@inproceedings{hoover-etal-2020-exbert,
title = "ex{BERT}: {A} {V}isual {A}nalysis {T}ool to {E}xplore {L}earned {R}epresentations in {T}ransformer {M}odels",
author = "Hoover, Benjamin and
Strobelt, Hendrik and
Gehrmann, Sebastian",
editor = "Celikyilmaz, Asli and
Wen, Tsung-Hsien",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-demos.22",
doi = "10.18653/v1/2020.acl-demos.22",
pages = "187--196",
abstract = "Large Transformer-based language models can route and reshape complex information via their multi-headed attention mechanism. Although the attention never receives explicit supervision, it can exhibit recognizable patterns following linguistic or positional information. Analyzing the learned representations and attentions is paramount to furthering our understanding of the inner workings of these models. However, analyses have to catch up with the rapid release of new models and the growing diversity of investigation techniques. To support analysis for a wide variety of models, we introduce exBERT, a tool to help humans conduct flexible, interactive investigations and formulate hypotheses for the model-internal reasoning process. exBERT provides insights into the meaning of the contextual representations and attention by matching a human-specified input to similar contexts in large annotated datasets. By aggregating the annotations of the matched contexts, exBERT can quickly replicate findings from literature and extend them to previously not analyzed models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hoover-etal-2020-exbert">
<titleInfo>
<title>exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformer Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Hoover</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hendrik</namePart>
<namePart type="family">Strobelt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Gehrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Asli</namePart>
<namePart type="family">Celikyilmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tsung-Hsien</namePart>
<namePart type="family">Wen</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>Large Transformer-based language models can route and reshape complex information via their multi-headed attention mechanism. Although the attention never receives explicit supervision, it can exhibit recognizable patterns following linguistic or positional information. Analyzing the learned representations and attentions is paramount to furthering our understanding of the inner workings of these models. However, analyses have to catch up with the rapid release of new models and the growing diversity of investigation techniques. To support analysis for a wide variety of models, we introduce exBERT, a tool to help humans conduct flexible, interactive investigations and formulate hypotheses for the model-internal reasoning process. exBERT provides insights into the meaning of the contextual representations and attention by matching a human-specified input to similar contexts in large annotated datasets. By aggregating the annotations of the matched contexts, exBERT can quickly replicate findings from literature and extend them to previously not analyzed models.</abstract>
<identifier type="citekey">hoover-etal-2020-exbert</identifier>
<identifier type="doi">10.18653/v1/2020.acl-demos.22</identifier>
<location>
<url>https://aclanthology.org/2020.acl-demos.22</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>187</start>
<end>196</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformer Models
%A Hoover, Benjamin
%A Strobelt, Hendrik
%A Gehrmann, Sebastian
%Y Celikyilmaz, Asli
%Y Wen, Tsung-Hsien
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F hoover-etal-2020-exbert
%X Large Transformer-based language models can route and reshape complex information via their multi-headed attention mechanism. Although the attention never receives explicit supervision, it can exhibit recognizable patterns following linguistic or positional information. Analyzing the learned representations and attentions is paramount to furthering our understanding of the inner workings of these models. However, analyses have to catch up with the rapid release of new models and the growing diversity of investigation techniques. To support analysis for a wide variety of models, we introduce exBERT, a tool to help humans conduct flexible, interactive investigations and formulate hypotheses for the model-internal reasoning process. exBERT provides insights into the meaning of the contextual representations and attention by matching a human-specified input to similar contexts in large annotated datasets. By aggregating the annotations of the matched contexts, exBERT can quickly replicate findings from literature and extend them to previously not analyzed models.
%R 10.18653/v1/2020.acl-demos.22
%U https://aclanthology.org/2020.acl-demos.22
%U https://doi.org/10.18653/v1/2020.acl-demos.22
%P 187-196
Markdown (Informal)
[exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformer Models](https://aclanthology.org/2020.acl-demos.22) (Hoover et al., ACL 2020)
ACL