Answer Extraction
By Steven P. Abney, Michael Collins, Amit Singhal. 2000
155 citations recorded by the source corpus.
Information retrieval systems have typically concentrated on retrieving a set of documents which are relevant to a user's query. This paper describes a system that attempts to retrieve a much smaller section of text, namely, a direct answer to a user's question. The SMART IR system is used to extract a ranked set of passages that are relevant to the query. Entities are extracted from these passages as potential answers to the question, and ranked for plausibility according to how well their type matches the query, and according to their frequency and position in the passages. The system was evaluated at the TREC-8 question answering track: we give results and error analysis on these queries.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Michele Banko
- Eric Brill
- Marius Pasca
- Sanda M. Harabagiu
- Susan T. Dumais
- Mihai Surdeanu
- Steven J. Maiorano
- Dan I. Moldovan
Citations in the corpus
- An Analysis of the AskMSR Question-Answering System (2002, background): “The most common linguistic resources include: part-of-speech tagging, parsing, named entity extraction, semantic relations, dictionaries, WordNet, etc. (e.g., Abney et al., 2000; Chen et al. 2000; Harabagiu et al., 2000; Hovy et al., 2000; Pasca et al., 2001; Prager et al., 2000).”
- Web question answering: is more always better? (2002, unknown): “[2] S. Abney, M. Collins and A. Singhal (2000).”
- Performance Issues and Error Analysis in an Open-Domain Question Answering System (2002, methodology): “Since most QA systems consist of modules that are chained serially [Abney et al. 2000; Prager et al. 2000], the overall performance is controlled by their weakest link.”
- Open-domain textual question answering techniques (2003, methodology): “The question semantics are later used to extract the answer from text paragraphs (Abney, Collins and Singhal 2000; Radev et al .”