The Use of Predictive Annotation for Question Answering in TREC8

  title={The Use of Predictive Annotation for Question Answering in TREC8},
  author={John M. Prager and Dragomir R. Radev and Eric W. Brown and Anni Coden and Valerie Samn},
This paper introduces the technique of Predictive Annotation, a methodology for indexing texts for retrieval aimed at answering fact-seeking questions. The essence of the approach can be stated simply: index the answers. This is done by establishing about 20 classes of objects that can be identified in text by shallow parsing, and by annotating and indexing the text with these labels, which we call QATokens. Given a question, its class is identified and the question is modified accordingly to… CONTINUE READING
Highly Cited
This paper has 82 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 52 extracted citations

Conversational Bootstrapping and Other Tricks of a Concierge Robot

2017 12th ACM/IEEE International Conference on Human-Robot Interaction (HRI • 2017
View 2 Excerpts

Biomedical Question Types Classification using syntactic and rule based approach

2015 7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K) • 2015
View 1 Excerpt

82 Citations

Citations per Year
Semantic Scholar estimates that this publication has 82 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-6 of 6 references

Disambiguation of Proper Names in Text

View 5 Excerpts
Highly Influenced

“Language Reuse and Regeneration: Generating Natural Language Summaries from Multiple On-Line Sources”

Dragomir R. Radev
PhD thesis, • 1998

Identifying and Extracting Relations in Text ”

Roy Byrd, Yael Ravin

Similar Papers

Loading similar papers…