@inproceedings{li-etal-2020-branching,
title = "On the Branching Bias of Syntax Extracted from Pre-trained Language Models",
author = "Li, Huayang and
Liu, Lemao and
Huang, Guoping and
Shi, Shuming",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.401",
doi = "10.18653/v1/2020.findings-emnlp.401",
pages = "4473--4478",
abstract = "Many efforts have been devoted to extracting constituency trees from pre-trained language models, often proceeding in two stages: feature definition and parsing. However, this kind of methods may suffer from the branching bias issue, which will inflate the performances on languages with the same branch it biases to. In this work, we propose quantitatively measuring the branching bias by comparing the performance gap on a language and its reversed language, which is agnostic to both language models and extracting methods. Furthermore, we analyze the impacts of three factors on the branching bias, namely feature definitions, parsing algorithms, and language models. Experiments show that several existing works exhibit branching biases, and some implementations of these three factors can introduce the branching bias.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2020-branching">
<titleInfo>
<title>On the Branching Bias of Syntax Extracted from Pre-trained Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Huayang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lemao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guoping</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuming</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Many efforts have been devoted to extracting constituency trees from pre-trained language models, often proceeding in two stages: feature definition and parsing. However, this kind of methods may suffer from the branching bias issue, which will inflate the performances on languages with the same branch it biases to. In this work, we propose quantitatively measuring the branching bias by comparing the performance gap on a language and its reversed language, which is agnostic to both language models and extracting methods. Furthermore, we analyze the impacts of three factors on the branching bias, namely feature definitions, parsing algorithms, and language models. Experiments show that several existing works exhibit branching biases, and some implementations of these three factors can introduce the branching bias.</abstract>
<identifier type="citekey">li-etal-2020-branching</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.401</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.401</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>4473</start>
<end>4478</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On the Branching Bias of Syntax Extracted from Pre-trained Language Models
%A Li, Huayang
%A Liu, Lemao
%A Huang, Guoping
%A Shi, Shuming
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F li-etal-2020-branching
%X Many efforts have been devoted to extracting constituency trees from pre-trained language models, often proceeding in two stages: feature definition and parsing. However, this kind of methods may suffer from the branching bias issue, which will inflate the performances on languages with the same branch it biases to. In this work, we propose quantitatively measuring the branching bias by comparing the performance gap on a language and its reversed language, which is agnostic to both language models and extracting methods. Furthermore, we analyze the impacts of three factors on the branching bias, namely feature definitions, parsing algorithms, and language models. Experiments show that several existing works exhibit branching biases, and some implementations of these three factors can introduce the branching bias.
%R 10.18653/v1/2020.findings-emnlp.401
%U https://aclanthology.org/2020.findings-emnlp.401
%U https://doi.org/10.18653/v1/2020.findings-emnlp.401
%P 4473-4478
Markdown (Informal)
[On the Branching Bias of Syntax Extracted from Pre-trained Language Models](https://aclanthology.org/2020.findings-emnlp.401) (Li et al., Findings 2020)
ACL