Learning Dependency Translation Models as Collections of Finite-State Head Transducers
Bibliographic Data
| ID | 12156193 |
|---|---|
| Authors | Hiyan Alshawi (Shannon Laboratory, AT&T Labs, 180 Park Avenue, Florham Park, NJ 07932, corresponding author), Srinivas Bangalore (Shannon Laboratory, AT&T Labs, 180 Park Avenue, Florham Park, NJ 07932), Shona Douglas (Shannon Laboratory, AT&T Labs, 180 Park Avenue, Florham Park, NJ 07932) |
| Year | 2000 |
| Volume | 26 |
| Issue | 1 |
| Pages | 45-60 |
| Publication date | 2000-03-01 |
| 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 | 10.1162/089120100561629 |
| OpenAlex | W2124262992 |
| Language | EN |
| Citations received | 4 |
| References cited | 6 |
The paper defines weighted head transducers, finite-state machines that perform middle-out string transduction. These transducers are strictly more expressive than the special case of standard left-to-right finite-state transducers. Dependency transduction models are then defined as collections of weighted head transducers that are applied hierarchically. A dynamic programming search algorithm is described for finding the optimal transduction of an input string with respect to a dependency transduction model. A method for automatically training a dependency transduction model from a set of input-output example strings is presented. The method first searches for hierarchical alignments of the training examples guided by correlation statistics, and then constructs the transitions of head transducers that are consistent with these alignments. Experimental results are given for applying the training method to translation from English to Spanish and Japanese
Acoustics · Algorithm · Dependency (UML · Finite-state machine · Head (geology · Machine translation · Physics · Programming language · Representation (politics · Set (abstract data type · String (physics · Transducer · Transduction (biophysics · Translation (biology · Computer Science · Handwritten Text Recognition Techniques · Mathematics · Natural Language Processing Techniques · Topic Modeling · Artificial Intelligence
| Citations per year | 0.18 |
|---|---|
| Citation span | 2004 - 2017 (14) |
| Highly cited | No |