Abstract
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[a1][c7]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) PDF

I will also give a brief talk about Ngram Search Engine and the Web People Search (WePS). Ngram search engine is a tool to search ngrams which match user's ngram query which can include arbitrary wildcards in a tenth of a second. It is a useful tool for semantic knowledge discovery. WePS is a task to disambiguate search results of people name. At the first evaluation at SemEval-2007, 16 groups have participated. We are preparing the second evaluation which includes people's attribution extraction task.