Academic Paper |
|
|
|
|
| Title: | Dependency-based n-gram models for general purpose sentence realisation |
| Author: | Yuqing Guo |
| Institution: | Toshiba (China) Research and Development Center |
| Author: | Haifeng Wang |
| Institution: | Baidu |
| Author: | Josef Van Genabith |
| Email: | click here to access email |
| Institution: | Dublin City University |
| Linguistic Field: | Computational Linguistics; Semantics; Syntax |
| Subject Language: |
Chinese, Mandarin
English |
| Abstract: | This paper presents a general-purpose, wide-coverage, probabilistic sentence generator based on dependency n-gram models. This is particularly interesting as many semantic or abstract syntactic input specifications for sentence realisation can be represented as labelled bi-lexical dependencies or typed predicate-argument structures. Our generation method captures the mapping between semantic representations and surface forms by linearising a set of dependencies directly, rather than via the application of grammar rules as in more traditional chart-style or unification-based generators. In contrast to conventional n-gram language models over surface word forms, we exploit structural information and various linguistic features inherent in the dependency representations to constrain the generation space and improve the generation quality. A series of experiments shows that dependency-based n-gram models generalise well to different languages (English and Chinese) and representations (LFG and CoNLL). Compared with state-of-the-art generation systems, our general-purpose sentence realiser is highly competitive with the added advantages of being simple, fast, robust and accurate. |
|
|
|
|
This article appears in Natural Language Engineering Vol. 17, Issue 4, which you can read on Cambridge's site or on LINGUIST . |
|
|
|
|
Back
Add a new paper Return to Academic Papers main page Return to Directory of Linguists main page |
|
|
About LINGUIST
|
Contact Us
|
Report Broken Link
While the LINGUIST List makes every effort to ensure the linguistic relevance of sites listed on its pages, it cannot vouch for their contents. |
|
