@inproceedings{ek-ilinykh-2023-vector,
title = "Vector Norms as an Approximation of Syntactic Complexity",
author = "Ek, Adam and
Ilinykh, Nikolai",
editor = "Ilinykh, Nikolai and
Morger, Felix and
Dann{\'e}lls, Dana and
Dobnik, Simon and
Megyesi, Be{\'a}ta and
Nivre, Joakim",
booktitle = "Proceedings of the Second Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2023)",
month = may,
year = "2023",
address = "T{\'o}rshavn, the Faroe Islands",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.resourceful-1.15",
pages = "121--131",
abstract = "Internal representations in transformer models can encode useful linguistic knowledge about syntax. Such knowledge could help optimise the data annotation process. However, identifying and extracting such representations from big language models is challenging. In this paper we evaluate two multilingual transformers for the presence of knowledge about the syntactic complexity of sentences and examine different vector norms. We provide a fine-grained evaluation of different norms in different layers and for different languages. Our results suggest that no single part in the models would be the primary source for the knowledge of syntactic complexity. But some norms show a higher degree of sensitivity to syntactic complexity, depending on the language and model used.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ek-ilinykh-2023-vector">
<titleInfo>
<title>Vector Norms as an Approximation of Syntactic Complexity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Ek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Ilinykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Ilinykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="family">Morger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dana</namePart>
<namePart type="family">Dannélls</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Dobnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Beáta</namePart>
<namePart type="family">Megyesi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joakim</namePart>
<namePart type="family">Nivre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Tórshavn, the Faroe Islands</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Internal representations in transformer models can encode useful linguistic knowledge about syntax. Such knowledge could help optimise the data annotation process. However, identifying and extracting such representations from big language models is challenging. In this paper we evaluate two multilingual transformers for the presence of knowledge about the syntactic complexity of sentences and examine different vector norms. We provide a fine-grained evaluation of different norms in different layers and for different languages. Our results suggest that no single part in the models would be the primary source for the knowledge of syntactic complexity. But some norms show a higher degree of sensitivity to syntactic complexity, depending on the language and model used.</abstract>
<identifier type="citekey">ek-ilinykh-2023-vector</identifier>
<location>
<url>https://aclanthology.org/2023.resourceful-1.15</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>121</start>
<end>131</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Vector Norms as an Approximation of Syntactic Complexity
%A Ek, Adam
%A Ilinykh, Nikolai
%Y Ilinykh, Nikolai
%Y Morger, Felix
%Y Dannélls, Dana
%Y Dobnik, Simon
%Y Megyesi, Beáta
%Y Nivre, Joakim
%S Proceedings of the Second Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2023)
%D 2023
%8 May
%I Association for Computational Linguistics
%C Tórshavn, the Faroe Islands
%F ek-ilinykh-2023-vector
%X Internal representations in transformer models can encode useful linguistic knowledge about syntax. Such knowledge could help optimise the data annotation process. However, identifying and extracting such representations from big language models is challenging. In this paper we evaluate two multilingual transformers for the presence of knowledge about the syntactic complexity of sentences and examine different vector norms. We provide a fine-grained evaluation of different norms in different layers and for different languages. Our results suggest that no single part in the models would be the primary source for the knowledge of syntactic complexity. But some norms show a higher degree of sensitivity to syntactic complexity, depending on the language and model used.
%U https://aclanthology.org/2023.resourceful-1.15
%P 121-131
Markdown (Informal)
[Vector Norms as an Approximation of Syntactic Complexity](https://aclanthology.org/2023.resourceful-1.15) (Ek & Ilinykh, RESOURCEFUL 2023)
ACL
- Adam Ek and Nikolai Ilinykh. 2023. Vector Norms as an Approximation of Syntactic Complexity. In Proceedings of the Second Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2023), pages 121–131, Tórshavn, the Faroe Islands. Association for Computational Linguistics.