@inproceedings{dakota-2021-genres,
title = "Genres, Parsers, and {BERT}: The Interaction Between Parsers and {BERT} Models in Cross-Genre Constituency Parsing in {E}nglish and {S}wedish",
author = "Dakota, Daniel",
editor = "Ben-David, Eyal and
Cohen, Shay and
McDonald, Ryan and
Plank, Barbara and
Reichart, Roi and
Rotman, Guy and
Ziser, Yftah",
booktitle = "Proceedings of the Second Workshop on Domain Adaptation for NLP",
month = apr,
year = "2021",
address = "Kyiv, Ukraine",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.adaptnlp-1.7",
pages = "59--71",
abstract = "Genre and domain are often used interchangeably, but are two different properties of a text. Successful parser adaptation requires both cross-domain and cross-genre sensitivity (Rehbein and Bildhauer, 2017). While the impact domain differences have on parser performance degradation is more easily measurable in respect to lexical differences, impact of genre differences can be more nuanced. With the predominance of pre-trained language models (LMs; e.g. BERT (Devlin et al., 2019)), there are now additional complexities in developing cross-genre sensitive models due to the infusion of linguistic characteristics derived from, usually, a third genre. We perform a systematic set of experiments using two neural constituency parsers to examine how different parsers behave in combination with different BERT models with varying source and target genres in English and Swedish. We find that there is extensive difficulty in predicting the best source due to the complex interactions between genres, parsers, and LMs. Additionally, the influence of the data used to derive the underlying BERT model heavily influences how best to create more robust and effective cross-genre parsing models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dakota-2021-genres">
<titleInfo>
<title>Genres, Parsers, and BERT: The Interaction Between Parsers and BERT Models in Cross-Genre Constituency Parsing in English and Swedish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Dakota</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Domain Adaptation for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eyal</namePart>
<namePart type="family">Ben-David</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shay</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">McDonald</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Plank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roi</namePart>
<namePart type="family">Reichart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Rotman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yftah</namePart>
<namePart type="family">Ziser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Kyiv, Ukraine</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Genre and domain are often used interchangeably, but are two different properties of a text. Successful parser adaptation requires both cross-domain and cross-genre sensitivity (Rehbein and Bildhauer, 2017). While the impact domain differences have on parser performance degradation is more easily measurable in respect to lexical differences, impact of genre differences can be more nuanced. With the predominance of pre-trained language models (LMs; e.g. BERT (Devlin et al., 2019)), there are now additional complexities in developing cross-genre sensitive models due to the infusion of linguistic characteristics derived from, usually, a third genre. We perform a systematic set of experiments using two neural constituency parsers to examine how different parsers behave in combination with different BERT models with varying source and target genres in English and Swedish. We find that there is extensive difficulty in predicting the best source due to the complex interactions between genres, parsers, and LMs. Additionally, the influence of the data used to derive the underlying BERT model heavily influences how best to create more robust and effective cross-genre parsing models.</abstract>
<identifier type="citekey">dakota-2021-genres</identifier>
<location>
<url>https://aclanthology.org/2021.adaptnlp-1.7</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>59</start>
<end>71</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Genres, Parsers, and BERT: The Interaction Between Parsers and BERT Models in Cross-Genre Constituency Parsing in English and Swedish
%A Dakota, Daniel
%Y Ben-David, Eyal
%Y Cohen, Shay
%Y McDonald, Ryan
%Y Plank, Barbara
%Y Reichart, Roi
%Y Rotman, Guy
%Y Ziser, Yftah
%S Proceedings of the Second Workshop on Domain Adaptation for NLP
%D 2021
%8 April
%I Association for Computational Linguistics
%C Kyiv, Ukraine
%F dakota-2021-genres
%X Genre and domain are often used interchangeably, but are two different properties of a text. Successful parser adaptation requires both cross-domain and cross-genre sensitivity (Rehbein and Bildhauer, 2017). While the impact domain differences have on parser performance degradation is more easily measurable in respect to lexical differences, impact of genre differences can be more nuanced. With the predominance of pre-trained language models (LMs; e.g. BERT (Devlin et al., 2019)), there are now additional complexities in developing cross-genre sensitive models due to the infusion of linguistic characteristics derived from, usually, a third genre. We perform a systematic set of experiments using two neural constituency parsers to examine how different parsers behave in combination with different BERT models with varying source and target genres in English and Swedish. We find that there is extensive difficulty in predicting the best source due to the complex interactions between genres, parsers, and LMs. Additionally, the influence of the data used to derive the underlying BERT model heavily influences how best to create more robust and effective cross-genre parsing models.
%U https://aclanthology.org/2021.adaptnlp-1.7
%P 59-71
Markdown (Informal)
[Genres, Parsers, and BERT: The Interaction Between Parsers and BERT Models in Cross-Genre Constituency Parsing in English and Swedish](https://aclanthology.org/2021.adaptnlp-1.7) (Dakota, AdaptNLP 2021)
ACL