@inproceedings{nishimwe-etal-2024-making,
title = "Making Sentence Embeddings Robust to User-Generated Content",
author = "Nishimwe, Lydia and
Sagot, Beno{\^\i}t and
Bawden, Rachel",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.958",
pages = "10984--10998",
abstract = "NLP models have been known to perform poorly on user-generated content (UGC), mainly because it presents a lot of lexical variations and deviates from the standard texts on which most of these models were trained. In this work, we focus on the robustness of LASER, a sentence embedding model, to UGC data. We evaluate this robustness by LASER{'}s ability to represent non-standard sentences and their standard counterparts close to each other in the embedding space. Inspired by previous works extending LASER to other languages and modalities, we propose RoLASER, a robust English encoder trained using a teacher-student approach to reduce the distances between the representations of standard and UGC sentences. We show that with training only on standard and synthetic UGC-like data, RoLASER significantly improves LASER{'}s robustness to both natural and artificial UGC data by achieving up to 2x and 11x better scores. We also perform a fine-grained analysis on artificial UGC data and find that our model greatly outperforms LASER on its most challenging UGC phenomena such as keyboard typos and social media abbreviations. Evaluation on downstream tasks shows that RoLASER performs comparably to or better than LASER on standard data, while consistently outperforming it on UGC data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nishimwe-etal-2024-making">
<titleInfo>
<title>Making Sentence Embeddings Robust to User-Generated Content</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lydia</namePart>
<namePart type="family">Nishimwe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benoît</namePart>
<namePart type="family">Sagot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachel</namePart>
<namePart type="family">Bawden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>NLP models have been known to perform poorly on user-generated content (UGC), mainly because it presents a lot of lexical variations and deviates from the standard texts on which most of these models were trained. In this work, we focus on the robustness of LASER, a sentence embedding model, to UGC data. We evaluate this robustness by LASER’s ability to represent non-standard sentences and their standard counterparts close to each other in the embedding space. Inspired by previous works extending LASER to other languages and modalities, we propose RoLASER, a robust English encoder trained using a teacher-student approach to reduce the distances between the representations of standard and UGC sentences. We show that with training only on standard and synthetic UGC-like data, RoLASER significantly improves LASER’s robustness to both natural and artificial UGC data by achieving up to 2x and 11x better scores. We also perform a fine-grained analysis on artificial UGC data and find that our model greatly outperforms LASER on its most challenging UGC phenomena such as keyboard typos and social media abbreviations. Evaluation on downstream tasks shows that RoLASER performs comparably to or better than LASER on standard data, while consistently outperforming it on UGC data.</abstract>
<identifier type="citekey">nishimwe-etal-2024-making</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.958</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>10984</start>
<end>10998</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Making Sentence Embeddings Robust to User-Generated Content
%A Nishimwe, Lydia
%A Sagot, Benoît
%A Bawden, Rachel
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F nishimwe-etal-2024-making
%X NLP models have been known to perform poorly on user-generated content (UGC), mainly because it presents a lot of lexical variations and deviates from the standard texts on which most of these models were trained. In this work, we focus on the robustness of LASER, a sentence embedding model, to UGC data. We evaluate this robustness by LASER’s ability to represent non-standard sentences and their standard counterparts close to each other in the embedding space. Inspired by previous works extending LASER to other languages and modalities, we propose RoLASER, a robust English encoder trained using a teacher-student approach to reduce the distances between the representations of standard and UGC sentences. We show that with training only on standard and synthetic UGC-like data, RoLASER significantly improves LASER’s robustness to both natural and artificial UGC data by achieving up to 2x and 11x better scores. We also perform a fine-grained analysis on artificial UGC data and find that our model greatly outperforms LASER on its most challenging UGC phenomena such as keyboard typos and social media abbreviations. Evaluation on downstream tasks shows that RoLASER performs comparably to or better than LASER on standard data, while consistently outperforming it on UGC data.
%U https://aclanthology.org/2024.lrec-main.958
%P 10984-10998
Markdown (Informal)
[Making Sentence Embeddings Robust to User-Generated Content](https://aclanthology.org/2024.lrec-main.958) (Nishimwe et al., LREC-COLING 2024)
ACL
- Lydia Nishimwe, Benoît Sagot, and Rachel Bawden. 2024. Making Sentence Embeddings Robust to User-Generated Content. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 10984–10998, Torino, Italia. ELRA and ICCL.