@inproceedings{samih-kallmeyer-2023-unsupervised,
title = "Unsupervised Semantic Frame Induction Revisited",
author = "Samih, Younes and
Kallmeyer, Laura",
editor = "Amblard, Maxime and
Breitholtz, Ellen",
booktitle = "Proceedings of the 15th International Conference on Computational Semantics",
month = jun,
year = "2023",
address = "Nancy, France",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.iwcs-1.10/",
pages = "89--93",
abstract = "This paper addresses the task of semantic frame induction based on pre-trained language models (LMs). The current state of the art is to directly use contextualized embeddings from models such as BERT and to cluster them in a two step clustering process (first lemma-internal, then over all verb tokens in the data set). We propose not to use the LM`s embeddings as such but rather to refine them via some transformer-based denoising autoencoder. The resulting embeddings allow to obtain competitive results while clustering them in a single pass. This shows clearly that the autoendocer allows to already concentrate on the information that is relevant for distinguishing event types."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="samih-kallmeyer-2023-unsupervised">
<titleInfo>
<title>Unsupervised Semantic Frame Induction Revisited</title>
</titleInfo>
<name type="personal">
<namePart type="given">Younes</namePart>
<namePart type="family">Samih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Kallmeyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Conference on Computational Semantics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maxime</namePart>
<namePart type="family">Amblard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ellen</namePart>
<namePart type="family">Breitholtz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Nancy, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper addresses the task of semantic frame induction based on pre-trained language models (LMs). The current state of the art is to directly use contextualized embeddings from models such as BERT and to cluster them in a two step clustering process (first lemma-internal, then over all verb tokens in the data set). We propose not to use the LM‘s embeddings as such but rather to refine them via some transformer-based denoising autoencoder. The resulting embeddings allow to obtain competitive results while clustering them in a single pass. This shows clearly that the autoendocer allows to already concentrate on the information that is relevant for distinguishing event types.</abstract>
<identifier type="citekey">samih-kallmeyer-2023-unsupervised</identifier>
<location>
<url>https://aclanthology.org/2023.iwcs-1.10/</url>
</location>
<part>
<date>2023-06</date>
<extent unit="page">
<start>89</start>
<end>93</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unsupervised Semantic Frame Induction Revisited
%A Samih, Younes
%A Kallmeyer, Laura
%Y Amblard, Maxime
%Y Breitholtz, Ellen
%S Proceedings of the 15th International Conference on Computational Semantics
%D 2023
%8 June
%I Association for Computational Linguistics
%C Nancy, France
%F samih-kallmeyer-2023-unsupervised
%X This paper addresses the task of semantic frame induction based on pre-trained language models (LMs). The current state of the art is to directly use contextualized embeddings from models such as BERT and to cluster them in a two step clustering process (first lemma-internal, then over all verb tokens in the data set). We propose not to use the LM‘s embeddings as such but rather to refine them via some transformer-based denoising autoencoder. The resulting embeddings allow to obtain competitive results while clustering them in a single pass. This shows clearly that the autoendocer allows to already concentrate on the information that is relevant for distinguishing event types.
%U https://aclanthology.org/2023.iwcs-1.10/
%P 89-93
Markdown (Informal)
[Unsupervised Semantic Frame Induction Revisited](https://aclanthology.org/2023.iwcs-1.10/) (Samih & Kallmeyer, IWCS 2023)
ACL
- Younes Samih and Laura Kallmeyer. 2023. Unsupervised Semantic Frame Induction Revisited. In Proceedings of the 15th International Conference on Computational Semantics, pages 89–93, Nancy, France. Association for Computational Linguistics.