Main Profile

At A Glance

Development of Large-Scale Grammars Through Corpus Construction (Japanese Audio)

Google Tech Talk14:00- JST Oct 27 2010At Google Japan (Japanese Audio)Speaker : Yusuke Miyao (宮尾祐介)Bio : http://www.nii.ac.jp/en/faculty/digital_content/MIYAO-Yusuke/Affiliation : National Institute of Informatics (?立情報?研究所)Language : spoken in Japanese and slides in EnglishTitle : Development of large-scale grammars through corpus constructionAbstract :A crucial bottleneck of grammar-based deep parsing is the difficultyof the development of large-scale grammars that can analyze real-worldsentences. In our approach, the final goal of grammar development isthe construction of a treebank (parsed corpus) that conforms to agrammar theory. Given an existing corpus (e.g. Penn Treebank) and agrammar theory, we can construct a treebank at low cost. Since alarge-scale lexicon can be extracted automatically from the treebank,a large-scale grammar can be developed in a short period. In thistalk, I overview our method of corpus-based grammar development, incomparison with manual grammar development and grammar learning.Japanese title : コ?パス構築に基づく大規模文法開?Japanese abstract :文法に基づく深い構文解析の最大の問題?は,?世界の文を解析できる大規模文法の??が困難なことである.コ?パス構築に基づく文法開?手法では,文法開?の最終目的を,文法理論に基づくツリ?バンク(解析?みコ?パス)の構築と考える.既存のコ?パス(Penn Treebank など)と文法理論を利用すると,ツリ?バンクは比較的低コストで構築することができる.すると,大規模?書はツリ?バンクから自動獲得できるので,大規模文法を短期間で開?することが可能となった.本ト?クでは,人手による文法開?や文法?習と?比しながら,コ?パス構築に基づく文法開?手法を概?する.
Length: 01:11:10

Contact

Questions about Development of Large-Scale Grammars Through Corpus Construction (Japanese Audio)

Want more info about Development of Large-Scale Grammars Through Corpus Construction (Japanese Audio)? Get free advice from education experts and Noodle community members.

  • Answer

Ask a New Question