Hierarchical Phrase-Based Translation with Weighted Finite-State Transducers and Shallow- n Grammars
Bibliographic Data
| ID | 12156465 |
|---|---|
| Authors | Adrià de Gispert (University of Cambridge, corresponding author), Gonzalo Iglesias (Universidade de Vigo), Graeme Blackwood (0009-0004-0609-7613, University of Cambridge), Eduardo Rodríguez Banga (0000-0001-7989-4526, Universidade de Vigo), Bill Byrne (0000-0003-1896-4492, University of Cambridge), William Byrne (University of Cambridge) |
| Year | 2010 |
| Volume | 36 |
| Issue | 3 |
| Pages | 505-533 |
| Publication date | 2010-07-27 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Computational Linguistics (JOURNAL) |
| Journal identifiers | ISSN: 0891-2017 • E-ISSN: 1530-9312 |
| Publisher | Association for Computational Linguistics (PUBLISHER • US) |
| DOI | 10.1162/coli_a_00006 |
| OpenAlex | W2114550122 |
| Language | EN |
| Citations received | 3 |
| References cited | 9 |
In this article we describe HiFST, a lattice-based decoder for hierarchical phrase-based translation and alignment. The decoder is implemented with standard Weighted Finite-State Transducer (WFST) operations as an alternative to the well-known cube pruning procedure. We find that the use of WFSTs rather than k-best lists requires less pruning in translation search, resulting in fewer search errors, better parameter optimization, and improved translation performance. The direct generation of translation lattices in the target language can improve subsequent rescoring procedures, yielding further gains when applying long-span language models and Minimum Bayes Risk decoding. We also provide insights as to how to control the size of the search space defined by hierarchical rules. We show that shallow-n grammars, low-level rule catenation, and other search constraints can help to match the power of the translation system to specific language pairs
Algorithm · Example-based machine translation · Language model · Machine translation · Natural language processing · Phrase · Pruning · Rule-based machine translation · Speech recognition · Synchronous context-free grammar · Translation (biology · Algorithms and Data Compression · Computer Science · Natural Language Processing Techniques · Topic Modeling · Artificial Intelligence
| Citations per year | 0.25 |
|---|---|
| Citation span | 2014 - 2016 (3) |
| Highly cited | No |