@inproceedings{amini-cotterell-2022-parsing,
title = "On Parsing as Tagging",
author = "Amini, Afra and
Cotterell, Ryan",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.607",
doi = "10.18653/v1/2022.emnlp-main.607",
pages = "8884--8900",
abstract = "There are many proposals to reduce constituency parsing to tagging. To figure out what these approaches have in common, we offer a unifying pipeline, which consists of three steps: linearization, learning, and decoding. We prove that classic shift{--}reduce parsing can be reduced to tetratagging{---}the state-of-the-art constituency tagger{---}under two assumptions: right-corner transformation in the linearization step and factored scoring in the learning step. We ask what is the most critical factor that makes parsing-as-tagging methods accurate while being efficient. To answer this question, we empirically evaluate a taxonomy of tagging pipelines with different choices of linearizers, learners, and decoders. Based on the results in English as well as a set of 8 typologically diverse languages, we conclude that the linearization of the derivation tree and its alignment with the input sequence is the most critical factor in achieving accurate parsers as taggers.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="amini-cotterell-2022-parsing">
<titleInfo>
<title>On Parsing as Tagging</title>
</titleInfo>
<name type="personal">
<namePart type="given">Afra</namePart>
<namePart type="family">Amini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>There are many proposals to reduce constituency parsing to tagging. To figure out what these approaches have in common, we offer a unifying pipeline, which consists of three steps: linearization, learning, and decoding. We prove that classic shift–reduce parsing can be reduced to tetratagging—the state-of-the-art constituency tagger—under two assumptions: right-corner transformation in the linearization step and factored scoring in the learning step. We ask what is the most critical factor that makes parsing-as-tagging methods accurate while being efficient. To answer this question, we empirically evaluate a taxonomy of tagging pipelines with different choices of linearizers, learners, and decoders. Based on the results in English as well as a set of 8 typologically diverse languages, we conclude that the linearization of the derivation tree and its alignment with the input sequence is the most critical factor in achieving accurate parsers as taggers.</abstract>
<identifier type="citekey">amini-cotterell-2022-parsing</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.607</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.607</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>8884</start>
<end>8900</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On Parsing as Tagging
%A Amini, Afra
%A Cotterell, Ryan
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F amini-cotterell-2022-parsing
%X There are many proposals to reduce constituency parsing to tagging. To figure out what these approaches have in common, we offer a unifying pipeline, which consists of three steps: linearization, learning, and decoding. We prove that classic shift–reduce parsing can be reduced to tetratagging—the state-of-the-art constituency tagger—under two assumptions: right-corner transformation in the linearization step and factored scoring in the learning step. We ask what is the most critical factor that makes parsing-as-tagging methods accurate while being efficient. To answer this question, we empirically evaluate a taxonomy of tagging pipelines with different choices of linearizers, learners, and decoders. Based on the results in English as well as a set of 8 typologically diverse languages, we conclude that the linearization of the derivation tree and its alignment with the input sequence is the most critical factor in achieving accurate parsers as taggers.
%R 10.18653/v1/2022.emnlp-main.607
%U https://aclanthology.org/2022.emnlp-main.607
%U https://doi.org/10.18653/v1/2022.emnlp-main.607
%P 8884-8900
Markdown (Informal)
[On Parsing as Tagging](https://aclanthology.org/2022.emnlp-main.607) (Amini & Cotterell, EMNLP 2022)
ACL
- Afra Amini and Ryan Cotterell. 2022. On Parsing as Tagging. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 8884–8900, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.