Universal Lemmatizer: A sequence-to-sequence model for lemmatizing Universal Dependencies treebanks.
Saved in:
| Title: | Universal Lemmatizer: A sequence-to-sequence model for lemmatizing Universal Dependencies treebanks. |
|---|---|
| Authors: | Kanerva, Jenna1 (AUTHOR) jmnybl@utu.fi, Ginter, Filip1 (AUTHOR), Salakoski, Tapio1 (AUTHOR) |
| Source: | Natural Language Engineering. Sep2021, Vol. 27 Issue 5, p545-574. 30p. |
| Subjects: | Morphosyntax, Data augmentation, Machine learning, Instructional systems |
| Geographic Terms: | Turku (Finland) |
| Abstract: | In this paper, we present a novel lemmatization method based on a sequence-to-sequence neural network architecture and morphosyntactic context representation. In the proposed method, our context-sensitive lemmatizer generates the lemma one character at a time based on the surface form characters and its morphosyntactic features obtained from a morphological tagger. We argue that a sliding window context representation suffers from sparseness, while in majority of cases the morphosyntactic features of a word bring enough information to resolve lemma ambiguities while keeping the context representation dense and more practical for machine learning systems. Additionally, we study two different data augmentation methods utilizing autoencoder training and morphological transducers especially beneficial for low-resource languages. We evaluate our lemmatizer on 52 different languages and 76 different treebanks, showing that our system outperforms all latest baseline systems. Compared to the best overall baseline, UDPipe Future, our system outperforms it on 62 out of 76 treebanks reducing errors on average by 19% relative. The lemmatizer together with all trained models is made available as a part of the Turku-neural-parsing-pipeline under the Apache 2.0 license. [ABSTRACT FROM AUTHOR] |
| Copyright of Natural Language Engineering is the property of Cambridge University Press and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 152210224 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Universal Lemmatizer: A sequence-to-sequence model for lemmatizing Universal Dependencies treebanks. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Kanerva%2C+Jenna%22">Kanerva, Jenna</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> jmnybl@utu.fi</i><br /><searchLink fieldCode="AR" term="%22Ginter%2C+Filip%22">Ginter, Filip</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Salakoski%2C+Tapio%22">Salakoski, Tapio</searchLink><relatesTo>1</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Natural+Language+Engineering%22">Natural Language Engineering</searchLink>. Sep2021, Vol. 27 Issue 5, p545-574. 30p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Morphosyntax%22">Morphosyntax</searchLink><br /><searchLink fieldCode="DE" term="%22Data+augmentation%22">Data augmentation</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Instructional+systems%22">Instructional systems</searchLink> – Name: SubjectGeographic Label: Geographic Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Turku+%28Finland%29%22">Turku (Finland)</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: In this paper, we present a novel lemmatization method based on a sequence-to-sequence neural network architecture and morphosyntactic context representation. In the proposed method, our context-sensitive lemmatizer generates the lemma one character at a time based on the surface form characters and its morphosyntactic features obtained from a morphological tagger. We argue that a sliding window context representation suffers from sparseness, while in majority of cases the morphosyntactic features of a word bring enough information to resolve lemma ambiguities while keeping the context representation dense and more practical for machine learning systems. Additionally, we study two different data augmentation methods utilizing autoencoder training and morphological transducers especially beneficial for low-resource languages. We evaluate our lemmatizer on 52 different languages and 76 different treebanks, showing that our system outperforms all latest baseline systems. Compared to the best overall baseline, UDPipe Future, our system outperforms it on 62 out of 76 treebanks reducing errors on average by 19% relative. The lemmatizer together with all trained models is made available as a part of the Turku-neural-parsing-pipeline under the Apache 2.0 license. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Natural Language Engineering is the property of Cambridge University Press and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=152210224 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1017/S1351324920000224 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 30 StartPage: 545 Subjects: – SubjectFull: Morphosyntax Type: general – SubjectFull: Data augmentation Type: general – SubjectFull: Machine learning Type: general – SubjectFull: Instructional systems Type: general – SubjectFull: Turku (Finland) Type: general Titles: – TitleFull: Universal Lemmatizer: A sequence-to-sequence model for lemmatizing Universal Dependencies treebanks. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Kanerva, Jenna – PersonEntity: Name: NameFull: Ginter, Filip – PersonEntity: Name: NameFull: Salakoski, Tapio IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 09 Text: Sep2021 Type: published Y: 2021 Identifiers: – Type: issn-print Value: 13513249 Numbering: – Type: volume Value: 27 – Type: issue Value: 5 Titles: – TitleFull: Natural Language Engineering Type: main |
| ResultId | 1 |
