A New, Fully Automatic Version of Mitkov's Knowledge-Poor Pronoun Resolution Method
CICLing '02 Proceedings of the Third International Conference on Computational Linguistics and Intelligent Text Processing
Discovery of inference rules for question-answering
Natural Language Engineering
A maximum entropy approach to identifying sentence boundaries
ANLC '97 Proceedings of the fifth conference on Applied natural language processing
Automatic retrieval and clustering of similar words
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 2
Semantic inference at the lexical-syntactic level
AAAI'07 Proceedings of the 22nd national conference on Artificial intelligence - Volume 1
Inference rules and their application to recognizing textual entailment
EACL '09 Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics
Inferring textual entailment with a probabilistically sound calculus*
Natural Language Engineering
Extracting paraphrase patterns from bilingual parallel corpora
Natural Language Engineering
Inference rules for recognizing textual entailment
IWCS-8 '09 Proceedings of the Eighth International Conference on Computational Semantics
Natural language as the basis for meaning representation and inference
CICLing'08 Proceedings of the 9th international conference on Computational linguistics and intelligent text processing
Terminological paraphrase extraction from scientific literature based on predicate argument tuples
Journal of Information Science
Semantic annotation for textual entailment recognition
MICAI'12 Proceedings of the 11th Mexican international conference on Advances in Computational Intelligence - Volume Part II
Hi-index | 0.00 |
We present a new framework for textual entailment, which provides a modular integration between knowledge-based exact inference and cost-based approximate matching. Diverse types of knowledge are uniformly represented as entailment rules, which were acquired both manually and automatically. Our proof system operates directly on parse trees, and infers new trees by applying entailment rules, aiming to strictly generate the target hypothesis from the source text. In order to cope with inevitable knowledge gaps, a cost function is used to measure the remaining "distance" from the hypothesis.