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

Enrique Alfonseca; Marco De Boni; José-Luis Jara-Valencia; Suresh Manandhar

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

Enrique Alfonseca, Marco De Boni, José-Luis Jara-Valencia, Suresh Manandhar

Computer Science

Research output: Contribution to conference › Paper › peer-review

Abstract

Introduction This was our first entry at TREC and the system we presented was, due to time constraints, an incomplete prototype. Our main aims were to verify the usefulness of syntactic analysis for QA and to experiment with different semantic distance metrics in view of a more complete and fully integrated future system. To this end we made use of a part-of-speech tagger and NP chunker in conjunction with entity recognition and semantic distance metrics. We also envisaged experimenting with a shallow best first parser but time factors meant integration with the rest of the system was not achieved. Unfortunately due to time constraints no testing and no parameter tuning was carried out prior TREC. This in turn meant that a number of small bugs negatively influenced our results. Moreover it was not possible to carry out experiments in parameter tuning, meaning our system did not achieve optimal performance.

Original language	Undefined/Unknown
Publication status	Published - 2001

Access to Document

Cite this

@conference{6470030a194042d4a5c7f0e26d8da8d4,

title = "A ProtoType Question Answering System Using Syntactic and Semantic Information for Answer Retrieval",

abstract = "Introduction This was our first entry at TREC and the system we presented was, due to time constraints, an incomplete prototype. Our main aims were to verify the usefulness of syntactic analysis for QA and to experiment with different semantic distance metrics in view of a more complete and fully integrated future system. To this end we made use of a part-of-speech tagger and NP chunker in conjunction with entity recognition and semantic distance metrics. We also envisaged experimenting with a shallow best first parser but time factors meant integration with the rest of the system was not achieved. Unfortunately due to time constraints no testing and no parameter tuning was carried out prior TREC. This in turn meant that a number of small bugs negatively influenced our results. Moreover it was not possible to carry out experiments in parameter tuning, meaning our system did not achieve optimal performance. ",

author = "Enrique Alfonseca and Boni, {Marco De} and Jos{\'e}-Luis Jara-Valencia and Suresh Manandhar",

year = "2001",

language = "Undefined/Unknown",

}

TY - CONF

T1 - A ProtoType Question Answering System Using Syntactic and Semantic Information for Answer Retrieval

AU - Alfonseca, Enrique

AU - Boni, Marco De

AU - Jara-Valencia, José-Luis

AU - Manandhar, Suresh

PY - 2001

Y1 - 2001

N2 - Introduction This was our first entry at TREC and the system we presented was, due to time constraints, an incomplete prototype. Our main aims were to verify the usefulness of syntactic analysis for QA and to experiment with different semantic distance metrics in view of a more complete and fully integrated future system. To this end we made use of a part-of-speech tagger and NP chunker in conjunction with entity recognition and semantic distance metrics. We also envisaged experimenting with a shallow best first parser but time factors meant integration with the rest of the system was not achieved. Unfortunately due to time constraints no testing and no parameter tuning was carried out prior TREC. This in turn meant that a number of small bugs negatively influenced our results. Moreover it was not possible to carry out experiments in parameter tuning, meaning our system did not achieve optimal performance.

AB - Introduction This was our first entry at TREC and the system we presented was, due to time constraints, an incomplete prototype. Our main aims were to verify the usefulness of syntactic analysis for QA and to experiment with different semantic distance metrics in view of a more complete and fully integrated future system. To this end we made use of a part-of-speech tagger and NP chunker in conjunction with entity recognition and semantic distance metrics. We also envisaged experimenting with a shallow best first parser but time factors meant integration with the rest of the system was not achieved. Unfortunately due to time constraints no testing and no parameter tuning was carried out prior TREC. This in turn meant that a number of small bugs negatively influenced our results. Moreover it was not possible to carry out experiments in parameter tuning, meaning our system did not achieve optimal performance.

M3 - Paper

ER -