Constrained Sequence-to-sequence Semitic Root Extraction for Enriching Word Embeddings
| Autor: | Xingyu Fu, Nahil Sobh, Clare R. Voss, Jiawei Han, Ahmed El-Kishky, Aseel Addawood |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Root (linguistics)
Morphology (linguistics) Computer science business.industry Analogy Word formation Semitic languages computer.software_genre Variety (linguistics) Multiclass classification Morpheme Language model Artificial intelligence Semitic root business computer Word (computer architecture) Natural language processing |
| Zdroj: | WANLP@ACL 2019 |
| Popis: | 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-to-sequence 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|