@inproceedings{klimaszewski-wroblewska-2021-combo-state,
title = "{COMBO}: State-of-the-Art Morphosyntactic Analysis",
author = "Klimaszewski, Mateusz and
Wr{\'o}blewska, Alina",
editor = "Adel, Heike and
Shi, Shuming",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-demo.7",
doi = "10.18653/v1/2021.emnlp-demo.7",
pages = "50--62",
abstract = "We introduce COMBO {--} a fully neural NLP system for accurate part-of-speech tagging, morphological analysis, lemmatisation, and (enhanced) dependency parsing. It predicts categorical morphosyntactic features whilst also exposes their vector representations, extracted from hidden layers. COMBO is an easy to install Python package with automatically downloadable pre-trained models for over 40 languages. It maintains a balance between efficiency and quality. As it is an end-to-end system and its modules are jointly trained, its training is competitively fast. As its models are optimised for accuracy, they achieve often better prediction quality than SOTA. The COMBO library is available at: \url{https://gitlab.clarin-pl.eu/syntactic-tools/combo}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="klimaszewski-wroblewska-2021-combo-state">
<titleInfo>
<title>COMBO: State-of-the-Art Morphosyntactic Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mateusz</namePart>
<namePart type="family">Klimaszewski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alina</namePart>
<namePart type="family">Wróblewska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Heike</namePart>
<namePart type="family">Adel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuming</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce COMBO – a fully neural NLP system for accurate part-of-speech tagging, morphological analysis, lemmatisation, and (enhanced) dependency parsing. It predicts categorical morphosyntactic features whilst also exposes their vector representations, extracted from hidden layers. COMBO is an easy to install Python package with automatically downloadable pre-trained models for over 40 languages. It maintains a balance between efficiency and quality. As it is an end-to-end system and its modules are jointly trained, its training is competitively fast. As its models are optimised for accuracy, they achieve often better prediction quality than SOTA. The COMBO library is available at: https://gitlab.clarin-pl.eu/syntactic-tools/combo.</abstract>
<identifier type="citekey">klimaszewski-wroblewska-2021-combo-state</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-demo.7</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-demo.7</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>50</start>
<end>62</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T COMBO: State-of-the-Art Morphosyntactic Analysis
%A Klimaszewski, Mateusz
%A Wróblewska, Alina
%Y Adel, Heike
%Y Shi, Shuming
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F klimaszewski-wroblewska-2021-combo-state
%X We introduce COMBO – a fully neural NLP system for accurate part-of-speech tagging, morphological analysis, lemmatisation, and (enhanced) dependency parsing. It predicts categorical morphosyntactic features whilst also exposes their vector representations, extracted from hidden layers. COMBO is an easy to install Python package with automatically downloadable pre-trained models for over 40 languages. It maintains a balance between efficiency and quality. As it is an end-to-end system and its modules are jointly trained, its training is competitively fast. As its models are optimised for accuracy, they achieve often better prediction quality than SOTA. The COMBO library is available at: https://gitlab.clarin-pl.eu/syntactic-tools/combo.
%R 10.18653/v1/2021.emnlp-demo.7
%U https://aclanthology.org/2021.emnlp-demo.7
%U https://doi.org/10.18653/v1/2021.emnlp-demo.7
%P 50-62
Markdown (Informal)
[COMBO: State-of-the-Art Morphosyntactic Analysis](https://aclanthology.org/2021.emnlp-demo.7) (Klimaszewski & Wróblewska, EMNLP 2021)
ACL
- Mateusz Klimaszewski and Alina Wróblewska. 2021. COMBO: State-of-the-Art Morphosyntactic Analysis. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 50–62, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.