2007 Fiscal Year Final Research Report Summary
Building resources and a model for computing paraphrase based on lexical semantics
| Project/Area Number |
17300047
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | Nara Institute of Science and Technology |
|---|
Principal Investigator |
INUI Kentaro Nara Institute of Science and Technology, Graduate School of Information Science, Associate Professor (60272689)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
TAKEUCHI Koichi Okayama University, Faculty of Engineering, Lecturer (80311174)
FUJITA Atsushi Nagoya University, Graduate School of Engineering, Assistant Professor (10402801)
NAKATANI Kentaro Konan University, 文学部, Associate Professor (80388751)
|
|---|
| Project Period (FY) |
2005 – 2007
|
| Keywords | natural language processing / recognizing textual entailment / paraphrase / lexical knowledge / lexical semantics / predicate-argument structure / knowledge acquisition / lexical conceptual structure |
|---|
| Research Abstract |
Aiming at building a computational model and computational recourses for computing paraphrase at the level of predicate-argument structure, this research project gained the following results:
(i) For paraphrase knowledge, a large-scale hierarchical lexicon of predicate-argument structure was built. The lexicon organizes about 4,000 Japanese basic verbs (about 7,000 senses in total) with predicate-argument structure information in a fine-grained semantic hierarchy so that lexical entries in a semantic class can be regarded as near synonyms. For augmenting this knowledge base, additional knowledge about event relations are extracted from glosses found in a human-use dictionary of Japanese. Over 35,000 relations are extracted and classified into 8 relation types, all of which are considered useful for recognizing paraphrase or textual entailment.
(ii) For scaling the basic paraphrase knowledge above, automatic acquisition of semantic relations between events from a large corpus was also exp
… More
lored. We proposed several extensions to a state-of-the-art method originally designed for entity relation extraction, reporting on the present results of our experiments on a Japanese Web corpus. The results show that (a) there are indeed specific cooccurrence patterns useful for event relation acquisition, (b) the use of cooccurrence samples involving verbal nouns has positive impacts on both re-call and precision, and (c) over five thousand relation instances are acquired from a 500M-sentence Web corpus with a precision of about 66% for action-effect relations.
(iii) For building a computational model of paraphrase, we explore the regularity underlying these classes of paraphrases, focusing on the paraphrasing of Japanese light-verb constructions (LVCs). We propose a paraphrasing model for LVCs that is based on transforming the Lexical Conceptual Structures (LCSs) of verbal elements. We also propose a refinement of an existing LCS dictionary. Experimental results show that our LCS-based paraphrasing model characterizes some of the semantic features of those verbs required for generating paraphrases, such as the direction of an action and the relationship between arguments and surface cases. Less
|
Research Products
(12 results)
-
-
-
-
-
-
-
-
-
-
-
[Presentation] Exploiting Lexical Conceptual Structure for Paraphrase Generation Natural Language Processing (IJCNLP 2005)2005
Author(s)
Atsushi, Fujita, Kentaro, Inui, Yuji, Matsumoto
Organizer
Second International Joint Conference Proceedings, (Lecture Notes in Artificial Intelligence 3651, Robert Dale, Kam-Fai Wong, Jian Su, OiYee Kwong eds.)
Place of Presentation
Korea
Year and Date
20050000
Description
「研究成果報告書概要(欧文)」より
-
