Interpreting Natural Language using Answer Set Programming, Inconsistency Management, and Relevance Theory

Inspire project

Project Description

In the Inspire project we propose to advance the field of Natural Language Understanding (NLU) by combining techniques of Answer Set Programming, Inconsistency management, and Relevance Theory for interpreting natural language.

Natural language is a very efficient form of communication: humans leave out many details when they use language because other humans can easily fill these details. As an example, ‘morning coffee’ means ‘coffee drunk in the morning’ while ‘morning newspaper’ means ‘newspaper read in the morning’, and humans understand that without effort although neither ‘drunk’ nor ‘read’ is visible in the text. This underspecification, often combined with a high ambiguity of natural language, is a big challenge for NLU systems. The Inspire project aims to advance scientific methods that allow computers to interpret natural language text with the goal of recovering its intended meaning.

An existing approach in that direction is the usage of background knowledge bases (WordNet, FrameNet) together with abductive reasoning. The idea of abduction is to find the best explanation for a given observed text input. In this project we want to build an improved NLU formalism based on Answer Set Programming (ASP).

ASP is a general purpose logic programming formalism that supports comfortable representation of knowledge and nonmonotonic reasoning (such as abduction). In an ASP program we describe a set of potential solutions and relationships/constraints between concepts. Based on such a representation, an ASP solver (a software tool) computes solutions that respect all specified relationships and constraints. ASP can handle circular knowledge without problems and allows for an efficient integration of external knowledge such as WordNet and FrameNet.

To deal with inconsistencies of WordNet and FrameNet, we plan to use Inconsistency Management techniques and we want to apply principles from Relevance Theory for selecting the best interpretation of a given text.

Project Team:

Project Outcomes:

J  Journal Article  C  Conference Paper  E  Editorship  O  Other  

Publications 2018:

J  and . Best-Effort Inductive Logic Programming via Fine-grained Cost-based Hypothesis Generation. Machine Learning 107 (7), pages 1141-1169, , DOI: 10.1007/s10994-018-5708-2. [  ]

J . Answer Set Programming applied to Coreference Resolution and Semantic Similarity. KI - Künstliche Intelligenz 32 (2), pages 207-208, , DOI: 10.1007/s13218-018-0539-7. [  ]

J . Adjudication of Coreference Annotations via Answer Set Optimization. Journal of Experimental & Theoretical Artificial Intelligence 30 (4), pages 525-546, , DOI: 10.1080/0952813X.2018.1456793. [  ]

Publications 2017:

J , , , and . Constraints, Lazy Constraints, or Propagators in ASP Solving: An Empirical Analysis. Theory and Practice of Logic Programming 17 (5-6), pages 780-799, , Presented at ICLP 2017, DOI: 10.1017/S1471068417000254. [  ] [  ]

C , , , , and . Answer Set Programming with External Sources. In: Reasoning Web International Summer School 10370 LNCS, pages 204-275, , DOI: 10.1007/978-3-319-61033-7_7. [  ]

C . Adjudication of Coreference Annotations via Answer Set Optimization. In: Logic Programming and Nonmonotonic Reasoning (LPNMR), volume 10377 of Lecture Notes in Computer Science, pages 343-357, , Best Application Paper, DOI: 10.1007/978-3-319-61660-5_31.

O . Learning Logic Rules from Text using Statistical Methods for Natural Lan guage Processing. PhD Thesis, Sabanci University, . [  ]

J , , and . Improving Scalability of Inductive Logic Programming via Pruning and Best-Effort Optimisation. Expert Systems With Applications 87, pages 291-303, , DOI: 10.1016/j.eswa.2017.06.013. [  ] [  ]

J , , and . Applications of Non-monotonic Reasoning to Automotive Product Configuration using Answer Set Programming. Journal of Intelligent Manufacturing, , DOI: 10.1007/s10845-017-1333-3. [  ] [  ]

O . Inspire at Inductive Logic Programming Competition: Fine-grained Cost-based Hypothesis Generation. , Short technical note. [  ]

Publications 2016:

J . Modeling Variations of First-Order Horn Abduction in Answer Set Programming. Fundamenta Informaticae 149 (1-2), pages 159-207, , Available as arXiv:1512.08899 [cs.AI], DOI: 10.3233/FI-2016-1446. [  ] [  ]

C , , and . External Propagators in WASP: Preliminary Report. In: International Workshop on Experimental Evaluation of Algorithms for Solving Problems with Combinatorial Explosion (RCRA), volume 1745 of CEUR Workshop Proceedings, pages 1-9, . [  ]

C , , and . ASP for Abduction in Natural Language Understanding made more efficient using External Propagators. In: Proceedings of the 8th International Workshop on Logic Programming with Constraints for Language Processing (CSLP), pages 19-21, . [  ] [  ]

C  and . Inspire at SemEval 2016 Task 2: Interpretable Semantic Textual Similarity Alignment based on Answer Set Programming. In: Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval 2016), pages 1109-1115, . [  ]

C , , , , and . SteM at SemEval-2016 Task 4A: Applying Active Learning to Improve Sentiment Classification. In: Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval 2016), pages 64-70, . [  ]

Publications 2015:

O . Modeling Variations of First-Order Horn Abduction in Answer Set Programming. Technical Report, Computer Engineering Department, Faculty of Engineering, Marmara University, , arXiv:1512.08899 [cs.AI]. [  ]

C . Modeling Abduction over Acyclic First-Order Logic Horn Theories in Answer Set Programming: Preliminary Experiments. In: International Workshop on Experimental Evaluation of Algorithms for Solving Problems with Combinatorial Explosion (RCRA), volume 1451 of CEUR Workshop Proceedings, pages 76-90, . [  ]

C  and . Using Semantic Web Resources for Solving Winograd Schemas: Sculptures, Shelves, Envy, and Success. In: Posters&Demos@SEMANTiCS 2015 and DSci15 Workshop, volume 1481 of CEUR Workshop Proceedings, pages 22-25, . [  ]

C , , and . On Structural Analysis of Non-Ground Answer-Set Programs. In: International Conference on Logic Programming (ICLP), Technical Communications, volume 1433 of CEUR Workshop Proceedings, . [  ]

Impressum: Medieninhaber Peter Schüller (Privatperson), Fasangartengasse 57 1130 Wien AUSTRIA. Email: Telefon: +43(0)69910963525