@inproceedings{asaadi-etal-2022-giccs,
title = "{G}i{CCS}: A {G}erman in-Context Conversational Similarity Benchmark",
author = "Asaadi, Shima and
Kolagar, Zahra and
Liebel, Alina and
Zarcone, Alessandra",
editor = "Bosselut, Antoine and
Chandu, Khyathi and
Dhole, Kaustubh and
Gangal, Varun and
Gehrmann, Sebastian and
Jernite, Yacine and
Novikova, Jekaterina and
Perez-Beltrachini, Laura",
booktitle = "Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.gem-1.30",
doi = "10.18653/v1/2022.gem-1.30",
pages = "351--362",
abstract = "The Semantic textual similarity (STS) task is commonly used to evaluate the semantic representations that language models (LMs) learn from texts, under the assumption that good-quality representations will yield accurate similarity estimates. When it comes to estimating the similarity of two utterances in a dialogue, however, the conversational context plays a particularly important role. We argue for the need of benchmarks specifically created using conversational data in order to evaluate conversational LMs in the STS task. We introduce GiCCS, a first conversational STS evaluation benchmark for German. We collected the similarity annotations for GiCCS using best-worst scaling and presenting the target items in context, in order to obtain highly-reliable context-dependent similarity scores. We present benchmarking experiments for evaluating LMs on capturing the similarity of utterances. Results suggest that pretraining LMs on conversational data and providing conversational context can be useful for capturing similarity of utterances in dialogues. GiCCS will be publicly available to encourage benchmarking of conversational LMs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="asaadi-etal-2022-giccs">
<titleInfo>
<title>GiCCS: A German in-Context Conversational Similarity Benchmark</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shima</namePart>
<namePart type="family">Asaadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zahra</namePart>
<namePart type="family">Kolagar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alina</namePart>
<namePart type="family">Liebel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandra</namePart>
<namePart type="family">Zarcone</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antoine</namePart>
<namePart type="family">Bosselut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khyathi</namePart>
<namePart type="family">Chandu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaustubh</namePart>
<namePart type="family">Dhole</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varun</namePart>
<namePart type="family">Gangal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Gehrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yacine</namePart>
<namePart type="family">Jernite</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jekaterina</namePart>
<namePart type="family">Novikova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Perez-Beltrachini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The Semantic textual similarity (STS) task is commonly used to evaluate the semantic representations that language models (LMs) learn from texts, under the assumption that good-quality representations will yield accurate similarity estimates. When it comes to estimating the similarity of two utterances in a dialogue, however, the conversational context plays a particularly important role. We argue for the need of benchmarks specifically created using conversational data in order to evaluate conversational LMs in the STS task. We introduce GiCCS, a first conversational STS evaluation benchmark for German. We collected the similarity annotations for GiCCS using best-worst scaling and presenting the target items in context, in order to obtain highly-reliable context-dependent similarity scores. We present benchmarking experiments for evaluating LMs on capturing the similarity of utterances. Results suggest that pretraining LMs on conversational data and providing conversational context can be useful for capturing similarity of utterances in dialogues. GiCCS will be publicly available to encourage benchmarking of conversational LMs.</abstract>
<identifier type="citekey">asaadi-etal-2022-giccs</identifier>
<identifier type="doi">10.18653/v1/2022.gem-1.30</identifier>
<location>
<url>https://aclanthology.org/2022.gem-1.30</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>351</start>
<end>362</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GiCCS: A German in-Context Conversational Similarity Benchmark
%A Asaadi, Shima
%A Kolagar, Zahra
%A Liebel, Alina
%A Zarcone, Alessandra
%Y Bosselut, Antoine
%Y Chandu, Khyathi
%Y Dhole, Kaustubh
%Y Gangal, Varun
%Y Gehrmann, Sebastian
%Y Jernite, Yacine
%Y Novikova, Jekaterina
%Y Perez-Beltrachini, Laura
%S Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F asaadi-etal-2022-giccs
%X The Semantic textual similarity (STS) task is commonly used to evaluate the semantic representations that language models (LMs) learn from texts, under the assumption that good-quality representations will yield accurate similarity estimates. When it comes to estimating the similarity of two utterances in a dialogue, however, the conversational context plays a particularly important role. We argue for the need of benchmarks specifically created using conversational data in order to evaluate conversational LMs in the STS task. We introduce GiCCS, a first conversational STS evaluation benchmark for German. We collected the similarity annotations for GiCCS using best-worst scaling and presenting the target items in context, in order to obtain highly-reliable context-dependent similarity scores. We present benchmarking experiments for evaluating LMs on capturing the similarity of utterances. Results suggest that pretraining LMs on conversational data and providing conversational context can be useful for capturing similarity of utterances in dialogues. GiCCS will be publicly available to encourage benchmarking of conversational LMs.
%R 10.18653/v1/2022.gem-1.30
%U https://aclanthology.org/2022.gem-1.30
%U https://doi.org/10.18653/v1/2022.gem-1.30
%P 351-362
Markdown (Informal)
[GiCCS: A German in-Context Conversational Similarity Benchmark](https://aclanthology.org/2022.gem-1.30) (Asaadi et al., GEM 2022)
ACL
- Shima Asaadi, Zahra Kolagar, Alina Liebel, and Alessandra Zarcone. 2022. GiCCS: A German in-Context Conversational Similarity Benchmark. In Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM), pages 351–362, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.