21 |
Semantic Operations for Transfer-based Machine Translation
|
|
|
|
Abstract:
Thesis (Ph.D.)--University of Washington, 2018 ; This dissertation describes a new approach to the automatic extraction of semantic mappings (transfer rules) for rule-based machine translation. This approach continues previous work in combining HPSG rule-based grammars, whose precise bidirectional implementation facilitates deep semantic analysis of sentences and the enumeration of grammatical realizations of semantic representations, and data-driven techniques of machine translation, whose automatic extraction of knowledge and statistical inference allow models to be quickly built from bitexts and to rank extracted patterns by their frequency. I define two new methods for bilingually aligning semantic fragments (or semantic subgraphs) and a heuristic strategy for aligning nodes between source and target subgraphs, which together allow me to design transfer systems that meet, and at times exceed, the translation coverage and quality of the prior state of the art with a significantly reduced dependence on idiosyncratic language-pair definitions (i.e., improved language independence). These improvements are made possible by a number of semantic operations, either designed or implemented by me and defined within this dissertation, that fully model the semantic representations and allow for inspection and transformation as graph operations. I apply my methods to the task of translating Japanese sentences into English—a typologically distant language pair.
|
|
Keyword:
Artificial intelligence; Computer science; grammar; HPSG; Linguistics; machine translation; semantic dependencies; semantics; transfer
|
|
URL: http://hdl.handle.net/1773/42432
|
|
BASE
|
|
Hide details
|
|
23 |
Challenges and opportunities of applying natural language processing in business process management
|
|
|
|
BASE
|
|
Show details
|
|
24 |
Towards Linguistically Generalizable NLP Systems: A Workshop and Shared Task ...
|
|
|
|
BASE
|
|
Show details
|
|
26 |
STREAMLInED Challenges: Aligning Research Interests with Shared Tasks
|
|
|
|
In: 2nd Workshop on the Use of Computational Methods in the Study of Endangered Languages, March 6-7, 2017. Honolulu, Hawai‘i, USA (2017)
|
|
BASE
|
|
Show details
|
|
27 |
Automated Gloss Mapping for Inferring Grammatical Properties
|
|
|
|
BASE
|
|
Show details
|
|
33 |
Are We There Yet?: The Development of a Corpus Annotated for Social Acts in Multilingual Online Discourse
|
|
|
|
In: Dialogue & Discourse; Vol 4 No 2 (2013); 1-33 ; 2152-9620 (2013)
|
|
BASE
|
|
Show details
|
|
36 |
Deriving a lexicon for a precision grammar from language documentation resources: a case study of Chintang ...
|
|
|
|
BASE
|
|
Show details
|
|
37 |
From Database to Treebank: On Enhancing Hypertext Grammars with Grammar Engineering and Treebank Search
|
|
|
|
BASE
|
|
Show details
|
|
38 |
From Database to Treebank: On Enhancing Hypertext Grammars with Grammar Engineering and Treebank Search
|
|
|
|
BASE
|
|
Show details
|
|
39 |
Deriving a lexicon for a precision grammar from language documentation resources: a case study of Chintang
|
|
|
|
In: Bender, Emily M; Schikowski, Robert; Bickel, Balthasar (2012). Deriving a lexicon for a precision grammar from language documentation resources: a case study of Chintang. In: Kay, M; Boitet, C. Proceedings of the 24th International Conference on Computational Linguistics (COLING). Mumbai: Association for Computational Linguistics, 247-262. (2012)
|
|
BASE
|
|
Show details
|
|
40 |
An analysis of translation divergence patterns using PanLex translation pairs
|
|
|
|
BASE
|
|
Show details
|
|
|
|