；Heidelberg Institute for Theoretical Studies gGmbH（海德堡理论研究所）
The common practice in coreference resolution is to identify and evaluate the maximum span of mentions. The use of maximum spans tangles coreference evaluation with the challenges of mention boundary detection like prepositional phrase attachment. To address this problem, minimum spans are manually annotated in smaller corpora. However, this additional annotation is costly and therefore, this solution does not scale to large corpora. In this paper, we propose the MINA algorithm for automatically extracting minimum spans to benefit from minimum span evaluation in all corpora. We show that the e…
Technische Universität Darmstadt（达姆施塔特工业大学）；Heidelberg Institute for Theoretical Studies gGmbH（海德堡理论研究所有限责任公司）
Coreference resolution is an intermediate step for text understanding. It is used in tasks and domains for which we do not necessarily have coreference annotated corpora. Therefore, generalization is of special importance for coreference resolution. However, while recent coreference resolvers have notable improvements on the CoNLL dataset, they struggle to generalize properly to new domains or datasets. In this paper, we investigate the role of linguistic features in building more generalizable coreference resolvers. We show that generalization improves only slightly by merely using a set of a…
Coreference resolution is an important component in analyzing narrative text from administrative data (e.g., clinical or police sources). However, existing coreference models trained on general language corpora suffer from poor transferability due to domain gaps, especially when they are applied to gender-inclusive data with lesbian, gay, bisexual, and transgender (LGBT) individuals. In this paper, we analyzed the challenges of coreference resolution in an exemplary form of administrative text written in English: violent death narratives from the USA's Centers for Disease Control's (CDC) Natio…
Queen Mary University of London（伦敦玛丽女王大学）；UKP Lab, Technische Universität Darmstadt（德国达姆施塔特工业大学UKP实验室）
Now that the performance of coreference resolvers on the simpler forms of anaphoric reference has greatly improved, more attention is devoted to more complex aspects of anaphora. One limitation of virtually all coreference resolution models is the focus on single-antecedent anaphors. Plural anaphors with multiple antecedents-so-called split-antecedent anaphors (as in John met Mary. They went to the movies) have not been widely studied, because they are not annotated in ONTONOTES and are relatively infrequent in other corpora. In this paper, we introduce the first model for unrestricted resolut…
University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；Brown University（布朗大学）；Google（谷歌）
Large-scale, high-quality corpora are critical for advancing research in coreference resolution. However, existing datasets vary in their definition of coreferences and have been collected via complex and lengthy guidelines that are curated for linguistic experts. These concerns have sparked a growing interest among researchers to curate a unified set of guidelines suitable for annotators with various backgrounds. In this work, we develop a crowdsourcing-friendly coreference annotation methodology, ezCoref, consisting of an annotation tool and an interactive tutorial. We use ezCoref to re-anno…
Language Technologies Institute（语言技术研究所）；Carnegie Mellon University（卡内基梅隆大学）
Coreference resolution (CR) is an essential part of discourse analysis. Most recently, neural approaches have been proposed to improve over SOTA models from earlier paradigms. So far none of the published neural models leverage external semantic knowledge such as type information. This paper offers the first such model and evaluation, demonstrating modest gains in accuracy by introducing either gold standard or predicted types. In the proposed approach, type information serves both to (1) improve mention representation and (2) create a soft type consistency check between coreference candidate …
Queen Mary University of London（伦敦玛丽女王大学）；Google Research（谷歌研究院）
Mention detection is an important preprocessing step for annotation and interpretation in applications such as NER and coreference resolution, but few stand-alone neural models have been proposed able to handle the full range of mentions. In this work, we propose and compare three neural network-based approaches to mention detection. The first approach is based on the mention detection part of a state of the art coreference resolution system; the second uses ELMO embeddings together with a bidirectional LSTM and a biaffine classifier; the third approach uses the recently introduced BERT model.…
We propose a multi task learning-based neural model for resolving bridging references tackling two key challenges. The first challenge is the lack of large corpora annotated with bridging references. To address this, we use multi-task learning to help bridging reference resolution with coreference resolution. We show that substantial improvements of up to 8 p.p. can be achieved on full bridging resolution with this architecture. The second challenge is the different definitions of bridging used in different corpora, meaning that hand-coded systems or systems using special features designed for…
Coreference resolution is an important task for natural language understanding, and the resolution of ambiguous pronouns a longstanding challenge. Nonetheless, existing corpora do not capture ambiguous pronouns in sufficient volume or diversity to accurately indicate the practical utility of models. Furthermore, we find gender bias in existing corpora and systems favoring masculine entities. To address this, we present and release GAP, a gender-balanced labeled corpus of 8,908 ambiguous pronoun-name pairs sampled to provide diverse coverage of challenges posed by real-world text. We explore a …
Islamic Azad University Tehran North Branch（伊斯兰阿扎德大学德黑兰北部分校）；Shahid Beheshti University（沙希德·贝赫什提大学）
Pronoun resolution is a challenging subset of an essential field in natural language processing called coreference resolution. Coreference resolution is about finding all entities in the text that refers to the same real-world entity. This paper presents a hybrid model combining multiple rulebased sieves with a machine-learning sieve for pronouns. For this purpose, seven high-precision rule-based sieves are designed for the Persian language. Then, a random forest classifier links pronouns to the previous partial clusters. The presented method demonstrates exemplary performance using pipeline d…
This paper proposes a method to analyze Japanese anaphora, in which zero pronouns (omitted obligatory cases) are used to refer to preceding entities (antecedents). Unlike the case of general coreference resolution, zero pronouns have to be detected prior to resolution because they are not expressed in discourse. Our method integrates two probability parameters to perform zero pronoun detection and resolution in a single framework. The first parameter quantifies the degree to which a given case is a zero pronoun. The second parameter quantifies the degree to which a given entity is the antecede…
Cross-document event coreference resolution is a foundational task for NLP applications involving multi-text processing. However, existing corpora for this task are scarce and relatively small, while annotating only modest-size clusters of documents belonging to the same topic. To complement these resources and enhance future research, we present Wikipedia Event Coreference (WEC), an efficient methodology for gathering a large-scale dataset for cross-document event coreference from Wikipedia, where coreference links are not restricted within predefined topics. We apply this methodology to the …
School of Computer Science and Engineering（计算机科学与工程学院）；The Hebrew University of Jerusalem（希伯来大学）
Recent works have found evidence of gender bias in models of machine translation and coreference resolution using mostly synthetic diagnostic datasets. While these quantify bias in a controlled experiment, they often do so on a small scale and consist mostly of artificial, out-of-distribution sentences. In this work, we find grammatical patterns indicating stereotypical and non-stereotypical gender-role assignments (e.g., female nurses versus male dancers) in corpora from three domains, resulting in a first large-scale gender bias dataset of 108K diverse real-world English sentences. We manual…
The Hebrew University of Jerusalem（希伯来大学）；Bar Ilan University（巴伊兰大学）
Machine translation (MT) requires a wide range of linguistic capabilities, which current end-to-end models are expected to learn implicitly by observing aligned sentences in bilingual corpora. In this work, we ask: \emph{How well do MT models learn coreference resolution from implicit signal?} To answer this question, we develop an evaluation methodology that derives coreference clusters from MT output and evaluates them without requiring annotations in the target language. We further evaluate several prominent open-source and commercial MT systems, translating from English to six target langu…
Studies of the contextual and linguistic factors that constrain discourse phenomena such as reference are coming to depend increasingly on annotated language corpora. In preparing the corpora, it is important to evaluate the reliability of the annotation, but methods for doing so have not been readily available. In this report, I present a method for computing reliability of coreference annotation. First I review a method for applying the information retrieval metrics of recall and precision to coreference annotation proposed by Marc Vilain and his collaborators. I show how this method makes i…
NRC "Kurchatov institute"（国家研究中心“库尔恰托夫研究所”）；MEPhI National Research Nuclear University（莫斯科工程物理学院国家核研究大学）；I.M. Sechenov First Moscow State Medical University (Sechenov University)（谢切诺夫第一莫斯科国立医科大学（谢切诺夫大学））
We present the full-size Russian complexly NER-labeled corpus of Internet user reviews, along with an evaluation of accuracy levels reached on this corpus by a set of advanced deep learning neural networks to extract the pharmacologically meaningful entities from Russian texts. The corpus annotation includes mentions of the following entities: Medication (33005 mentions), Adverse Drug Reaction (1778), Disease (17403), and Note (4490). Two of them - Medication and Disease - comprise a set of attributes. A part of the corpus has the coreference annotation with 1560 coreference chains in 300 docu…
