Question Answering Based on Semantic Structures

The ability to answer complex questions posed in Natural Language depends on (1) the depth of the available semantic representations and (2) the inferential mechanisms they support. In this paper we describe a QA architecture where questions are analyzed and candidate answers generated by 1) identifying predicate argument structures and semantic frames from the input and 2) performing structured probabilistic inference using the extracted relations in the context of a domain and scenario model. A novel aspect of our system is a scalable and expressive representation of actions and events based on Coordinated Probabilistic Relational Models (CPRM). In this paper we report on the ability of the implemented system to perform several forms of probabilistic and temporal inferences to extract answers to complex questions. The results indicate enhanced accuracy over current state-of-the-art Q/A systems.

[1]  Sanda M. Harabagiu,et al.  Performance issues and error analysis in an open-domain question answering system , 2003, TOIS.

[2]  Sanda M. Harabagiu,et al.  Incremental Topic Representations , 2004, COLING.

[3]  Mitchell P. Marcus,et al.  Adding Semantic Annotation to the Penn TreeBank , 1998 .

[4]  Sheila A. McIlraith,et al.  Analysis and simulation of Web services , 2003, Comput. Networks.

[5]  Srini Narayanan,et al.  Putting Frames in Perspective , 2002, COLING.

[6]  Michael Collins,et al.  A New Statistical Parser Based on Bigram Lexical Dependencies , 1996, ACL.

[7]  Ellen Riloff,et al.  Automatically Generating Extraction Patterns from Untagged Text , 1996, AAAI/IAAI, Vol. 2.

[8]  Martha Palmer,et al.  Adding predicate argument structure to the Penn TreeBank , 2002 .

[9]  Richard M. Schwartz,et al.  An Algorithm that Learns What's in a Name , 1999, Machine Learning.

[10]  Daniel Gildea,et al.  The Necessity of Parsing for Predicate Argument Recognition , 2002, ACL.

[11]  G. Lakoff,et al.  Philosophy in the flesh : the embodied mind and its challenge to Western thought , 1999 .

[12]  Daniel Gildea,et al.  Automatic Labeling of Semantic Roles , 2000, ACL.

[13]  John B. Lowe,et al.  The Berkeley FrameNet Project , 1998, ACL.

[14]  Gianfranco Ciardo,et al.  A Characterization of the Stochastic Process Underlying a Stochastic Petri Net , 1994, IEEE Trans. Software Eng..

[15]  Kevin Murphy,et al.  Dynamic Bayesian Networks , 2002 .

[16]  Srinivas Narayanan,et al.  Reasoning About Actions in Narrative Understanding , 1999, IJCAI.

[17]  Sanda M. Harabagiu,et al.  Performance Issues and Error Analysis in an Open-Domain Question Answering System , 2002, ACL.

[18]  Daphne Koller,et al.  Probabilistic reasoning for complex systems , 1999 .

[19]  Lise Getoor,et al.  Learning Probabilistic Relational Models , 1999, IJCAI.

[20]  J. Pearl.  Causality: Models, Reasoning and Inference , 2000 .

[21]  Sanda M. Harabagiu,et al.  Using Predicate-Argument Structures for Information Extraction , 2003, ACL.

[22]  J. Feldman,et al.  Karma: knowledge-based active representations for metaphor and aspect , 1997 .

[23]  Sanda M. Harabagiu,et al.  COGEX: A Logic Prover for Question Answering , 2003, NAACL.

[24]  Stuart J. Russell,et al.  Dynamic bayesian networks: representation, inference and learning , 2002 .

[25]  Marti A. Hearst.  Text Tiling: Segmenting Text into Multi-paragraph Subtopic Passages , 1997, CL.

[26]  Eduard H. Hovy,et al.  The Automated Acquisition of Topic Signatures for Text Summarization , 2000, COLING.