（まだ英語の内容が多いですが、徐々に日本語コンテンツを増やしていこうと思います。詳細は英語版のほうにあります。）
I am a fifth year Ph.D. candidate at LTI in CMU, advised by Dr. Teruko Mitamura. My research interest includes measuring meaning similarity of texts, and its application to Question Answering, Recognizing Textual Entailment, automatic evaluation of Information Access system, Information Extraction, and Information Retrieval. I am one of the organizers of a benchmark task for recognizing textual entailment, paraphrase and contradiction, called NTCIR-9 RITE (Recognizing Inference in TExt).
| 学歴 |
 |
博士課程
(2006年8月 - 現在)
カーネギーメロン大学 (米国ピッツバーグ)
コンピュータサイエンス学部・言語技術研究所
修士
(2004年8月 - 2006年8月)
カーネギーメロン大学 (米国ピッツバーグ)
コンピュータサイエンス学部・言語技術研究所
(2000年4月 - 2004年3月)
学士 早稲田大学・情報学科 (村岡洋一研究室)
|
研究
プロジェクト |
|
(2011年秋 - 現在)
Yahoo! FREP プロジェクト - 雇用主: Yahoo! Labs
We are developing a question answering prototype which can process complex questions asked in a community Q&A site.
(2011年冬 - 現在)
SmartReader - スポンサー: NPRP (カタール国立研究基金)
We are developing an intelligent educational software for English language learners. It's going to be application of various computer science research, especially Question Answering, and Paraphrase Generation.
(2010年春 - 現在)
MRP:マシンリーディングプログラム - スポンサー: 米国防高等研究計画局 (米国空軍研究所)
I work at RACR (Reading and Contextual Reasoning) team under Machine Reading Program, which aims to build a universal text engine that captures knowledge from naturally occurring text and transforms it into the formal representations used by artificial intelligence (AI) reasoning systems. I have contributed in two aspects so far: 1. building an mixture-of-expert system that smartly merges outputs from various NLP components; 2. buidling automatic evaluation software for evaluating entity and relation mention extraction accuracy which also provides tools to analyze errors.
(2009年6月 - 2009年8月)
ワトソン (DeepQA) プロジェクト - 雇用主: IBMリサーチ
At IBM T.J. Watson Research Center, New York, I spent three months as a research intern. I developed one of the algorithms used to score answer candidates. The algorithm analyzes supporting evidence found in a set of text passages retrieved for each candidate answer, and estimates how well they support the answer by modeling the semantic similarity between the passages and the Jeopardy! clue.
(2008年秋 - 2010年春)
KIJI QA プロジェクト - スポンサー: IBM研究所
We built a Complex QA system for Japanese, in collaboration with IBM Research - Tokyo, which ultimately aims at solving various problems in Business Intelligence. The system has been evaluated in NTCIR ACLIA and resulted in a good performance. The project HTML-based annotation viewer for UIMA.
(2004年秋 - 2008年秋)
JAVELIN QA Project - スポンサー: AQUAINT (ARDA/DTO/IARPA)
As a graduate research assistant, I contributed in building open-domain Factoid and Complex Question Answering systems where I worked on crosslingual English-to-Japanese (EJ) and monolingual Japanese-to-Japanese (JJ) modules. My experience varies in various aspects of the QA research, e.g. Question Analysis, Named Entity Transliteration, Document Retrieval, Information Extraction, Answer Summarization, web-based demo, and batch evaluation with automatic error analysis.
As a result of intensive research effort, the Javlein system achieved remarkable results in competition style evaluation-oriented QA tasks similar to TREC and CLEF; we achieved the best result among participants in NTCIR-6 CLQA JJ subtask, NTCIR-7 ACLIA CCLQA EJ and JJ task, and NTCIR-7 ACLIA IR4QA EJ task.
|
| |
|
