Neural Polysynthetic Language Modelling
Research in natural language processing commonly assumes that approaches that work well for English and and other widely-used languages are "language agnostic". In high-resource languages, especially those that are analytic, a common approach is to treat morphologically-distinct variants o...
Main Authors: | , , , , , , , , , , , , , , , , , , , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
arXiv
2020
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.2005.05477 https://arxiv.org/abs/2005.05477 |
id |
ftdatacite:10.48550/arxiv.2005.05477 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.2005.05477 2023-05-15T15:53:45+02:00 Neural Polysynthetic Language Modelling Schwartz, Lane Tyers, Francis Levin, Lori Kirov, Christo Littell, Patrick Lo, Chi-kiu Prud'hommeaux, Emily Park, Hyunji Hayley Steimel, Kenneth Knowles, Rebecca Micher, Jeffrey Strunk, Lonny Liu, Han Haley, Coleman Zhang, Katherine J. Jimmerson, Robbie Andriyanets, Vasilisa Muis, Aldrian Obaja Otani, Naoki Park, Jong Hyuk Zhang, Zhisong 2020 https://dx.doi.org/10.48550/arxiv.2005.05477 https://arxiv.org/abs/2005.05477 unknown arXiv arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ Computation and Language cs.CL FOS Computer and information sciences Article CreativeWork article Preprint 2020 ftdatacite https://doi.org/10.48550/arxiv.2005.05477 2022-03-10T15:43:29Z Research in natural language processing commonly assumes that approaches that work well for English and and other widely-used languages are "language agnostic". In high-resource languages, especially those that are analytic, a common approach is to treat morphologically-distinct variants of a common root as completely independent word types. This assumes, that there are limited morphological inflections per root, and that the majority will appear in a large enough corpus, so that the model can adequately learn statistics about each form. Approaches like stemming, lemmatization, or subword segmentation are often used when either of those assumptions do not hold, particularly in the case of synthetic languages like Spanish or Russian that have more inflection than English. In the literature, languages like Finnish or Turkish are held up as extreme examples of complexity that challenge common modelling assumptions. Yet, when considering all of the world's languages, Finnish and Turkish are closer to the average case. When we consider polysynthetic languages (those at the extreme of morphological complexity), approaches like stemming, lemmatization, or subword modelling may not suffice. These languages have very high numbers of hapax legomena, showing the need for appropriate morphological handling of words, without which it is not possible for a model to capture enough word statistics. We examine the current state-of-the-art in language modelling, machine translation, and text prediction for four polysynthetic languages: GuaranĂ, St. Lawrence Island Yupik, Central Alaskan Yupik, and Inuktitut. We then propose a novel framework for language modelling that combines knowledge representations from finite-state morphological analyzers with Tensor Product Representations in order to enable neural language models capable of handling the full range of typologically variant languages. Article in Journal/Newspaper central alaskan yupik inuktitut St Lawrence Island St. Lawrence Island Yupik Yupik DataCite Metadata Store (German National Library of Science and Technology) Lawrence Island ENVELOPE(-103.718,-103.718,56.967,56.967) |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
unknown |
topic |
Computation and Language cs.CL FOS Computer and information sciences |
spellingShingle |
Computation and Language cs.CL FOS Computer and information sciences Schwartz, Lane Tyers, Francis Levin, Lori Kirov, Christo Littell, Patrick Lo, Chi-kiu Prud'hommeaux, Emily Park, Hyunji Hayley Steimel, Kenneth Knowles, Rebecca Micher, Jeffrey Strunk, Lonny Liu, Han Haley, Coleman Zhang, Katherine J. Jimmerson, Robbie Andriyanets, Vasilisa Muis, Aldrian Obaja Otani, Naoki Park, Jong Hyuk Zhang, Zhisong Neural Polysynthetic Language Modelling |
topic_facet |
Computation and Language cs.CL FOS Computer and information sciences |
description |
Research in natural language processing commonly assumes that approaches that work well for English and and other widely-used languages are "language agnostic". In high-resource languages, especially those that are analytic, a common approach is to treat morphologically-distinct variants of a common root as completely independent word types. This assumes, that there are limited morphological inflections per root, and that the majority will appear in a large enough corpus, so that the model can adequately learn statistics about each form. Approaches like stemming, lemmatization, or subword segmentation are often used when either of those assumptions do not hold, particularly in the case of synthetic languages like Spanish or Russian that have more inflection than English. In the literature, languages like Finnish or Turkish are held up as extreme examples of complexity that challenge common modelling assumptions. Yet, when considering all of the world's languages, Finnish and Turkish are closer to the average case. When we consider polysynthetic languages (those at the extreme of morphological complexity), approaches like stemming, lemmatization, or subword modelling may not suffice. These languages have very high numbers of hapax legomena, showing the need for appropriate morphological handling of words, without which it is not possible for a model to capture enough word statistics. We examine the current state-of-the-art in language modelling, machine translation, and text prediction for four polysynthetic languages: GuaranĂ, St. Lawrence Island Yupik, Central Alaskan Yupik, and Inuktitut. We then propose a novel framework for language modelling that combines knowledge representations from finite-state morphological analyzers with Tensor Product Representations in order to enable neural language models capable of handling the full range of typologically variant languages. |
format |
Article in Journal/Newspaper |
author |
Schwartz, Lane Tyers, Francis Levin, Lori Kirov, Christo Littell, Patrick Lo, Chi-kiu Prud'hommeaux, Emily Park, Hyunji Hayley Steimel, Kenneth Knowles, Rebecca Micher, Jeffrey Strunk, Lonny Liu, Han Haley, Coleman Zhang, Katherine J. Jimmerson, Robbie Andriyanets, Vasilisa Muis, Aldrian Obaja Otani, Naoki Park, Jong Hyuk Zhang, Zhisong |
author_facet |
Schwartz, Lane Tyers, Francis Levin, Lori Kirov, Christo Littell, Patrick Lo, Chi-kiu Prud'hommeaux, Emily Park, Hyunji Hayley Steimel, Kenneth Knowles, Rebecca Micher, Jeffrey Strunk, Lonny Liu, Han Haley, Coleman Zhang, Katherine J. Jimmerson, Robbie Andriyanets, Vasilisa Muis, Aldrian Obaja Otani, Naoki Park, Jong Hyuk Zhang, Zhisong |
author_sort |
Schwartz, Lane |
title |
Neural Polysynthetic Language Modelling |
title_short |
Neural Polysynthetic Language Modelling |
title_full |
Neural Polysynthetic Language Modelling |
title_fullStr |
Neural Polysynthetic Language Modelling |
title_full_unstemmed |
Neural Polysynthetic Language Modelling |
title_sort |
neural polysynthetic language modelling |
publisher |
arXiv |
publishDate |
2020 |
url |
https://dx.doi.org/10.48550/arxiv.2005.05477 https://arxiv.org/abs/2005.05477 |
long_lat |
ENVELOPE(-103.718,-103.718,56.967,56.967) |
geographic |
Lawrence Island |
geographic_facet |
Lawrence Island |
genre |
central alaskan yupik inuktitut St Lawrence Island St. Lawrence Island Yupik Yupik |
genre_facet |
central alaskan yupik inuktitut St Lawrence Island St. Lawrence Island Yupik Yupik |
op_rights |
arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
op_doi |
https://doi.org/10.48550/arxiv.2005.05477 |
_version_ |
1766388939934924800 |