Deep Cross-Lingual Coreference Resolution for Less-Resourced Languages: The Case of Basque

Urbizu, Gorka; Soraluze, Ander; Arregi, Olatz

doi:10.18653/v1/w19-2806

Cited by 11 publications

(13 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The importance of improvements in the task can be found in its use in stateof-the-art approaches of other tasks such as Entity Linking (Kundu et al, 2018;Ling et al, 2015), Machine Translation (Popescu-Belis, 2019Urbizu et al, 2019;Voita et al, 2018), Summarization (Song et al, 2019;Barros et al, 2019) and Chat Bots (Zhu et al, 2018;Jonell et al, 2018). As a result, we believe that the best approach is to enhance the current language modelling approaches, utilized by all the majority of the tasks, with coreference information.…”

Section: Discussionmentioning

confidence: 99%

A Neural Entity Coreference Resolution Review

Stylianou,

Vlahavas

2019

Preprint

View full text Add to dashboard Cite

Entity Coreference Resolution is the task of resolving all the mentions in a document that refer to the same real world entity and is considered as one of the most difficult tasks in natural language understanding. While in it is not an end task, it has been proved to improve downstream natural language processing tasks such as entity linking, machine translation, summarization and chatbots. We conducted a systematic a review of neural-based approached and provide a detailed appraisal of the datasets and evaluation metrics in the field. Emphasis is given on Pronoun Resolution, a subtask of Coreference Resolution, which has seen various improvements in the recent years. We conclude the study by highlight the lack of agreed upon standards and propose a way to expand the task even further.

show abstract

Section: Discussionmentioning

confidence: 99%

A Neural Entity Coreference Resolution Review

Stylianou,

Vlahavas

2019

Preprint

View full text Add to dashboard Cite

show abstract

“…For some languages, annotated resources are either not available or very scarce, which is one of the reasons why authors experiment with learning cross-lingual coreference resolution. For example, Urbizu et al [23] present a coreference resolution system for the Basque language, which they train on an English corpus. They compare the cross-lingual system with a monolingual (Basque) one and show that the cross-lingual system works slightly better.…”

Section: Coreference Resolution In Non-english Languagesmentioning

confidence: 99%

Neural coreference resolution for Slovene language

Klemen

Žitnik

2022

ComSIS

View full text Add to dashboard Cite

Coreference resolution systems aim to recognize and cluster together mentions of the same underlying entity. While there exist large amounts of research on broadly spoken languages such as English and Chinese, research on coreference in other languages is comparably scarce. In this work we first present SentiCoref 1.0 - a coreference resolution dataset for Slovene language that is comparable to English-based corpora. Further, we conduct a series of analyses using various complex models that range from simple linear models to current state-of-the-art deep neural coreference approaches leveraging pre-trained contextual embeddings. Apart from SentiCoref, we evaluate models also on a smaller coref149 Slovene dataset to justify the creation of a new corpus. We investigate robustness of the models using cross-domain data and data augmentations. Models using contextual embeddings achieve the best results - up to 0.92 average F1 score for the SentiCoref dataset. Cross-domain experiments indicate that SentiCoref allows the models to learn more general patterns, which enables them to outperform models, learned on coref149 only.

show abstract

“…Cross-lingual transfer learning has been studied for other NLP and IE tasks, including sentiment analysis (Chen et al, 2018b), relation extraction (Lin et al, 2017;Zou et al, 2018;Wang et al, 2018;, event extraction (Chen and Ji, 2009a;Hsi et al, 2016;Subburathinam et al, 2019b;Nguyen et al, 2021b), and entity coreference resolution (Rahman and Ng, 2012;Hardmeier et al, 2013;Martins, 2015;Kundu et al, 2018;Urbizu et al, 2019). Compared to such prior work, this paper presents two novel approaches to improve the language generalization of representation vectors based on multi-view alignment and OT.…”

Section: Related Workmentioning

confidence: 99%

Learning Cross-lingual Representations for Event Coreference Resolution with Multi-view Alignment and Optimal Transport

Phung¹,

Tran²,

Nguyen³

et al. 2021

Proceedings of the 1st Workshop on Multilingual Representation Learning

View full text Add to dashboard Cite

We study a new problem of cross-lingual transfer learning for event coreference resolution (ECR) where models trained on data from a source language are adapted for evaluations in different target languages. We introduce the first baseline model for this task based on XLM-RoBERTa, a state-of-the-art multilingual pre-trained language model. We also explore language adversarial neural networks (LANN) that present language discriminators to distinguish texts from the source and target languages to improve the language generalization for ECR. In addition, we introduce two novel mechanisms to further enhance the general representation learning of LANN, featuring: (i) multi-view alignment to penalize cross coreference-label alignment of examples in the source and target languages, and (ii) optimal transport to select close examples in the source and target languages to provide better training signals for the language discriminators. Finally, we perform extensive experiments for cross-lingual ECR from English to Spanish and Chinese to demonstrate the effectiveness of the proposed methods.

show abstract

Deep Cross-Lingual Coreference Resolution for Less-Resourced Languages: The Case of Basque

Cited by 11 publications

References 24 publications

A Neural Entity Coreference Resolution Review

A Neural Entity Coreference Resolution Review

Neural coreference resolution for Slovene language

Learning Cross-lingual Representations for Event Coreference Resolution with Multi-view Alignment and Optimal Transport

Contact Info

Product

Resources

About