@inproceedings{gowda-may-2020-finding,
    title = "Finding the Optimal Vocabulary Size for Neural Machine Translation",
    author = "Gowda, Thamme  and
      May, Jonathan",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2020.findings-emnlp.352",
    pages = "3955--3964",
    abstract = "We cast neural machine translation (NMT) as a classification task in an autoregressive setting and analyze the limitations of both classification and autoregression components. Classifiers are known to perform better with balanced class distributions during training. Since the Zipfian nature of languages causes imbalanced classes, we explore its effect on NMT. We analyze the effect of various vocabulary sizes on NMT performance on multiple languages with many data sizes, and reveal an explanation for why certain vocabulary sizes are better than others.",
}

{"_id":"wQ7Fora7y6H52kijk","bibbaseid":"gowda-may-findingtheoptimalvocabularysizeforneuralmachinetranslation-2020","author_short":["Gowda, T.","May, J."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Finding the Optimal Vocabulary Size for Neural Machine Translation","author":[{"propositions":[],"lastnames":["Gowda"],"firstnames":["Thamme"],"suffixes":[]},{"propositions":[],"lastnames":["May"],"firstnames":["Jonathan"],"suffixes":[]}],"booktitle":"Findings of the Association for Computational Linguistics: EMNLP 2020","month":"November","year":"2020","address":"Online","publisher":"Association for Computational Linguistics","url":"https://www.aclweb.org/anthology/2020.findings-emnlp.352","pages":"3955–3964","abstract":"We cast neural machine translation (NMT) as a classification task in an autoregressive setting and analyze the limitations of both classification and autoregression components. Classifiers are known to perform better with balanced class distributions during training. Since the Zipfian nature of languages causes imbalanced classes, we explore its effect on NMT. We analyze the effect of various vocabulary sizes on NMT performance on multiple languages with many data sizes, and reveal an explanation for why certain vocabulary sizes are better than others.","bibtex":"@inproceedings{gowda-may-2020-finding,\n title = \"Finding the Optimal Vocabulary Size for Neural Machine Translation\",\n author = \"Gowda, Thamme and\n May, Jonathan\",\n booktitle = \"Findings of the Association for Computational Linguistics: EMNLP 2020\",\n month = nov,\n year = \"2020\",\n address = \"Online\",\n publisher = \"Association for Computational Linguistics\",\n url = \"https://www.aclweb.org/anthology/2020.findings-emnlp.352\",\n pages = \"3955--3964\",\n abstract = \"We cast neural machine translation (NMT) as a classification task in an autoregressive setting and analyze the limitations of both classification and autoregression components. Classifiers are known to perform better with balanced class distributions during training. Since the Zipfian nature of languages causes imbalanced classes, we explore its effect on NMT. We analyze the effect of various vocabulary sizes on NMT performance on multiple languages with many data sizes, and reveal an explanation for why certain vocabulary sizes are better than others.\",\n}\n\n","author_short":["Gowda, T.","May, J."],"key":"gowda-may-2020-finding","id":"gowda-may-2020-finding","bibbaseid":"gowda-may-findingtheoptimalvocabularysizeforneuralmachinetranslation-2020","role":"author","urls":{"Paper":"https://www.aclweb.org/anthology/2020.findings-emnlp.352"},"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://jonmay.github.io/webpage/cutelabname/cutelabname.bib","dataSources":["ZdhKtP2cSp3Aki2ge","EaLNEHNTErABZiJhs","X5WBAKQabka5TW5z7","aLL97n6dowbaE6bHj","BnZgtH7HDESgbxKxt","hbZSwot2msWk92m5B","fcWjcoAgajPvXWcp7","GvHfaAWP6AfN6oLQE","j3Qzx9HAAC6WtJDHS","5eM3sAccSEpjSDHHQ"],"keywords":[],"search_terms":["finding","optimal","vocabulary","size","neural","machine","translation","gowda","may"],"title":"Finding the Optimal Vocabulary Size for Neural Machine Translation","year":2020}