@inproceedings{shareghi-etal-2019-show,
title = "Show Some Love to Your n-grams: A Bit of Progress and Stronger n-gram Language Modeling Baselines",
author = "Shareghi, Ehsan and
Gerz, Daniela and
Vuli{\'c}, Ivan and
Korhonen, Anna",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1417",
doi = "10.18653/v1/N19-1417",
pages = "4113--4118",
abstract = "In recent years neural language models (LMs) have set the state-of-the-art performance for several benchmarking datasets. While the reasons for their success and their computational demand are well-documented, a comparison between neural models and more recent developments in n-gram models is neglected. In this paper, we examine the recent progress in n-gram literature, running experiments on 50 languages covering all morphological language families. Experimental results illustrate that a simple extension of Modified Kneser-Ney outperforms an lstm language model on 42 languages while a word-level Bayesian n-gram LM (Shareghi et al., 2017) outperforms the character-aware neural model (Kim et al., 2016) on average across all languages, and its extension which explicitly injects linguistic knowledge (Gerz et al., 2018) on 8 languages. Further experiments on larger Europarl datasets for 3 languages indicate that neural architectures are able to outperform computationally much cheaper n-gram models: n-gram training is up to 15,000x quicker. Our experiments illustrate that standalone n-gram models lend themselves as natural choices for resource-lean or morphologically rich languages, while the recent progress has significantly improved their accuracy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shareghi-etal-2019-show">
<titleInfo>
<title>Show Some Love to Your n-grams: A Bit of Progress and Stronger n-gram Language Modeling Baselines</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ehsan</namePart>
<namePart type="family">Shareghi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniela</namePart>
<namePart type="family">Gerz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Vulić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-jun</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In recent years neural language models (LMs) have set the state-of-the-art performance for several benchmarking datasets. While the reasons for their success and their computational demand are well-documented, a comparison between neural models and more recent developments in n-gram models is neglected. In this paper, we examine the recent progress in n-gram literature, running experiments on 50 languages covering all morphological language families. Experimental results illustrate that a simple extension of Modified Kneser-Ney outperforms an lstm language model on 42 languages while a word-level Bayesian n-gram LM (Shareghi et al., 2017) outperforms the character-aware neural model (Kim et al., 2016) on average across all languages, and its extension which explicitly injects linguistic knowledge (Gerz et al., 2018) on 8 languages. Further experiments on larger Europarl datasets for 3 languages indicate that neural architectures are able to outperform computationally much cheaper n-gram models: n-gram training is up to 15,000x quicker. Our experiments illustrate that standalone n-gram models lend themselves as natural choices for resource-lean or morphologically rich languages, while the recent progress has significantly improved their accuracy.</abstract>
<identifier type="citekey">shareghi-etal-2019-show</identifier>
<identifier type="doi">10.18653/v1/N19-1417</identifier>
<location>
<url>https://aclanthology.org/N19-1417</url>
</location>
<part>
<date>2019-jun</date>
<extent unit="page">
<start>4113</start>
<end>4118</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Show Some Love to Your n-grams: A Bit of Progress and Stronger n-gram Language Modeling Baselines
%A Shareghi, Ehsan
%A Gerz, Daniela
%A Vulić, Ivan
%A Korhonen, Anna
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 jun
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F shareghi-etal-2019-show
%X In recent years neural language models (LMs) have set the state-of-the-art performance for several benchmarking datasets. While the reasons for their success and their computational demand are well-documented, a comparison between neural models and more recent developments in n-gram models is neglected. In this paper, we examine the recent progress in n-gram literature, running experiments on 50 languages covering all morphological language families. Experimental results illustrate that a simple extension of Modified Kneser-Ney outperforms an lstm language model on 42 languages while a word-level Bayesian n-gram LM (Shareghi et al., 2017) outperforms the character-aware neural model (Kim et al., 2016) on average across all languages, and its extension which explicitly injects linguistic knowledge (Gerz et al., 2018) on 8 languages. Further experiments on larger Europarl datasets for 3 languages indicate that neural architectures are able to outperform computationally much cheaper n-gram models: n-gram training is up to 15,000x quicker. Our experiments illustrate that standalone n-gram models lend themselves as natural choices for resource-lean or morphologically rich languages, while the recent progress has significantly improved their accuracy.
%R 10.18653/v1/N19-1417
%U https://aclanthology.org/N19-1417
%U https://doi.org/10.18653/v1/N19-1417
%P 4113-4118
Markdown (Informal)
[Show Some Love to Your n-grams: A Bit of Progress and Stronger n-gram Language Modeling Baselines](https://aclanthology.org/N19-1417) (Shareghi et al., NAACL 2019)
ACL