Constrained sequence-to-sequence semitic root extraction for enriching word embeddings

Ahmed El-Kishky, Xingyu Fu, Aseel Addawood, Nahil Sobh, Clare Voss, Jiawei Han

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we tackle the problem of "root extraction" from words in the Semitic language family. A challenge in applying natural language processing techniques to these languages is the data sparsity problem that arises from their rich internal morphology, where the substructure is inherently non-concatenative and morphemes are interdigitated in word formation. While previous automated methods have relied on human-curated rules or multiclass classification, they have not fully leveraged the various combinations of regular, sequential concatenative morphology within the words and the internal interleaving within templatic stems of roots and patterns. To address this, we propose a constrained sequence-tosequence root extraction method. Experimental results show our constrained model outperforms a variety of methods at root extraction. Furthermore, by enriching word embeddings with resulting decompositions, we show improved results on word analogy, word similarity, and language modeling tasks.

Original languageEnglish (US)
Title of host publicationACL 2019 - 4th Arabic Natural Language Processing Workshop, WANLP 2019 - Proceedings of the Workshop
PublisherAssociation for Computational Linguistics (ACL)
Pages88-96
Number of pages9
ISBN (Electronic)9781950737321
DOIs
StatePublished - 2019
Event4th Arabic Natural Language Processing Workshop, WANLP 2019, held at ACL 2019 - Florence, Italy
Duration: Aug 1 2019 → …

Publication series

NameACL 2019 - 4th Arabic Natural Language Processing Workshop, WANLP 2019 - Proceedings of the Workshop

Conference

Conference4th Arabic Natural Language Processing Workshop, WANLP 2019, held at ACL 2019
Country/TerritoryItaly
CityFlorence
Period8/1/19 → …

ASJC Scopus subject areas

  • Software
  • Language and Linguistics
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'Constrained sequence-to-sequence semitic root extraction for enriching word embeddings'. Together they form a unique fingerprint.

Cite this