| |
| My
Previous Research |
| |
Projects |
|
Academic Activities
|
|
Refereed Papers |
|
Non-Refereed Papers |
|
Misc |
|
| Projects |
| -
Question Answering |
| |
Question
answering is a promising area of information
retrieval, which takes a step closer to information
retrieval rather than document retrieval.
A typical question answering system takes
the user's questions in natural language,
and returns the concise answers to it. For
instance, return "Paris" for the
question "what is the capital of France?".
Thus, the users do not have to look for the
answers in the returned documents. |
| |
Demo:
Web-based
NSIR |
| |
| -
Web Mining |
| |
The
Web overwhelms us with immense amounts of interconnected,
rich, and dynamic hypertext information. However,
the information on the Web is not stored in
any systematically structured way, posing great
challenges to those who seeks the demanded information
buried in billions of Web pages. Web mining
is the research area to find significant statistical
patterns relating hypertext documents, hyperlinks,
topics, and queries and using these patterns
to connect users to information they seek. |
| |
Bibliography [bib; html sorted by author; html in reverse chronological order] |
| |
| -
Information Retrieval on XML data |
| |
Information
retrieval and database systems have followed
two quite seperated paths. Unlike the field
of database systems, which has focused on structured
data and structured query, a typical information
retrieval system is to locate relevant documents
based on user input such as keyword-based queries.
This project takes a step to integrate these
two fields: to handle keyword-based queries
on semi-structured XML corpus. |
| |
| -
Automatic Text Summarization |
| |
Text
summarization is the process of identifying
salient concepts in text narrative, conceptualizing
the relationships that exist among them and
generating concise representations of the input
text that preserve the gist of its content.
According to the size of the input, one distinguishes
between single-document summarizers (SDS) and
multi-document summarizers (MDS). |
| |
| ACADEMIC
ACTIVITIES |
| -
Participated in the Text
Retrieval Conference (TREC) 2003 Question
Answering Track Passage Task. August, 2003. |
| -
Attended The
26th Annual International ACM SIGIR Conference
in Toronto, Canada. July, 2003 |
| -
Participated in the Document
Understanding Conferences (DUC) 2003. February,
2003 |
| -
Participated in the Text
Retrieval Conference (TREC) 2002 Question
Answering Track. August, 2002. |
| -
Participated in the 8-week summer workshop
on Automatic Summarization of Multiple (Multilingual)
Documents. The
Center for Language and Speech Processing.
Johns Hopkins University.
June-August, 2001 |
| |
| REFEREED
PAPERS |
| -
Dragomir R. Radev, Simone Teufel, Horacio Saggion,
Wai Lam, John Blitzer, Hong Qi, Arda Celebi,
Danyu Liu, Elliott Drabek. Evaluation challenges
in large-scale multi-document summarization.
To appear in The 41st Annual Meeting of the
Association for Computational Linguistics (ACL),
Sapporo, Japan, July, 2003. |
| -
Dragomir R. Radev, Weiguo Fan, Hong Qi, Harris
Wu, and Amardeep Grewal. Probabilistic Question
Answering from the Web. In The 11th International
World Wide Web Conference, Honolulu, Hawaii,
May 2002. [pdf]
|
| -
Dragomir R. Radev, Hong Qi, Zhiping Zheng, Sasha
Blair-Goldensohn, Zhu Zhang, Waiguo Fan, and
John Prager. Mining the web for answers to natural
language questions. In ACM CIKM 2001: Tenth
International Conference on Information and
Knowledge Management, Atlanta, GA, 2001. [pdf] |
| |
| NON-REFEREED
PAPERS |
| -
Dragomir R. Radev, Jahna Otterbacher, Hong Qi,
and Daniel Tam. MEAD ReDUCs: Michigan at DUC
2003. To be appear in Document Understanding
Conferences (DUC) 2003 Text Summarization Workshop,
June, 2003. |
| -
Hong Qi, Jahna Otterbacher, Adam Winkel, and
Dragomir R. Radev. The University of Michigan
at TREC2002: Question Answering and Novelty
Tracks. In The 11th Text REtrieval Conference,
Gaithersburg, MD, November 2002. |
| -
Cong Yu, Hong Qi, H. V. Jagadish. Integration
of IR into an XML Database. First Annual Workshop
of the Initiative for the Evaluation of XML
Retrieval (INEX), Schloss Dagstuhl, Wadern,
Germany. 2002. |
| |
| MISC |
| -
Cong Yu, H.V. Jagadish, D. R. Radev. Querying
XML Using Structures and Keywords in Timber.
Presented by Hong Qi. In Demo section at the
26th Annual International ACM SIGIR Conference
on Research and Development in Information Retrieval.
Toronto, Canada, July 2003. |
| -
Dragomir Radev, Adam Winkel, and Hong Qi. Hypergraph
based content transfer for information retrieval
and question answering. Presentations in Second
Workshop on Algorithms and Models for the Web-Graph
(WAW 2003), Budapest, Hungary, May 2003. |
| -
Hong Qi. Introduction to Natural Language Processing.
Invited talk for the Medical School at the University
of Michigan. November 2002. |
| - Dragomir
R. Radev, Hong Qi, Harris Wu, and Weiguo Fan.
Evaluating Web-based Question Answering Systems.
In Demo section, LREC 2002, Las Palmas, Spain,
June 2002. |
| |
|
| |