BibSonomy :: publication ::

tag user group author concept BibTeX key search:all search:diego_ma

The blue social bookmark and publication sharing system.

entry of diego_ma:

(0)

This publication has not been reviewed yet.

rating distribution

average user rating

The average rating is computed over all reviews. However, some of them may be invisible to you due to the visibility setting chosen by the reviewers.

(0.0 of 5.0 based on 0 reviews)

How to Select an Answer String?

by: Abdessamad Echihabi, Ulf Hermjakob, Eduard Hovy, Daniel Marcu, Eric Melz, and Deepak Ravichandran

In: Advances in Textual Question AnsweringKluwer (2004) .

Resources (URL, PDF, PS...)

URL:	http://www.isi.edu/~marcu/papers.html

Given a question Q and a sentence/paragraph SP that is likely to contain the answer to Q, an answer selection module is supposed to select the ``exact'' answer sub-string A $\subset$ SP. We study three distinct approaches to solving this problem: one approach uses algorithms that rely on rich knowledge bases and sophisticated syntactic/semantic processing; one approach uses patterns that are learned in an unsupervised manner from the web, using computational biology-inspired alignment algorithms; and one approach uses statistical noisy-channel algorithms similar to those used in machine translation. We assess the strengths and weaknesses of these three approaches and show how they can be combined using a maximum entropy-based framework.

BibTeX record

@incollection{Echihabi:2004,
  abstract = {Given a question Q and a sentence/paragraph SP that is likely to contain the answer to Q, an answer selection module is supposed to select the ``exact'' answer sub-string A $\subset$ SP. We study three distinct approaches to solving this problem: one approach uses algorithms that rely on rich knowledge bases and sophisticated syntactic/semantic processing; one approach uses patterns that are learned in an unsupervised manner from the web, using computational biology-inspired alignment algorithms; and one approach uses statistical noisy-channel algorithms similar to those used in machine translation. We assess the strengths and weaknesses of these three approaches and show how they can be combined using a maximum entropy-based framework.},
  added-at = {2007-12-14T02:38:27.000+0100},
  author = {Echihabi, Abdessamad and Hermjakob, Ulf and Hovy, Eduard and Marcu, Daniel and Melz, Eric and Ravichandran, Deepak},
  biburl = {http://www.bibsonomy.org/bibtex/2380b4b132d8f3219a5a9c6a471dadc14/diego_ma},
  booktitle = {Advances in Textual Question Answering},
  editor = {Strzalkowski, Tomek and Harabagiu, Sanda},
  interhash = {357637401d8b20434d895c170126c737},
  intrahash = {380b4b132d8f3219a5a9c6a471dadc14},
  keywords = {answer_extraction},
  publisher = {Kluwer},
  timestamp = {2007-12-14T02:38:27.000+0100},
  title = {How to Select an Answer String?},
  url = {http://www.isi.edu/~marcu/papers.html},
  year = 2004
}

Endnote record

%0 Book Section
%1 Echihabi:2004
%A Echihabi, Abdessamad
%A Hermjakob, Ulf
%A Hovy, Eduard
%A Marcu, Daniel
%A Melz, Eric
%A Ravichandran, Deepak
%B Advances in Textual Question Answering
%D 2004
%E Strzalkowski, Tomek
%E Harabagiu, Sanda
%I Kluwer
%K 
%T How to Select an Answer String?
%U http://www.isi.edu/~marcu/papers.html
%X Given a question Q and a sentence/paragraph SP that is likely to contain the answer to Q, an answer selection module is supposed to select the ``exact'' answer sub-string A $\subset$ SP. We study three distinct approaches to solving this problem: one approach uses algorithms that rely on rich knowledge bases and sophisticated syntactic/semantic processing; one approach uses patterns that are learned in an unsupervised manner from the web, using computational biology-inspired alignment algorithms; and one approach uses statistical noisy-channel algorithms similar to those used in machine translation. We assess the strengths and weaknesses of these three approaches and show how they can be combined using a maximum entropy-based framework.

BibSonomy :: publication ::

How to Select an Answer String?

Resources (URL, PDF, PS...)

Abstract

BibTeX record

Endnote record