SARAL: A Low-Resource Cross-Lingual Domain-Focused Information Retrieval System for Effective Rapid Document Triage

SARAL: A Low-Resource Cross-Lingual Domain-Focused Information Retrieval System for Effective Rapid Document Triage. Boschee, E., Barry, J., Billa, J., Freedman, M., \textbfGowda, Thamme, Lignos, C., Palen-Michel, C., Pust, M., Khonglah, B. K., Madikeri, S., May, J., & Miller, S. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 19–24, Florence, Italy, July, 2019. Association for Computational Linguistics.

Paper doi abstract bibtex

With the increasing democratization of electronic media, vast information resources are available in less-frequently-taught languages such as Swahili or Somali. That information, which may be crucially important and not available elsewhere, can be difficult for monolingual English speakers to effectively access. In this paper we present an end-to-end cross-lingual information retrieval (CLIR) and summarization system for low-resource languages that 1) enables English speakers to search foreign language repositories of text and audio using English queries, 2) summarizes the retrieved documents in English with respect to a particular information need, and 3) provides complete transcriptions and translations as needed. The SARAL system achieved the top end-to-end performance in the most recent IARPA MATERIAL CLIR+summarization evaluations. Our demonstration system provides end-to-end open query retrieval and summarization capability, and presents the original source text or audio, speech transcription, and machine translation, for two low resource languages.

@inproceedings{boschee-etal-2019-saral,
    title = "{SARAL}: A Low-Resource Cross-Lingual Domain-Focused Information Retrieval System for Effective Rapid Document Triage",
    author = "Boschee, Elizabeth  and
      Barry, Joel  and
      Billa, Jayadev  and
      Freedman, Marjorie  and
      \textbf{Gowda, Thamme}  and
      Lignos, Constantine  and
      Palen-Michel, Chester  and
      Pust, Michael  and
      Khonglah, Banriskhem Kayang  and
      Madikeri, Srikanth  and
      May, Jonathan  and
      Miller, Scott",
    booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations",
    month = jul,
    year = "2019",
    address = "Florence, Italy",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/P19-3004",
    doi = "10.18653/v1/P19-3004",
    pages = "19--24",
    abstract = "With the increasing democratization of electronic media, vast information resources are available in less-frequently-taught languages such as Swahili or Somali. That information, which may be crucially important and not available elsewhere, can be difficult for monolingual English speakers to effectively access. In this paper we present an end-to-end cross-lingual information retrieval (CLIR) and summarization system for low-resource languages that 1) enables English speakers to search foreign language repositories of text and audio using English queries, 2) summarizes the retrieved documents in English with respect to a particular information need, and 3) provides complete transcriptions and translations as needed. The SARAL system achieved the top end-to-end performance in the most recent IARPA MATERIAL CLIR+summarization evaluations. Our demonstration system provides end-to-end open query retrieval and summarization capability, and presents the original source text or audio, speech transcription, and machine translation, for two low resource languages.",
}

Downloads: 0

{"_id":"XyjZPf8GQZAQCPcaa","bibbaseid":"boschee-barry-billa-freedman-textbfgowda-lignos-palenmichel-pust-etal-saralalowresourcecrosslingualdomainfocusedinformationretrievalsystemforeffectiverapiddocumenttriage-2019","author_short":["Boschee, E.","Barry, J.","Billa, J.","Freedman, M.","\\textbfGowda, Thamme","Lignos, C.","Palen-Michel, C.","Pust, M.","Khonglah, B. K.","Madikeri, S.","May, J.","Miller, S."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"SARAL: A Low-Resource Cross-Lingual Domain-Focused Information Retrieval System for Effective Rapid Document Triage","author":[{"propositions":[],"lastnames":["Boschee"],"firstnames":["Elizabeth"],"suffixes":[]},{"propositions":[],"lastnames":["Barry"],"firstnames":["Joel"],"suffixes":[]},{"propositions":[],"lastnames":["Billa"],"firstnames":["Jayadev"],"suffixes":[]},{"propositions":[],"lastnames":["Freedman"],"firstnames":["Marjorie"],"suffixes":[]},{"firstnames":[],"propositions":[],"lastnames":["\\textbfGowda, Thamme"],"suffixes":[]},{"propositions":[],"lastnames":["Lignos"],"firstnames":["Constantine"],"suffixes":[]},{"propositions":[],"lastnames":["Palen-Michel"],"firstnames":["Chester"],"suffixes":[]},{"propositions":[],"lastnames":["Pust"],"firstnames":["Michael"],"suffixes":[]},{"propositions":[],"lastnames":["Khonglah"],"firstnames":["Banriskhem","Kayang"],"suffixes":[]},{"propositions":[],"lastnames":["Madikeri"],"firstnames":["Srikanth"],"suffixes":[]},{"propositions":[],"lastnames":["May"],"firstnames":["Jonathan"],"suffixes":[]},{"propositions":[],"lastnames":["Miller"],"firstnames":["Scott"],"suffixes":[]}],"booktitle":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations","month":"July","year":"2019","address":"Florence, Italy","publisher":"Association for Computational Linguistics","url":"https://www.aclweb.org/anthology/P19-3004","doi":"10.18653/v1/P19-3004","pages":"19–24","abstract":"With the increasing democratization of electronic media, vast information resources are available in less-frequently-taught languages such as Swahili or Somali. That information, which may be crucially important and not available elsewhere, can be difficult for monolingual English speakers to effectively access. In this paper we present an end-to-end cross-lingual information retrieval (CLIR) and summarization system for low-resource languages that 1) enables English speakers to search foreign language repositories of text and audio using English queries, 2) summarizes the retrieved documents in English with respect to a particular information need, and 3) provides complete transcriptions and translations as needed. The SARAL system achieved the top end-to-end performance in the most recent IARPA MATERIAL CLIR+summarization evaluations. Our demonstration system provides end-to-end open query retrieval and summarization capability, and presents the original source text or audio, speech transcription, and machine translation, for two low resource languages.","bibtex":"@inproceedings{boschee-etal-2019-saral,\n title = \"{SARAL}: A Low-Resource Cross-Lingual Domain-Focused Information Retrieval System for Effective Rapid Document Triage\",\n author = \"Boschee, Elizabeth and\n Barry, Joel and\n Billa, Jayadev and\n Freedman, Marjorie and\n \\textbf{Gowda, Thamme} and\n Lignos, Constantine and\n Palen-Michel, Chester and\n Pust, Michael and\n Khonglah, Banriskhem Kayang and\n Madikeri, Srikanth and\n May, Jonathan and\n Miller, Scott\",\n booktitle = \"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations\",\n month = jul,\n year = \"2019\",\n address = \"Florence, Italy\",\n publisher = \"Association for Computational Linguistics\",\n url = \"https://www.aclweb.org/anthology/P19-3004\",\n doi = \"10.18653/v1/P19-3004\",\n pages = \"19--24\",\n abstract = \"With the increasing democratization of electronic media, vast information resources are available in less-frequently-taught languages such as Swahili or Somali. That information, which may be crucially important and not available elsewhere, can be difficult for monolingual English speakers to effectively access. In this paper we present an end-to-end cross-lingual information retrieval (CLIR) and summarization system for low-resource languages that 1) enables English speakers to search foreign language repositories of text and audio using English queries, 2) summarizes the retrieved documents in English with respect to a particular information need, and 3) provides complete transcriptions and translations as needed. The SARAL system achieved the top end-to-end performance in the most recent IARPA MATERIAL CLIR+summarization evaluations. Our demonstration system provides end-to-end open query retrieval and summarization capability, and presents the original source text or audio, speech transcription, and machine translation, for two low resource languages.\",\n}\n\n\n","author_short":["Boschee, E.","Barry, J.","Billa, J.","Freedman, M.","\\textbfGowda, Thamme","Lignos, C.","Palen-Michel, C.","Pust, M.","Khonglah, B. K.","Madikeri, S.","May, J.","Miller, S."],"bibbaseid":"boschee-barry-billa-freedman-textbfgowda-lignos-palenmichel-pust-etal-saralalowresourcecrosslingualdomainfocusedinformationretrievalsystemforeffectiverapiddocumenttriage-2019","role":"author","urls":{"Paper":"https://www.aclweb.org/anthology/P19-3004"},"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://bibbase.org/f/TnumWo2CpGS8ziR7g/tg.bib","dataSources":["Yq795aWkkPdk8PFkL"],"keywords":[],"search_terms":["saral","low","resource","cross","lingual","domain","focused","information","retrieval","system","effective","rapid","document","triage","boschee","barry","billa","freedman","\\textbfgowda","lignos","palen-michel","pust","khonglah","madikeri","may","miller"],"title":"SARAL: A Low-Resource Cross-Lingual Domain-Focused Information Retrieval System for Effective Rapid Document Triage","year":2019}