@inproceedings{hasler-etal-2012-sparse,
title = "Sparse lexicalised features and topic adaptation for {SMT}",
author = "Hasler, Eva and
Haddow, Barry and
Koehn, Philipp",
booktitle = "Proceedings of the 9th International Workshop on Spoken Language Translation: Papers",
month = dec # " 6-7",
year = "2012",
address = "Hong Kong, Table of contents",
url = "https://aclanthology.org/2012.iwslt-papers.17/",
pages = "268--275",
abstract = "We present a new approach to domain adaptation for SMT that enriches standard phrase-based models with lexicalised word and phrase pair features to help the model select appropriate translations for the target domain (TED talks). In addition, we show how source-side sentence-level topics can be incorporated to make the features differentiate between more fine-grained topics within the target domain (topic adaptation). We compare tuning our sparse features on a development set versus on the entire in-domain corpus and introduce a new method of porting them to larger mixed-domain models. Experimental results show that our features improve performance over a MIRA baseline and that in some cases we can get additional improvements with topic features. We evaluate our methods on two language pairs, English-French and German-English, showing promising results."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hasler-etal-2012-sparse">
<titleInfo>
<title>Sparse lexicalised features and topic adaptation for SMT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eva</namePart>
<namePart type="family">Hasler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-dec 6-7</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 9th International Workshop on Spoken Language Translation: Papers</title>
</titleInfo>
<originInfo>
<place>
<placeTerm type="text">Hong Kong, Table of contents</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a new approach to domain adaptation for SMT that enriches standard phrase-based models with lexicalised word and phrase pair features to help the model select appropriate translations for the target domain (TED talks). In addition, we show how source-side sentence-level topics can be incorporated to make the features differentiate between more fine-grained topics within the target domain (topic adaptation). We compare tuning our sparse features on a development set versus on the entire in-domain corpus and introduce a new method of porting them to larger mixed-domain models. Experimental results show that our features improve performance over a MIRA baseline and that in some cases we can get additional improvements with topic features. We evaluate our methods on two language pairs, English-French and German-English, showing promising results.</abstract>
<identifier type="citekey">hasler-etal-2012-sparse</identifier>
<location>
<url>https://aclanthology.org/2012.iwslt-papers.17/</url>
</location>
<part>
<date>2012-dec 6-7</date>
<extent unit="page">
<start>268</start>
<end>275</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sparse lexicalised features and topic adaptation for SMT
%A Hasler, Eva
%A Haddow, Barry
%A Koehn, Philipp
%S Proceedings of the 9th International Workshop on Spoken Language Translation: Papers
%D 2012
%8 dec 6 7
%C Hong Kong, Table of contents
%F hasler-etal-2012-sparse
%X We present a new approach to domain adaptation for SMT that enriches standard phrase-based models with lexicalised word and phrase pair features to help the model select appropriate translations for the target domain (TED talks). In addition, we show how source-side sentence-level topics can be incorporated to make the features differentiate between more fine-grained topics within the target domain (topic adaptation). We compare tuning our sparse features on a development set versus on the entire in-domain corpus and introduce a new method of porting them to larger mixed-domain models. Experimental results show that our features improve performance over a MIRA baseline and that in some cases we can get additional improvements with topic features. We evaluate our methods on two language pairs, English-French and German-English, showing promising results.
%U https://aclanthology.org/2012.iwslt-papers.17/
%P 268-275
Markdown (Informal)
[Sparse lexicalised features and topic adaptation for SMT](https://aclanthology.org/2012.iwslt-papers.17/) (Hasler et al., IWSLT 2012)
ACL