• Publications
  • Influence
COGEX: A Logic Prover for Question Answering
TLDR
This paper introduces the idea of automated reasoning applied to question answering and shows the feasibility of integrating a logic prover into a Question Answering system. Expand
  • 198
  • 18
  • PDF
Text and Knowledge Mining for Coreference Resolution
TLDR
We present a knowledge minimalist methodology of mining coreference rules from annotated text corpora using a meta-bootstrapping algorithm. Expand
  • 107
  • 11
  • PDF
Experiments with Open-Domain Textual Question Answering
TLDR
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. Expand
  • 188
  • 4
  • PDF
Multilingual Coreference Resolution
TLDR
In this paper we present a new multilingual data-driven method for coreference resolution as implemented in the SWIZZLE system. Expand
  • 54
  • 2
  • PDF
Intentions, Implicatures and Processing of Complex Questions
TLDR
We show that both the intentional structure and the implicatures enabled by it are essential components of Q/A systems capable of successfully processing complex questions. Expand
  • 7
  • 2
  • PDF
Acquisition of Linguistic Patterns for Knowledge-based Information Extraction
TLDR
In this paper we present a new method of automatic acquisition of linguistic patterns for Information Extraction, as implemented in the CICERO system. Expand
  • 81
  • 1
  • PDF
Open-domain textual question answering techniques
TLDR
Textual question answering is a technique of extracting a sentence or text snippet from a document or document collection that responds directly to a query. Expand
  • 81
  • 1
  • PDF
Knowledge-Lean Coreference Resolution and its Relation to Textual Cohesion and Coherence
TLDR
We present a new empirical method for coreference resolution, implemented in the COCKTAIL system. Expand
  • 32
  • 1
  • PDF
Multi-Document Summaries Based on Semantic Redundancy
TLDR
This paper presents a technique for producing short summaries from multiple documents using conceptual representations of redundant semantic information, called topic semantic signatures. Expand
  • 3
  • 1
  • PDF
Finding Answers in Large Collections of Texts: Paragraph Indexing W Abductive Inference
TLDR
This paper describes a methodology of answering questions by using information retrieved from very large collections of texts. Expand
  • 31
...
1
2
3
...