Parsing and question classification for question answering
Published 1 January 2001Open access
Ulf Hermjakob
Citations150
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.
TL;DR
It is demonstrated that for this type of application, parse trees have to be semantically richer and structurally more oriented towards semantics than what most treebanks offer.
Abstract
This paper describes machine learning based parsing and question classification for question answering. We demonstrate that for this type of application, parse trees have to be semantically richer and structurally more oriented towards semantics than what most treebanks offer. We empirically show how question parsing dramatically improves when augmenting a semantically enriched Penn treebank training corpus with an additional question treebank.
Keywords
Computer Science
Building a Large Annotated Corpus of English: The Penn Treebank
7,528 Citations1993Mitchell P. Marcus
Machine LearningAn Algorithm that Learns What's in a Name
784 Citations1999Daniel M. Bikel, Richard Schwartz +1 more
IdentiFinderTM, a hidden Markov model that learns to recognize and classify names, dates, times, and numerical quantities, is evaluated and is competitive with approaches based on handcrafted rules on mixed case text and superior on text where case information is not available.
Question Answering in Webclopedia.
246 Citations2000Eduard Hovy, Laurie Gerber +3 more
The QA Typology contains 94 nodes, of which 47 are leaf nodes; each Typology node has been annotated with examples and typical patterns of expression of both Question and Answer, as indicated in Figure 3.
arXiv (Cornell University)Building a Large-Scale Knowledge Base for Machine Translation
185 Citations1994Kevin Knight, Steve K. Luk
This paper focuses on the construction of a large ontology (or knowledge base, or world model) for supporting KBMT, which contains representations for some 70,000 commonly encountered objects, processes, qualities, and relations.
Toward semantics-based answer pinpointing
182 Citations2001Eduard Hovy, Laurie Gerber +3 more
The treatment of questions (Question-Answer Typology, question parsing, and results) in the Weblcopedia question answering system are described.
Experiments with open-domain textual Question Answering
157 Citations2000Sanda M. Harabagiu, Marius Paşca +1 more
This paper describes the integration of several knowledge-based natural language processing techniques into a Question Answering system, capable of mining textual answers from large collections of texts.
A hybrid approach for named entity and sub-type tagging
118 Citations2000Rohini K. Srihari, Cheng Niu +1 more
A hybrid approach for named entity (NE) tagging which combines Maximum Entropy Model, Hidden Markov Model and handcrafted grammatical rules is presented, which results in a very high precision tagger.
The TREC-8 Question Answering Track Evaluation.
69 Citations1999Ellen M. Voorhees, Dawn M. Tice
Learning parse and translation decisions from examples with rich context
60 Citations1997Ulf Hermjakob, Raymond J. Mooney
A knowledge and context-based system for parsing and translating natural language and evaluate it on sentences from the Wall Street Journal, which relies heavily on context, as encoded in features which describe the morphological, syntactic, semantic and other aspects of a given parse state.
Edinburgh Research Archive (University of Edinburgh)Named entity extraction for speech
31 Citations2005James Horlock
The results show that it is possible to improve named entity recognition at the expense of word error rate (WER) in contrast to the general view that F -score is directly proportional to WER.
Learning parse and translation decisions from examples with rich context
20 Citations1997Ulf Hermjakob, Raymond J. Mooney
Rapid parser development: a machine learning approach for Korean
13 Citations2000Ulf Hermjakob
This paper demonstrates that machine learning is a suitable approach for rapid parser development by generating a deterministic shift-reduce parser from 1000 newly treebanked Korean sentences.