Adapted End-to-End Coreference Resolution System for Anaphoric Identities in Dialogues

Xu, Liyan; Choi, Jinho D.

doi:10.18653/v1/2021.codi-sharedtask.6

Cited by 3 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Model For all experiments, we use the higherorder inference (HOI) coreference resolution model (Xu and Choi, 2020), modified slightly to predict singleton clusters (Xu and Choi, 2021). Given a document, HOI encodes texts with an encoder and enumerates all possible spans to detect mentions.…”

Section: Methodsmentioning

confidence: 99%

“…Coreference resolution in dialogue has recently reemerged as an area of research, with multiple datasets created and annotated for coreference resolution (Li et al (2016), Khosla et al (2021), more in Table 1) and the development of dialogue-specific models (Xu and Choi, 2021;Kobayashi et al, 2021;Kim et al, 2021). The datasets can be broadly categorized into transcripts of spoken conversations (e.g.…”

Section: Dialogue Coreference Resolutionmentioning

confidence: 99%

See 1 more Smart Citation

Multilingual Coreference Resolution in Multiparty Dialogue

Zheng¹,

Xia²,

Yarmohammadi³

et al. 2022

Preprint

View full text Add to dashboard Cite

Existing multiparty dialogue datasets for coreference resolution are nascent, and many challenges are still unaddressed. We create a largescale dataset, Multilingual Multiparty Coref (MMC), for this task based on TV transcripts. Due to the availability of gold-quality subtitles in multiple languages, we propose reusing the annotations to create silver coreference data in other languages (Chinese and Farsi) via annotation projection. On the gold (English) data, off-the-shelf models perform relatively poorly on MMC, suggesting that MMC has broader coverage of multiparty coreference than prior datasets. On the silver data, we find success both using it for data augmentation and training from scratch, which effectively simulates the zero-shot cross-lingual setting.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Dialogue Coreference Resolutionmentioning

confidence: 99%

Multilingual Coreference Resolution in Multiparty Dialogue

Zheng¹,

Xia²,

Yarmohammadi³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…pronouns are not considered in DocRED). Second, we support prediction of the singleton entity (entity with only one mention) by optimizing mention scores as suggested by Xu and Choi (2021). Full model details are described in Appendix A.1.…”

Section: Baselinementioning

confidence: 99%

“…pronouns are not annotated. In addition, we support predicting the singleton entity (entity with only one mention) in the same way as Xu and Choi (2021), by keeping all mention candidates whose mention scores > 0 regardless they co-refer with other mentions or not. Thereby a binary crossentropy optimization on mention scores is added in the training loss.…”

Section: A Appendixmentioning

confidence: 99%

Modeling Task Interactions in Document-Level Joint Entity and Relation Extraction

Li¹,

Choi²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

We target on the document-level relation extraction in an end-to-end setting, where the model needs to jointly perform mention extraction, coreference resolution (COREF) and relation extraction (RE) at once, and gets evaluated in an entity-centric way. Especially, we address the two-way interaction between COREF and RE that has not been the focus by previous work, and propose to introduce explicit interaction namely Graph Compatibility (GC) that is specifically designed to leverage task characteristics, bridging decisions of two tasks for direct task interference. Our experiments are conducted on DocRED and DWIE; in addition to GC, we implement and compare different multi-task settings commonly adopted in previous work, including pipeline, shared encoders, graph propagation, to examine the effectiveness of different interactions. The result shows that GC achieves the best performance by up to 2.3/5.1 F1 improvement over the baseline.

show abstract

“…Designed for identity anaphora resolution, these models were also adapted for bridging and discourse deixis resolution. Examples of span-based models submitted for CCST 2021 include systems by Kobayashi et al (2021), Renner et al (2021), Xu and Choi (2021). Other participants presented different approaches.…”

Section: Introductionmentioning

confidence: 99%

Anaphora Resolution in Dialogue: Description of the DFKI-TalkingRobots System for the CODI-CRAC 2021 Shared-Task

Anikina¹,

Oğuz²,

Skachkova³

et al. 2021

Proceedings of the CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue

View full text Add to dashboard Cite

We describe the system developed by the DFKI-TalkingRobots Team for the CODI-CRAC 2021 Shared-Task on anaphora resolution in dialogue. Our system consists of three subsystems: (1) the Workspace Coreference System (WCS) incrementally clusters mentions using semantic similarity based on embeddings combined with lexical feature heuristics; (2) the Mention-to-Mention (M2M) coreference resolution system pairs same entity mentions; (3) the Discourse Deixis Resolution (DDR) system employs a Siamese Network to detect discourse anaphor-antecedent pairs. WCS achieved F1-score of 55.6% averaged across the evaluation test sets, M2M 57.2% and DDR 21.5%, all on predicted mentions.

show abstract

Adapted End-to-End Coreference Resolution System for Anaphoric Identities in Dialogues

Cited by 3 publications

References 16 publications

Multilingual Coreference Resolution in Multiparty Dialogue

Multilingual Coreference Resolution in Multiparty Dialogue

Modeling Task Interactions in Document-Level Joint Entity and Relation Extraction

Anaphora Resolution in Dialogue: Description of the DFKI-TalkingRobots System for the CODI-CRAC 2021 Shared-Task

Contact Info

Product

Resources

About