Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

14

TREC
2001

favoriteEmaildiscussreport

166views Information Technology» more TREC 2001»

NTT Question Answering System in TREC 2001

13 years 5 months ago

NTT Question Answering System in TREC 2001

Download trec.nist.gov

In this report, we describe our question-answering system SAIQA-e (System for Advanced Interactive Question Answering in English) which ran the main task of TREC-10's QA-track. Our system has two characteristics (1) named entity recognition based on support vector machines and (2) heuristic apposition detection. The MPR score of the main task is 0.228 and experimental results indicate the effectiveness of the above two steps in terms of answer extraction accuracy.

Hideto Kazawa, Hideki Isozaki, Eisaku Maeda

Real-time Traffic

Interactive Question Answering | Main Task | Named Entity Recognition | TREC 2001 | TREC 2008 |

claim paper

Related Content

» A ProtoType Question Answering System Using Syntactic and Semantic Information for Answer ...

» TREC2001 QuestionAnswer Web and Cross Language Experiments using PIRCS

» Question Answering CNLP at the TREC10 Question Answering Track

» Question Answering Using a Large NLP System

» Multilingual QuestionAnswering the DIOGENE System

» TREC10 Experiments at KAIST Batch Filtering and Question Answering

» DataIntensive Question Answering

» Finding An Answer Based on the Recognition of the Question Focus

» CL Research Experiments in TREC10 Question Answering

Post Info
More Details (n/a)

Added	31 Oct 2010
Updated	31 Oct 2010
Type	Conference
Year	2001
Where	TREC
Authors	Hideto Kazawa, Hideki Isozaki, Eisaku Maeda

Comments (0)