Pronoun Coreference Resolution (PCR) is the task of resolving pronominal expressions to all mentions they refer to. Compared with the general coreference resolution task, the main challenge of PCR is the coreference relation prediction rather than the mention detection. As one important natural language understanding (NLU) component, pronoun resolution is crucial for many downstream tasks and still challenging for existing models, which motivates us to survey existing approaches and think about how to do better. In this survey, we first introduce representative datasets and models for the ordinary pronoun coreference resolution task. Then we focus on recent progress on hard pronoun coreference resolution problems (e.g., Winograd Schema Challenge) to analyze how well current models can understand commonsense. We conduct extensive experiments to show that even though current models are achieving good performance on the standard evaluation set, they are still not ready to be used in real applications (e.g., all SOTA models struggle on correctly resolving pronouns to infrequent objects). All experiment codes will be available upon acceptance.

Issues with coreference resolution are one of the most frequently mentioned challenges for information extraction from the biomedical literature. Thus, the biomedical genre has long been the second most researched genre for coreference resolution after the news domain, and the subject of a great deal of research for NLP in general. In recent years this interest has grown enormously leading to the development of a number of substantial datasets, of domain-specific contextual language models, and of several architectures. In this paper we review the state of-the-art of coreference in the biomedical domain with a particular attention on these most recent developments.

This paper presents a new corpus and annotation guideline for a novel coreference resolution task on fictional texts, and analyzes its unique characteristics. FantasyCoref contains 211 stories of Grimms’ Fairy Tales and 3 other fantasy literature annotated in the omniscient writer’s point of view (OWV) to handle distinctive aspects in this genre. This task is more challenging than general coreference resolution in two ways. First, documents in our corpus are 2.5 times longer than the ones in OntoNotes, raising a new layer of difficulty in resolving long-distant referents. Second, annotation of literary styles and concepts raise several issues which are not sufficiently addressed in the existing annotation guidelines. Hence, considerations on such issues and the concept of OWV are necessary to achieve high inter-annotator agreement (IAA) in coreference resolution of fictional texts. We carefully conduct annotation tasks in four stages to ensure the quality of our annotation. As a result, a high IAA score of 87% is achieved using the standard coreference evaluation metric. Finally, state-of-the-art coreference resolution approaches are evaluated on our corpus. After training with our annotated dataset, there was a 2.59% and 3.06% improvement over the model trained on the OntoNotes dataset. Also, we observe that the portion of errors specific to fictional texts declines after the training.

We present a system for resolving coreference on theater plays, DramaCoref. The system uses neural network techniques to provide a list of potential mentions. These mentions are assigned to common entities using generic and domain-specific rules. We find that DramaCoref works well on the theater plays when compared to corpora from other domains and profits from the inclusion of information specific to theater plays. On the best-performing setup, it achieves a CoNLL score of 32% when using automatically detected mentions and 55% when using gold mentions. Single rules achieve high precision scores; however, rules designed on other domains are often not applicable or yield unsatisfactory results. Error analysis shows that the mention detection is the main weakness of the system, providing directions for future improvements.

We introduce a modular, hybrid coreference resolution system that extends a rule-based baseline with three neural classifiers for the subtasks mention detection, mention attributes (gender, animacy, number), and pronoun resolution. The classifiers substantially increase coreference performance in our experiments with Dutch literature across all metrics on the development set: mention detection, LEA, CoNLL, and especially pronoun accuracy. However, on the test set, the best results are obtained with rule-based pronoun resolution. This inconsistent result highlights that the rule-based system is still a strong baseline, and more work is needed to improve pronoun resolution robustly for this dataset. While end-to-end neural systems require no feature engineering and achieve excellent performance in standard benchmarks with large training sets, our simple hybrid system scales well to long document coreference (>10k words) and attains superior results in our experiments on literature.

Large annotated corpora for coreference resolution are available for few languages. For machine translation, however, strong black-box systems exist for many languages. We empirically explore the appealing idea of leveraging such translation tools for bootstrapping coreference resolution in languages with limited resources. Two scenarios are analyzed, in which a large coreference corpus in a high-resource language is used for coreference predictions in a smaller language, i.e., by machine translating either the training corpus or the test data. In our empirical evaluation of coreference resolution using the two scenarios on several medium-resource languages, we find no improvement over monolingual baseline models. Our analysis of the various sources of error inherent to the studied scenarios, reveals that in fact the quality of contemporary machine translation tools is the main limiting factor.

Automatic coreference resolution is understudied in Danish even though most of the Danish Dependency Treebank (Buch-Kromann, 2003) is annotated with coreference relations. This paper describes a conversion of its partial, yet well-documented, coreference relations into coreference clusters and the training and evaluation of coreference models on this data. To the best of our knowledge, these are the first publicly available, neural coreference models for Danish. We also present a new entity linking annotation on the dataset using WikiData identifiers, a named entity disambiguation (NED) dataset, and a larger automatically created NED dataset enabling wikily supervised NED models. The entity linking annotation is benchmarked using a state-of-the-art neural entity disambiguation model.

Language Models are the underpin of all modern Natural Language Processing (NLP) tasks. The introduction of the Transformers architecture has contributed significantly into making Language Modeling very effective across many NLP task, leading to significant advancements in the field. However, Transformers come with a big computational cost, which grows quadratically with respect to the input length. This presents a challenge as to understand long texts requires a lot of context. In this paper, we propose a Fine-Tuning framework, named CoreLM, that extends the architecture of current Pretrained Language Models so that they incorporate explicit entity information. By introducing entity representations, we make available information outside the contextual space of the model, which results in a better Language Model for a fraction of the computational cost. We implement our approach using GPT2 and compare the fine-tuned model to the original. Our proposed model achieves a lower Perplexity in GUMBY and LAMBDADA datasets when compared to GPT2 and a fine-tuned version of GPT2 without any changes. We also compare the models’ performance in terms of Accuracy in LAMBADA and Children’s Book Test, with and without the use of model-created coreference annotations.

In pro-drop language like Arabic, Chinese, Italian, Japanese, Spanish, and many others, unrealized (null) arguments in certain syntactic positions can refer to a previously introduced entity, and are thus called anaphoric zero pronouns. The existing resources for studying anaphoric zero pronoun interpretation are however still limited. In this paper, we use five data augmentation methods to generate and detect anaphoric zero pronouns automatically. We use the augmented data as additional training materials for two anaphoric zero pronoun systems for Arabic. Our experimental results show that data augmentation improves the performance of the two systems, surpassing the state-of-the-art results.

In this paper, we develop bilingual transfer learning approaches to improve Arabic coreference resolution by leveraging additional English annotation via bilingual or multilingual pre-trained transformers. We show that bilingual transfer learning improves the strong transformer-based neural coreference models by 2-4 F1. We also systemically investigate the effectiveness of several pre-trained transformer models that differ in training corpora, languages covered, and model capacity. Our best model achieves a new state-of-the-art performance of 64.55 F1 on the Arabic OntoNotes dataset. Our code is publicly available at https://github.com/bnmin/arabic_coref.

Coreference decisions among event mentions and among co-occurring entity mentions are highly interdependent, thus motivating joint inference. Capturing the uncertainty over each variable can be crucial for inference among multiple dependent variables. Previous work on joint coreference employs heuristic approaches, lacking well-defined objectives, and lacking modeling of uncertainty on each side of the joint problem. We present a new approach of joint coreference, including (1) a formal cost function inspired by Dasgupta’s cost for hierarchical clustering, and (2) a representation for uncertainty of clustering of event and entity mentions, again based on a hierarchical structure. We describe an alternating optimization method for inference that when clustering event mentions, considers the uncertainty of the clustering of entity mentions and vice-versa. We show that our proposed joint model provides empirical advantages over state-of-the-art independent and joint models.

While coreference resolution is defined independently of dataset domain, most models for performing coreference resolution do not transfer well to unseen domains. We consolidate a set of 8 coreference resolution datasets targeting different domains to evaluate the off-the-shelf performance of models. We then mix three datasets for training; even though their domain, annotation guidelines, and metadata differ, we propose a method for jointly training a single model on this heterogeneous data mixture by using data augmentation to account for annotation differences and sampling to balance the data quantities. We find that in a zero-shot setting, models trained on a single dataset transfer poorly while joint training yields improved overall performance, leading to better generalization in coreference resolution models. This work contributes a new benchmark for robust coreference resolution and multiple new state-of-the-art results.

Recent work has shown fine-tuning neural coreference models can produce strong performance when adapting to different domains. However, at the same time, this can require a large amount of annotated target examples. In this work, we focus on supervised domain adaptation for clinical notes, proposing the use of concept knowledge to more efficiently adapt coreference models to a new domain. We develop methods to improve the span representations via (1) a retrofitting loss to incentivize span representations to satisfy a knowledge-based distance function and (2) a scaffolding loss to guide the recovery of knowledge from the span representation. By integrating these losses, our model is able to improve our baseline precision and F-1 score. In particular, we show that incorporating knowledge with end-to-end coreference models results in better performance on the most challenging, domain-specific spans.

Event coreference resolution is critical to understand events in the growing number of online news with multiple modalities including text, video, speech, etc. However, the events and entities depicting in different modalities may not be perfectly aligned and can be difficult to annotate, which makes the task especially challenging with little supervision available. To address the above issues, we propose a supervised model based on attention mechanism and an unsupervised model based on statistical machine translation, capable of learning the relative importance of modalities for event coreference resolution. Experiments on a video multimedia event dataset show that our multimodal models outperform text-only systems in event coreference resolution tasks. A careful analysis reveals that the performance gain of the multimodal model especially under unsupervised settings comes from better learning of visually salient events.

SOTA coreference resolution produces increasingly impressive scores on the OntoNotes benchmark. However lack of comparable data following the same scheme for more genres makes it difficult to evaluate generalizability to open domain data. Zhu et al. (2021) introduced the creation of the OntoGUM corpus for evaluating geralizability of the latest neural LM-based end-to-end systems. This paper covers details of the mapping process which is a set of deterministic rules applied to the rich syntactic and discourse annotations manually annotated in the GUM corpus. Out-of-domain evaluation across 12 genres shows nearly 15-20% degradation for both deterministic and deep learning systems, indicating a lack of generalizability or covert overfitting in existing coreference resolution models.

Despite significant recent progress in coreference resolution, the quality of current state-of-the-art systems still considerably trails behind human-level performance. Using the CoNLL-2012 and PreCo datasets, we dissect the best instantiation of the mainstream end-to-end coreference resolution model that underlies most current best-performing coreference systems, and empirically analyze the behavior of its two components: mention detector and mention linker. While the detector traditionally focuses heavily on recall as a design decision, we demonstrate the importance of precision, calling for their balance. However, we point out the difficulty in building a precise detector due to its inability to make important anaphoricity decisions. We also highlight the enormous room for improving the linker and show that the rest of its errors mainly involve pronoun resolution. We propose promising next steps and hope our findings will help future research in coreference resolution.