Presentation | 2002/7/9 Methods for Estimating Syntactic Similarity Tetsuro TAKAHASHI, Kentaro INUI, Yuji MATSUMOTO, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | This paper discusses how to estimate the similarity of a given pair of syntactic trees. The proposed method, an extension of Collins' Tree Kernel, provides three options for similarity measurement and relaxes the constraints of node/tree matching with the time complexity O(∣T_1∣∣T_2∣). The paper also argues that the proposed method fits the question-answering task. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | similarity estimation / tree structure / dependency structure / tree matching / Tree Kernel |
Paper # | NLC2002-33 |
Date of Issue |
Conference Information | |
Committee | NLC |
---|---|
Conference Date | 2002/7/9(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Natural Language Understanding and Models of Communication (NLC) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Methods for Estimating Syntactic Similarity |
Sub Title (in English) | |
Keyword(1) | similarity estimation |
Keyword(2) | tree structure |
Keyword(3) | dependency structure |
Keyword(4) | tree matching |
Keyword(5) | Tree Kernel |
1st Author's Name | Tetsuro TAKAHASHI |
1st Author's Affiliation | Graduate School of Information Science, Nara Institute Science and Technology() |
2nd Author's Name | Kentaro INUI |
2nd Author's Affiliation | Graduate School of Information Science, Nara Institute Science and Technology |
3rd Author's Name | Yuji MATSUMOTO |
3rd Author's Affiliation | Graduate School of Information Science, Nara Institute Science and Technology |
Date | 2002/7/9 |
Paper # | NLC2002-33 |
Volume (vol) | vol.102 |
Number (no) | 200 |
Page | pp.pp.- |
#Pages | 8 |
Date of Issue |