@inproceedings{zhao-etal-2019-weakly,
title = "Weakly Supervised Attentional Model for Low Resource Ad-hoc Cross-lingual Information Retrieval",
author = "Zhao, Lingjun and
Zbib, Rabih and
Jiang, Zhuolin and
Karakos, Damianos and
Huang, Zhongqiang",
editor = "Cherry, Colin and
Durrett, Greg and
Foster, George and
Haffari, Reza and
Khadivi, Shahram and
Peng, Nanyun and
Ren, Xiang and
Swayamdipta, Swabha",
booktitle = "Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-6129",
doi = "10.18653/v1/D19-6129",
pages = "259--264",
abstract = "We propose a weakly supervised neural model for Ad-hoc Cross-lingual Information Retrieval (CLIR) from low-resource languages. Low resource languages often lack relevance annotations for CLIR, and when available the training data usually has limited coverage for possible queries. In this paper, we design a model which does not require relevance annotations, instead it is trained on samples extracted from translation corpora as weak supervision. This model relies on an attention mechanism to learn spans in the foreign sentence that are relevant to the query. We report experiments on two low resource languages: Swahili and Tagalog, trained on less that 100k parallel sentences each. The proposed model achieves 19 MAP points improvement compared to using CNNs for feature extraction, 12 points improvement from machine translation-based CLIR, and up to 6 points improvement compared to probabilistic CLIR models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2019-weakly">
<titleInfo>
<title>Weakly Supervised Attentional Model for Low Resource Ad-hoc Cross-lingual Information Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lingjun</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rabih</namePart>
<namePart type="family">Zbib</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhuolin</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damianos</namePart>
<namePart type="family">Karakos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongqiang</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Colin</namePart>
<namePart type="family">Cherry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Greg</namePart>
<namePart type="family">Durrett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Foster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shahram</namePart>
<namePart type="family">Khadivi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nanyun</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swabha</namePart>
<namePart type="family">Swayamdipta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose a weakly supervised neural model for Ad-hoc Cross-lingual Information Retrieval (CLIR) from low-resource languages. Low resource languages often lack relevance annotations for CLIR, and when available the training data usually has limited coverage for possible queries. In this paper, we design a model which does not require relevance annotations, instead it is trained on samples extracted from translation corpora as weak supervision. This model relies on an attention mechanism to learn spans in the foreign sentence that are relevant to the query. We report experiments on two low resource languages: Swahili and Tagalog, trained on less that 100k parallel sentences each. The proposed model achieves 19 MAP points improvement compared to using CNNs for feature extraction, 12 points improvement from machine translation-based CLIR, and up to 6 points improvement compared to probabilistic CLIR models.</abstract>
<identifier type="citekey">zhao-etal-2019-weakly</identifier>
<identifier type="doi">10.18653/v1/D19-6129</identifier>
<location>
<url>https://aclanthology.org/D19-6129</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>259</start>
<end>264</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Weakly Supervised Attentional Model for Low Resource Ad-hoc Cross-lingual Information Retrieval
%A Zhao, Lingjun
%A Zbib, Rabih
%A Jiang, Zhuolin
%A Karakos, Damianos
%A Huang, Zhongqiang
%Y Cherry, Colin
%Y Durrett, Greg
%Y Foster, George
%Y Haffari, Reza
%Y Khadivi, Shahram
%Y Peng, Nanyun
%Y Ren, Xiang
%Y Swayamdipta, Swabha
%S Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F zhao-etal-2019-weakly
%X We propose a weakly supervised neural model for Ad-hoc Cross-lingual Information Retrieval (CLIR) from low-resource languages. Low resource languages often lack relevance annotations for CLIR, and when available the training data usually has limited coverage for possible queries. In this paper, we design a model which does not require relevance annotations, instead it is trained on samples extracted from translation corpora as weak supervision. This model relies on an attention mechanism to learn spans in the foreign sentence that are relevant to the query. We report experiments on two low resource languages: Swahili and Tagalog, trained on less that 100k parallel sentences each. The proposed model achieves 19 MAP points improvement compared to using CNNs for feature extraction, 12 points improvement from machine translation-based CLIR, and up to 6 points improvement compared to probabilistic CLIR models.
%R 10.18653/v1/D19-6129
%U https://aclanthology.org/D19-6129
%U https://doi.org/10.18653/v1/D19-6129
%P 259-264
Markdown (Informal)
[Weakly Supervised Attentional Model for Low Resource Ad-hoc Cross-lingual Information Retrieval](https://aclanthology.org/D19-6129) (Zhao et al., 2019)
ACL