@inproceedings{arora-etal-2020-investigative,
title = "An Investigative Study of Multi-Modal Cross-Lingual Retrieval",
author = "Arora, Piyush and
Shterionov, Dimitar and
Moriya, Yasufumi and
Kaushik, Abhishek and
Dzendzik, Daria and
Jones, Gareth",
editor = "McKeown, Kathy and
Oard, Douglas W. and
{Elizabeth} and
Schwartz, Richard",
booktitle = "Proceedings of the workshop on Cross-Language Search and Summarization of Text and Speech (CLSSTS2020)",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.clssts-1.10",
pages = "58--67",
abstract = "We describe work from our investigations of the novel area of multi-modal cross-lingual retrieval (MMCLIR) under low-resource conditions. We study the challenges associated with MMCLIR relating to: (i) data conversion between different modalities, for example speech and text, (ii) overcoming the language barrier between source and target languages; (iii) effectively scoring and ranking documents to suit the retrieval task; and (iv) handling low resource constraints that prohibit development of heavily tuned machine translation (MT) and automatic speech recognition (ASR) systems. We focus on the use case of retrieving text and speech documents in Swahili, using English queries which was the main focus of the OpenCLIR shared task. Our work is developed within the scope of this task. In this paper we devote special attention to the automatic translation (AT) component which is crucial for the overall quality of the MMCLIR system. We exploit a combination of dictionaries and phrase-based statistical machine translation (MT) systems to tackle effectively the subtask of query translation. We address each MMCLIR challenge individually, and develop separate components for automatic translation (AT), speech processing (SP) and information retrieval (IR). We find that results with respect to cross-lingual text retrieval are quite good relative to the task of cross-lingual speech retrieval. Overall we find that the task of MMCLIR and specifically cross-lingual speech retrieval is quite complex. Further we pinpoint open issues related to handling cross-lingual audio and text retrieval for low resource languages that need to be addressed in future research.",
language = "English",
ISBN = "979-10-95546-55-9",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="arora-etal-2020-investigative">
<titleInfo>
<title>An Investigative Study of Multi-Modal Cross-Lingual Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Piyush</namePart>
<namePart type="family">Arora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dimitar</namePart>
<namePart type="family">Shterionov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yasufumi</namePart>
<namePart type="family">Moriya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhishek</namePart>
<namePart type="family">Kaushik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daria</namePart>
<namePart type="family">Dzendzik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gareth</namePart>
<namePart type="family">Jones</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the workshop on Cross-Language Search and Summarization of Text and Speech (CLSSTS2020)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kathy</namePart>
<namePart type="family">McKeown</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Douglas</namePart>
<namePart type="given">W</namePart>
<namePart type="family">Oard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name>
<namePart>Elizabeth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="family">Schwartz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-55-9</identifier>
</relatedItem>
<abstract>We describe work from our investigations of the novel area of multi-modal cross-lingual retrieval (MMCLIR) under low-resource conditions. We study the challenges associated with MMCLIR relating to: (i) data conversion between different modalities, for example speech and text, (ii) overcoming the language barrier between source and target languages; (iii) effectively scoring and ranking documents to suit the retrieval task; and (iv) handling low resource constraints that prohibit development of heavily tuned machine translation (MT) and automatic speech recognition (ASR) systems. We focus on the use case of retrieving text and speech documents in Swahili, using English queries which was the main focus of the OpenCLIR shared task. Our work is developed within the scope of this task. In this paper we devote special attention to the automatic translation (AT) component which is crucial for the overall quality of the MMCLIR system. We exploit a combination of dictionaries and phrase-based statistical machine translation (MT) systems to tackle effectively the subtask of query translation. We address each MMCLIR challenge individually, and develop separate components for automatic translation (AT), speech processing (SP) and information retrieval (IR). We find that results with respect to cross-lingual text retrieval are quite good relative to the task of cross-lingual speech retrieval. Overall we find that the task of MMCLIR and specifically cross-lingual speech retrieval is quite complex. Further we pinpoint open issues related to handling cross-lingual audio and text retrieval for low resource languages that need to be addressed in future research.</abstract>
<identifier type="citekey">arora-etal-2020-investigative</identifier>
<location>
<url>https://aclanthology.org/2020.clssts-1.10</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>58</start>
<end>67</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Investigative Study of Multi-Modal Cross-Lingual Retrieval
%A Arora, Piyush
%A Shterionov, Dimitar
%A Moriya, Yasufumi
%A Kaushik, Abhishek
%A Dzendzik, Daria
%A Jones, Gareth
%Y McKeown, Kathy
%Y Oard, Douglas W.
%Y Schwartz, Richard
%E Elizabeth
%S Proceedings of the workshop on Cross-Language Search and Summarization of Text and Speech (CLSSTS2020)
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-55-9
%G English
%F arora-etal-2020-investigative
%X We describe work from our investigations of the novel area of multi-modal cross-lingual retrieval (MMCLIR) under low-resource conditions. We study the challenges associated with MMCLIR relating to: (i) data conversion between different modalities, for example speech and text, (ii) overcoming the language barrier between source and target languages; (iii) effectively scoring and ranking documents to suit the retrieval task; and (iv) handling low resource constraints that prohibit development of heavily tuned machine translation (MT) and automatic speech recognition (ASR) systems. We focus on the use case of retrieving text and speech documents in Swahili, using English queries which was the main focus of the OpenCLIR shared task. Our work is developed within the scope of this task. In this paper we devote special attention to the automatic translation (AT) component which is crucial for the overall quality of the MMCLIR system. We exploit a combination of dictionaries and phrase-based statistical machine translation (MT) systems to tackle effectively the subtask of query translation. We address each MMCLIR challenge individually, and develop separate components for automatic translation (AT), speech processing (SP) and information retrieval (IR). We find that results with respect to cross-lingual text retrieval are quite good relative to the task of cross-lingual speech retrieval. Overall we find that the task of MMCLIR and specifically cross-lingual speech retrieval is quite complex. Further we pinpoint open issues related to handling cross-lingual audio and text retrieval for low resource languages that need to be addressed in future research.
%U https://aclanthology.org/2020.clssts-1.10
%P 58-67
Markdown (Informal)
[An Investigative Study of Multi-Modal Cross-Lingual Retrieval](https://aclanthology.org/2020.clssts-1.10) (Arora et al., CLSSTS 2020)
ACL
- Piyush Arora, Dimitar Shterionov, Yasufumi Moriya, Abhishek Kaushik, Daria Dzendzik, and Gareth Jones. 2020. An Investigative Study of Multi-Modal Cross-Lingual Retrieval. In Proceedings of the workshop on Cross-Language Search and Summarization of Text and Speech (CLSSTS2020), pages 58–67, Marseille, France. European Language Resources Association.