Cross-lingual Joint Entity and Word Embedding to Improve Entity Linking and Parallel Sentence Mining

Cross-lingual Joint Entity and Word Embedding to Improve Entity Linking and Parallel Sentence Mining. Pan, X., \textbfGowda, Thamme, Ji, H., May, J., & Miller, S. In Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019), pages 56–66, Hong Kong, China, November, 2019. Association for Computational Linguistics.

Paper doi abstract bibtex

Entities, which refer to distinct objects in the real world, can be viewed as language universals and used as effective signals to generate less ambiguous semantic representations and align multiple languages. We propose a novel method, CLEW, to generate cross-lingual data that is a mix of entities and contextual words based on Wikipedia. We replace each anchor link in the source language with its corresponding entity title in the target language if it exists, or in the source language otherwise. A cross-lingual joint entity and word embedding learned from this kind of data not only can disambiguate linkable entities but can also effectively represent unlinkable entities. Because this multilingual common space directly relates the semantics of contextual words in the source language to that of entities in the target language, we leverage it for unsupervised cross-lingual entity linking. Experimental results show that CLEW significantly advances the state-of-the-art: up to 3.1% absolute F-score gain for unsupervised cross-lingual entity linking. Moreover, it provides reliable alignment on both the word/entity level and the sentence level, and thus we use it to mine parallel sentences for all (302, 2) language pairs in Wikipedia.

@inproceedings{pan-etal-2019-cross,
    title = "Cross-lingual Joint Entity and Word Embedding to Improve Entity Linking and Parallel Sentence Mining",
    author = "Pan, Xiaoman  and
      \textbf{Gowda, Thamme}  and
      Ji, Heng  and
      May, Jonathan  and
      Miller, Scott",
    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://www.aclweb.org/anthology/D19-6107",
    doi = "10.18653/v1/D19-6107",
    pages = "56--66",
    abstract = "Entities, which refer to distinct objects in the real world, can be viewed as language universals and used as effective signals to generate less ambiguous semantic representations and align multiple languages. We propose a novel method, CLEW, to generate cross-lingual data that is a mix of entities and contextual words based on Wikipedia. We replace each anchor link in the source language with its corresponding entity title in the target language if it exists, or in the source language otherwise. A cross-lingual joint entity and word embedding learned from this kind of data not only can disambiguate linkable entities but can also effectively represent unlinkable entities. Because this multilingual common space directly relates the semantics of contextual words in the source language to that of entities in the target language, we leverage it for unsupervised cross-lingual entity linking. Experimental results show that CLEW significantly advances the state-of-the-art: up to 3.1{\%} absolute F-score gain for unsupervised cross-lingual entity linking. Moreover, it provides reliable alignment on both the word/entity level and the sentence level, and thus we use it to mine parallel sentences for all (302, 2) language pairs in Wikipedia.",
}

Downloads: 0

{"_id":"c5KvZFunrb5RY7vCh","bibbaseid":"pan-textbfgowda-ji-may-miller-crosslingualjointentityandwordembeddingtoimproveentitylinkingandparallelsentencemining-2019","author_short":["Pan, X.","\\textbfGowda, Thamme","Ji, H.","May, J.","Miller, S."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Cross-lingual Joint Entity and Word Embedding to Improve Entity Linking and Parallel Sentence Mining","author":[{"propositions":[],"lastnames":["Pan"],"firstnames":["Xiaoman"],"suffixes":[]},{"firstnames":[],"propositions":[],"lastnames":["\\textbfGowda, Thamme"],"suffixes":[]},{"propositions":[],"lastnames":["Ji"],"firstnames":["Heng"],"suffixes":[]},{"propositions":[],"lastnames":["May"],"firstnames":["Jonathan"],"suffixes":[]},{"propositions":[],"lastnames":["Miller"],"firstnames":["Scott"],"suffixes":[]}],"booktitle":"Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)","month":"November","year":"2019","address":"Hong Kong, China","publisher":"Association for Computational Linguistics","url":"https://www.aclweb.org/anthology/D19-6107","doi":"10.18653/v1/D19-6107","pages":"56–66","abstract":"Entities, which refer to distinct objects in the real world, can be viewed as language universals and used as effective signals to generate less ambiguous semantic representations and align multiple languages. We propose a novel method, CLEW, to generate cross-lingual data that is a mix of entities and contextual words based on Wikipedia. We replace each anchor link in the source language with its corresponding entity title in the target language if it exists, or in the source language otherwise. A cross-lingual joint entity and word embedding learned from this kind of data not only can disambiguate linkable entities but can also effectively represent unlinkable entities. Because this multilingual common space directly relates the semantics of contextual words in the source language to that of entities in the target language, we leverage it for unsupervised cross-lingual entity linking. Experimental results show that CLEW significantly advances the state-of-the-art: up to 3.1% absolute F-score gain for unsupervised cross-lingual entity linking. Moreover, it provides reliable alignment on both the word/entity level and the sentence level, and thus we use it to mine parallel sentences for all (302, 2) language pairs in Wikipedia.","bibtex":"@inproceedings{pan-etal-2019-cross,\n title = \"Cross-lingual Joint Entity and Word Embedding to Improve Entity Linking and Parallel Sentence Mining\",\n author = \"Pan, Xiaoman and\n \\textbf{Gowda, Thamme} and\n Ji, Heng and\n May, Jonathan and\n Miller, Scott\",\n booktitle = \"Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)\",\n month = nov,\n year = \"2019\",\n address = \"Hong Kong, China\",\n publisher = \"Association for Computational Linguistics\",\n url = \"https://www.aclweb.org/anthology/D19-6107\",\n doi = \"10.18653/v1/D19-6107\",\n pages = \"56--66\",\n abstract = \"Entities, which refer to distinct objects in the real world, can be viewed as language universals and used as effective signals to generate less ambiguous semantic representations and align multiple languages. We propose a novel method, CLEW, to generate cross-lingual data that is a mix of entities and contextual words based on Wikipedia. We replace each anchor link in the source language with its corresponding entity title in the target language if it exists, or in the source language otherwise. A cross-lingual joint entity and word embedding learned from this kind of data not only can disambiguate linkable entities but can also effectively represent unlinkable entities. Because this multilingual common space directly relates the semantics of contextual words in the source language to that of entities in the target language, we leverage it for unsupervised cross-lingual entity linking. Experimental results show that CLEW significantly advances the state-of-the-art: up to 3.1{\\%} absolute F-score gain for unsupervised cross-lingual entity linking. Moreover, it provides reliable alignment on both the word/entity level and the sentence level, and thus we use it to mine parallel sentences for all (302, 2) language pairs in Wikipedia.\",\n}\n\n\n\n","author_short":["Pan, X.","\\textbfGowda, Thamme","Ji, H.","May, J.","Miller, S."],"bibbaseid":"pan-textbfgowda-ji-may-miller-crosslingualjointentityandwordembeddingtoimproveentitylinkingandparallelsentencemining-2019","role":"author","urls":{"Paper":"https://www.aclweb.org/anthology/D19-6107"},"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://bibbase.org/f/TnumWo2CpGS8ziR7g/tg.bib","dataSources":["Yq795aWkkPdk8PFkL"],"keywords":[],"search_terms":["cross","lingual","joint","entity","word","embedding","improve","entity","linking","parallel","sentence","mining","pan","\\textbfgowda","ji","may","miller"],"title":"Cross-lingual Joint Entity and Word Embedding to Improve Entity Linking and Parallel Sentence Mining","year":2019}