@inproceedings{kerscher-eger-2020-vec2sent,
title = "{V}ec2{S}ent: Probing Sentence Embeddings with Natural Language Generation",
author = "Kerscher, Martin and
Eger, Steffen",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.152",
doi = "10.18653/v1/2020.coling-main.152",
pages = "1729--1736",
abstract = "We introspect black-box sentence embeddings by conditionally generating from them with the objective to retrieve the underlying discrete sentence. We perceive of this as a new unsupervised probing task and show that it correlates well with downstream task performance. We also illustrate how the language generated from different encoders differs. We apply our approach to generate sentence analogies from sentence embeddings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kerscher-eger-2020-vec2sent">
<titleInfo>
<title>Vec2Sent: Probing Sentence Embeddings with Natural Language Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Kerscher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steffen</namePart>
<namePart type="family">Eger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introspect black-box sentence embeddings by conditionally generating from them with the objective to retrieve the underlying discrete sentence. We perceive of this as a new unsupervised probing task and show that it correlates well with downstream task performance. We also illustrate how the language generated from different encoders differs. We apply our approach to generate sentence analogies from sentence embeddings.</abstract>
<identifier type="citekey">kerscher-eger-2020-vec2sent</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.152</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.152</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>1729</start>
<end>1736</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Vec2Sent: Probing Sentence Embeddings with Natural Language Generation
%A Kerscher, Martin
%A Eger, Steffen
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F kerscher-eger-2020-vec2sent
%X We introspect black-box sentence embeddings by conditionally generating from them with the objective to retrieve the underlying discrete sentence. We perceive of this as a new unsupervised probing task and show that it correlates well with downstream task performance. We also illustrate how the language generated from different encoders differs. We apply our approach to generate sentence analogies from sentence embeddings.
%R 10.18653/v1/2020.coling-main.152
%U https://aclanthology.org/2020.coling-main.152
%U https://doi.org/10.18653/v1/2020.coling-main.152
%P 1729-1736
Markdown (Informal)
[Vec2Sent: Probing Sentence Embeddings with Natural Language Generation](https://aclanthology.org/2020.coling-main.152) (Kerscher & Eger, COLING 2020)
ACL