Developing a natural language interface to complex data
ACM Transactions on Database Systems (TODS)
An intelligent analyzer and understander of English
Communications of the ACM
Information retrieval using a transportable natural language interface
SIGIR '83 Proceedings of the 6th annual international ACM SIGIR conference on Research and development in information retrieval
Semantic interpretation against ambiguity
Semantic interpretation against ambiguity
ANLC '88 Proceedings of the second conference on Applied natural language processing
ACL '81 Proceedings of the 19th annual meeting on Association for Computational Linguistics
A general computational treatment of comparatives for natural language question answering
ACL '88 Proceedings of the 26th annual meeting on Association for Computational Linguistics
Parsing and interpreting comparatives
ACL '88 Proceedings of the 26th annual meeting on Association for Computational Linguistics
Some challenges in the design of comparative and evaluative question answering systems
KRAQ '09 Proceedings of the 2009 Workshop on Knowledge and Reasoning for Answering Questions
Grading knowledge: extracting degree information from texts
Grading knowledge: extracting degree information from texts
Comparative & Evaluative QA system in tourism domain
Proceedings of the Second International Conference on Computational Science, Engineering and Information Technology
Hi-index | 0.00 |
Comparative expressions (CEs) such as "bigger than" and "more oranges than" are highly ambiguous, and their meaning is context dependent. Thus, they pose problems for the semantic interpretation algorithms typically used in natural language database interfaces. We focus on the comparison attribute ambiguities that occur with CEs. To resolve these ambiguities our natural language interface interacts with the user, finding out which of the possible interpretations was intended. Our multi-level semantic processor facilitates this interaction by recognizing the occurrence of comparison attribute ambiguity and then calculating and presenting a list of candidate comparison attributes from which the user may choose.