@inproceedings{otmazgin-etal-2022-f,
title = "{F}-coref: Fast, Accurate and Easy to Use Coreference Resolution",
author = "Otmazgin, Shon and
Cattan, Arie and
Goldberg, Yoav",
editor = "Buntine, Wray and
Liakata, Maria",
booktitle = "Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing: System Demonstrations",
month = nov,
year = "2022",
address = "Taipei, Taiwan",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.aacl-demo.6/",
doi = "10.18653/v1/2022.aacl-demo.6",
pages = "48--56",
abstract = "We introduce fastcoref, a python package for fast, accurate, and easy-to-use English coreference resolution. The package is pip-installable, and allows two modes: an accurate mode based on the LingMess architecture, providing state-of-the-art coreference accuracy, and a substantially faster model, F-coref, which is the focus of this work. F-coref allows to process 2.8K OntoNotes documents in 25 seconds on a V100 GPU (compared to 6 minutes for the LingMess model, and to 12 minutes of the popular AllenNLP coreference model) with only a modest drop in accuracy. The fast speed is achieved through a combination of distillation of a compact model from the LingMess model, and an efficient batching implementation using a technique we call leftover batching. \url{https://github.com/shon-otmazgin/fastcoref}"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="otmazgin-etal-2022-f">
<titleInfo>
<title>F-coref: Fast, Accurate and Easy to Use Coreference Resolution</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shon</namePart>
<namePart type="family">Otmazgin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arie</namePart>
<namePart type="family">Cattan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wray</namePart>
<namePart type="family">Buntine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Taipei, Taiwan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce fastcoref, a python package for fast, accurate, and easy-to-use English coreference resolution. The package is pip-installable, and allows two modes: an accurate mode based on the LingMess architecture, providing state-of-the-art coreference accuracy, and a substantially faster model, F-coref, which is the focus of this work. F-coref allows to process 2.8K OntoNotes documents in 25 seconds on a V100 GPU (compared to 6 minutes for the LingMess model, and to 12 minutes of the popular AllenNLP coreference model) with only a modest drop in accuracy. The fast speed is achieved through a combination of distillation of a compact model from the LingMess model, and an efficient batching implementation using a technique we call leftover batching. https://github.com/shon-otmazgin/fastcoref</abstract>
<identifier type="citekey">otmazgin-etal-2022-f</identifier>
<identifier type="doi">10.18653/v1/2022.aacl-demo.6</identifier>
<location>
<url>https://aclanthology.org/2022.aacl-demo.6/</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>48</start>
<end>56</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T F-coref: Fast, Accurate and Easy to Use Coreference Resolution
%A Otmazgin, Shon
%A Cattan, Arie
%A Goldberg, Yoav
%Y Buntine, Wray
%Y Liakata, Maria
%S Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing: System Demonstrations
%D 2022
%8 November
%I Association for Computational Linguistics
%C Taipei, Taiwan
%F otmazgin-etal-2022-f
%X We introduce fastcoref, a python package for fast, accurate, and easy-to-use English coreference resolution. The package is pip-installable, and allows two modes: an accurate mode based on the LingMess architecture, providing state-of-the-art coreference accuracy, and a substantially faster model, F-coref, which is the focus of this work. F-coref allows to process 2.8K OntoNotes documents in 25 seconds on a V100 GPU (compared to 6 minutes for the LingMess model, and to 12 minutes of the popular AllenNLP coreference model) with only a modest drop in accuracy. The fast speed is achieved through a combination of distillation of a compact model from the LingMess model, and an efficient batching implementation using a technique we call leftover batching. https://github.com/shon-otmazgin/fastcoref
%R 10.18653/v1/2022.aacl-demo.6
%U https://aclanthology.org/2022.aacl-demo.6/
%U https://doi.org/10.18653/v1/2022.aacl-demo.6
%P 48-56
Markdown (Informal)
[F-coref: Fast, Accurate and Easy to Use Coreference Resolution](https://aclanthology.org/2022.aacl-demo.6/) (Otmazgin et al., AACL-IJCNLP 2022)
ACL
- Shon Otmazgin, Arie Cattan, and Yoav Goldberg. 2022. F-coref: Fast, Accurate and Easy to Use Coreference Resolution. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing: System Demonstrations, pages 48–56, Taipei, Taiwan. Association for Computational Linguistics.