Less is More, More or Less... Finding the Optimal Threshold for Lexicalization in Chunking
Fuente:
Redalyc
Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Artículo científico |
| Langue: | en |
| Publié: |
Instituto Politécnico Nacional
2017
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1876468003863789568 |
|---|---|
| author | Balázs Indig |
| author_facet | Balázs Indig |
| contents | Less is More, More or Less... Finding the Optimal Threshold for Lexicalization in Chunking Balázs Indig Computación CRF IOB labels Phrase chunking sequential tagging multiple IOB representations Lexicalization of the input of sequential taggers has gone a long way since it was invented by Molina and Pla [4]. In this paper we thoroughly investigate the method introduced by Indig and Endrédy [2] to find out the best lexicalization level for chunking and to explore the behavior of different IOB representations. Both tasks are applied to the CoNLL-2000 dataset. Our goal is to introduce a transformation method to accommodate the parameters of the development set to the training set using their frequency distributions which other tasks like POS tagging or NER could benefit too. 2017 artículo científico 1405-5546 https://www.redalyc.org/articulo.oa?id=61553900007 en http://www.redalyc.org/revista.oa?id=615 Computación y Sistemas application/pdf Instituto Politécnico Nacional Computación y Sistemas (México) Num.4 Vol.21 |
| format | Artículo científico |
| id | redalyc_61553900007 |
| institution | Redalyc |
| language | en |
| publishDate | 2017 |
| publisher | Instituto Politécnico Nacional |
| spellingShingle | Less is More, More or Less... Finding the Optimal Threshold for Lexicalization in Chunking Balázs Indig Computación CRF IOB labels Phrase chunking sequential tagging multiple IOB representations Less is More, More or Less... Finding the Optimal Threshold for Lexicalization in Chunking Balázs Indig Computación CRF IOB labels Phrase chunking sequential tagging multiple IOB representations Lexicalization of the input of sequential taggers has gone a long way since it was invented by Molina and Pla [4]. In this paper we thoroughly investigate the method introduced by Indig and Endrédy [2] to find out the best lexicalization level for chunking and to explore the behavior of different IOB representations. Both tasks are applied to the CoNLL-2000 dataset. Our goal is to introduce a transformation method to accommodate the parameters of the development set to the training set using their frequency distributions which other tasks like POS tagging or NER could benefit too. 2017 artículo científico 1405-5546 https://www.redalyc.org/articulo.oa?id=61553900007 en http://www.redalyc.org/revista.oa?id=615 Computación y Sistemas application/pdf Instituto Politécnico Nacional Computación y Sistemas (México) Num.4 Vol.21 |
| title | Less is More, More or Less... Finding the Optimal Threshold for Lexicalization in Chunking |
| topic | Computación CRF IOB labels Phrase chunking sequential tagging multiple IOB representations |
| url | https://www.redalyc.org/articulo.oa?id=61553900007 |