Joint Prediction of Word Alignment with Alignment Types
| Autor: | Anoop Sarkar, Anahita Mansouri Bigvand, Te Bu |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Linguistics and Language
Computer science business.industry Communication 05 social sciences Computer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing) Pattern recognition Statistical model 010501 environmental sciences Type (model theory) 01 natural sciences Computer Science Applications Task (project management) Human-Computer Interaction Artificial Intelligence 0502 economics and business Artificial intelligence 050207 economics business Joint (audio engineering) Word (computer architecture) Generative grammar 0105 earth and related environmental sciences |
| Zdroj: | Transactions of the Association for Computational Linguistics. 5:501-514 |
| ISSN: | 2307-387X |
| DOI: | 10.1162/tacl_a_00076 |
| Popis: | Current word alignment models do not distinguish between different types of alignment links. In this paper, we provide a new probabilistic model for word alignment where word alignments are associated with linguistically motivated alignment types. We propose a novel task of joint prediction of word alignment and alignment types and propose novel semi-supervised learning algorithms for this task. We also solve a sub-task of predicting the alignment type given an aligned word pair. In our experimental results, the generative models we introduce to model alignment types significantly outperform the models without alignment types. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|