Training Tree Transducers
Bibliographic Data
| ID | 12156247 |
|---|---|
| Authors | Jonathan Graehl (University of Southern California, Information Sciences Institute, 4676 Admiralty Way, Marina del Rey, CA 90292.., corresponding author), Kevin Knight (0000-0001-9117-1718, University of Southern California, Information Sciences Institute, 4676 Admiralty Way, Marina del Rey, CA 90292..), JONATHAN MAY (0000-0002-5284-477X, University of Southern California, Information Sciences Institute, 4676 Admiralty Way, Marina del Rey, CA 90292..) |
| Year | 2008 |
| Volume | 34 |
| Issue | 3 |
| Pages | 391-427 |
| Publication date | 2008-06-24 |
| 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.2008.07-051-r2-03-57 |
| OpenAlex | W1479669738 |
| Language | EN |
| Citations received | 3 |
| References cited | 14 |
Many probabilistic models for natural language are now written in terms of hierarchical tree structure. Tree-based modeling still lacks many of the standard tools taken for granted in (finite-state) string-based modeling. The theory of tree transducer automata provides a possible framework to draw on, as it has been worked out in an extensive literature. We motivate the use of tree transducers for natural language and address the training problem for probabilistic tree-to-tree and tree-to-string transducers
Electrical engineering · Transducer · Tree (set theory · Algorithms and Data Compression · Computer Science · Engineering · Handwritten Text Recognition Techniques · Mathematics · Natural Language Processing Techniques
| Citations per year | 0.19 |
|---|---|
| Citation span | 2010 - 2010 (1) |
| Highly cited | No |