[Date Prev][Date Next][Date Index]

[ntcir:262] Reminder: Seminar Talk on On-Demand Information Extraction

This is an announcement for a seminar talk by Satoshi
Sekine on "On-Demand Information Extraction and Wep
People Search Project", which will be held on
Dec. 13, NII, Tokyo, Japan.

The talk will be done in Japanese with English slide.
If you are interested in, please ask further information
to the secretariat of the info-plosion project at

[Japanese Annoucement]





(The talk will be in Japanese with English Slides.)



日時: 12月13日(木) 13時〜14時30分
Date&Time: December 13 (Thu.) 13:00pm - 14:30pm

場所: 国立情報学研究所 12階1208号室
Place: Room 1208, NII Hitotsubashi

講演者: 関根 聡 (ニューヨーク大学)
Speaker : Dr. Satoshi Sekine (New York University)

Title : On-Demand Information Extraction and Wep People Search Project

講演内容の紹介(in Japanese)

Abstract of On-Demand Information Extraction:
At present, adapting an Information Extraction system to new topics is
an expensive and slow process, requiring some knowledge engineering for
each new topic. We propose a new paradigm of Information Extraction
which operates 'on demand' in response to a user's query. On-demand
Information Extraction (ODIE) aims to completely eliminate the
customization effort. Given a user’s query, the system will
automatically create patterns to extract salient relations in the text
of the topic, and build tables from the extracted information using
paraphrase discovery technology. It relies on recent advances in pattern
discovery, paraphrase discovery, and extended named entity tagging.
I will show you a demo system, which produce a table in less than a
minute for any give queries.

S.Sekine "On-Demand Information Extraction" (COLING-ACL 07)

Abstract of Web People Search:
This task focuses on the disambiguation of person names in a Web
searching scenario. Finding people, information about people, in the
World Wide Web is one of the most common activities of Internet users.
Person names, however, are highly ambiguous. In most cases, therefore,
the results for this type of search are a mixture of pages about
different people that share the same name.

The participant's systems will receive as input, web pages retrieved
from a web search engine using a given person name as a query. The aim
of the task is to determine how many referents (different people) exist
for that person name, and assign to each referent its corresponding
documents. The challenge is to correctly estimate the number of
referents and group documents referring to the same individual.


Dr. Sekine's short resume:
Satoshi Sekine is an Assistant Research Professor at New York University.
He received his MSc at UMIST, UK in 1992 and his PhD in 1998 at NYU. He
has been working on various topics, including parser, NE, Information
Extraction and minimally supervised knowledge discovery. Recently, he
organized Workshop on Textual Entailment and Paraphrasing (ACL-07), Web
People Search task at SemEval-07 and served as guest editor on the
special issue on Named Entity. He lead a middle size NSF project for 5
years on On-Demand Information Extraction.

My homepage:


To: i-explosion-sec@xxxxxxxxx

12月13日講演会 参加申し込み


科研 特定領域「情報爆発IT基盤」事務局