TEAM: an experiment in the design of transportable natural-language interfaces
Artificial Intelligence
Extending the lexicon by exploiting subregularities
HLT '90 Proceedings of the workshop on Speech and Natural Language
Explanation-Based Generalization: A Unifying View
Machine Learning
Explanation-Based Learning: An Alternative View
Machine Learning
Lexical acquisition in the Core Language Engine
EACL '89 Proceedings of the fourth conference on European chapter of the Association for Computational Linguistics
ACL '87 Proceedings of the 25th annual meeting on Association for Computational Linguistics
Towards a self-extending lexicon
ACL '85 Proceedings of the 23rd annual meeting on Association for Computational Linguistics
Translation by Quasi Logical Form transfer
ACL '91 Proceedings of the 29th annual meeting on Association for Computational Linguistics
Logical Forms in the core language engine
ACL '89 Proceedings of the 27th annual meeting on Association for Computational Linguistics
Acquisition of lexical information: from a large textual Italian corpus
COLING '90 Proceedings of the 13th conference on Computational linguistics - Volume 3
Towards the automatic acquisition of lexical data
COLING '86 Proceedings of the 11th coference on Computational linguistics
Using a logic grammar to learn a lexicon
COLING '88 Proceedings of the 12th conference on Computational linguistics - Volume 2
An empirical study on thematic knowledge acquisition based on syntactic clues and heuristics
ACL '93 Proceedings of the 31st annual meeting on Association for Computational Linguistics
Incorporating linguistics constraints into inductive logic programming
ConLL '00 Proceedings of the 2nd workshop on Learning language in logic and the 4th conference on Computational natural language learning - Volume 7
Hi-index | 0.00 |
A method for automatic lexical acquisition is outlined. An existing lexicon that, in addition to ordinary lexical entries, contains prototypical entries for various non-exclusive paradigms of open-class words, is extended by inferring new lexical entries from texts containing unknown words. This is done by comparing the constraints placed on the unknown words by the natural language system's grammar with the prototypes and a number of hand-coded phrase templates specific for each paradigm. Once a sufficient number of observations of the word in different contexts have been made, a lexical entry is constructed for the word by assigning it to one or several paradigm(s).Parsing sentences with unknown words is normally very time-consuming due to the large number of grammatically possible analyses. To circumvent this problem, other phrase templates are extracted automatically from the grammar and domain-specific texts using an explanation-based learning method. These templates represent grammatically correct sentence patterns. When a sentence matches a template, the original parsing component can be bypassed, reducing parsing times dramatically.