An Anytime Algorithm for Interpreting Arguments

The problem of interpreting Natural Language (NL) discourse is generally of exponential complexity. However, since interactions with users must be conducted in real time, an exhaustive search is not a practical option. In this paper, we present an anytime algorithm that generates "good enough" interpretations of probabilistic NL arguments in the context of a Bayesian network (BN). These interpretations consist of: BN nodes that match the sentences in a given argument, assumptions that justify the beliefs in the argument, and a reasoning structure that adds detail to the argument. We evaluated our algorithm using automatically generated arguments and hand-generated arguments. In both cases, our algorithm generated good interpretations (and often the best interpretation) in real time.

[1]  Ingrid Zukerman,et al.  A Probabilistic Approach for Argument Interpretation , 2004, User Modeling and User-Adapted Interaction.

[2]  Ingrid Zukerman,et al.  Generation and selection of likely interpretations during plan recognition in task-oriented consultation systems , 1991, User Modeling and User-Adapted Interaction.

[3]  Rolf Haenni.  Anytime argumentative and abductive reasoning , 2003, Soft Comput..

[4]  Mark S. Boddy,et al.  An Analysis of Time-Dependent Planning , 1988, AAAI.

[5]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[6]  Lynn Lambert,et al.  A Process Model for Recognizing Communicative Acts and Modeling Negotiation Subdialogues , 1999, Comput. Linguistics.

[7]  Elmar Nöth,et al.  Empowering knowledge based speech understanding through statistics , 1998, ICSLP.

[8]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems , 1988 .

[9]  Swaminathan Natarajan.  Imprecise and Approximate Computation , 1995 .

[10]  Shlomo Zilberstein,et al.  Approximate Reasoning Using Anytime Algorithms , 1995 .

[11]  Eric Horvitz,et al.  Bounded Conditioning: Flexible Inference for Decisions under Scarce Resources , 2013, UAI 1989.

[12]  Ingrid Zukerman,et al.  Lexical Paraphrasing for Document Retrieval and Node Identification , 2003, IWP@ACL.

[13]  Michael McGill,et al.  Introduction to Modern Information Retrieval , 1983 .

[14]  Kristiina Jokinen,et al.  Confidence-Based Adaptivity in Response Generation for a Spoken Dialogue System , 2001, SIGDIAL Workshop.