Using Wikipedia at the TREC QA Track
Published 1 January 2005Open access
D.D. Ahn, V. Jijkoun, Gilad Mishne, Karin Müller, Maarten de Rijke, Stefan Schlobach
Citations93
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
Abstract
Copyright It is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or copyright holder(s), other than for strictly personal, individual use, unless the work is under an open content licence (like
Keywords
Computer ScienceSocial Sciences
Natural Language EngineeringDiscovery of inference rules for question-answering
532 Citations2001Dekang Lin, Patrick Pantel
This paper presents an unsupervised algorithm for discovering inference rules from text based on an extended version of Harris’ Distributional Hypothesis, which states that words that occurred in the same contexts tend to be similar.
Combining document representations for known-item search
237 Citations2003Paul Ogilvie, Jamie Callan
This paper investigates the pre-conditions for successful combination of document representations formed from structural markup for the task of known-item search, and presents a mixture-based language model to investigate several hypotheses.
MURAX
141 Citations1993Julian Kupiec
The methods hypothesize noun phrases that are likely to be the answer, and present the user with relevant text in which they are marked, focussing the user's attention appropriately, illustrated in a broad domain: answering general-knowledge questions using an on-line encyclopedia.
Information extraction for question answering
67 Citations2004Valentin Jijkoun, Maarten de Rijke +1 more
It is shown that the recall of the extraction component can be improved using syntactic parsing instead of more common surface text patterns, substantially increasing the number of factoid questions answered by the QA system.
Lecture notes in computer scienceAnswer Selection in a Multi-stream Open Domain Question Answering System
39 Citations2004Valentin Jijkoun, Maarten de Rijke
The main finding is that redundancy-based ideas in combination with naively learned stream weights conditioned on question type work best, and improve significantly over a number of baselines.
Data Archiving and Networked Services (DANS)The university of Amsterdam at QA@CLEF 2005
31 Citations2005Valentin Jijkoun, Gilad Mishne +1 more
European Conference on Artificial IntelligenceType checking in open-domain question answering
30 Citations2004Stefan Schlobach, Marius Olsthoorn +1 more
This work compares two kinds of strategies for answer type checking for open domain QA, one is redundancy-based and builds on the intuition that the amount of implicit knowledge which connects an answer to a question can be estimated by exploiting the redundancy of information available on the web, and the other is knowledge-intensive.
Language Models for Searching in Web Corpora
25 Citations2005Jaap Kamps, Gilad Mishne +1 more
The University of Amsterdam at the TREC 2003 Question Answering Track
23 Citations2003V. Jijkoun, Gilad Mishne +4 more
The ideas underlying the approaches to the TREC 2003 Question Answering track are explained, the results are reported on, and an error analysis is provided.
The Use of Sentence Similarity as a Semantic Relevance Metric for Question Answering.
22 Citations2003Marco De Boni, Suresh Manandhar
An algorithm for calculating semantic similarity between sentences using a variety of linguistic information is presented and applied to the problem of Question Answering and is shown to be useful in determining possible answers to a question.
Lecture notes in computer scienceHow Frogs Built the Berlin Wall
10 Citations2004Valentin Jijkoun, Gilad Mishne +1 more