Attention, intentions, and the structure of discourse
Computational Linguistics
Temporal ontology and temporal reference
Computational Linguistics - Special issue on tense and aspect
Computational Linguistics - Special issue on tense and aspect
Empirical studies on the disambiguation of cue phrases
Computational Linguistics
A non-projective dependency parser
ANLC '97 Proceedings of the fifth conference on Applied natural language processing
Temporal connectives in a discourse context
EACL '93 Proceedings of the sixth conference on European chapter of the Association for Computational Linguistics
Robust temporal processing of news
ACL '00 Proceedings of the 38th Annual Meeting on Association for Computational Linguistics
From temporal expressions to temporal information: semantic tagging of news messages
TASIP '01 Proceedings of the workshop on Temporal and spatial information processing - Volume 13
Assigning time-stamps to event-clauses
TASIP '01 Proceedings of the workshop on Temporal and spatial information processing - Volume 13
Acquiring the meaning of discourse markers
ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics
Automatic fusion of knowledge stored in ontologies
Intelligent Decision Technologies - Engineering and management of IDTs for knowledge management systems
Hi-index | 0.00 |
This paper describes a machine learning approach to the identification of temporal clauses by disambiguating the subordinating conjunctions used to introduce them. Temporal clauses are regularly marked by subordinators, many of which are ambiguous, being able to introduce clauses of different semantic roles. The paper also describes our work on generating an annotated corpus of sentences embedding clauses introduced by ambiguous subordinators that might have temporal value. Each such clause is annotated as temporal or non-temporal by testing whether it answers the questions when, how often or how long with respect to the action of its superordinate clause. Using this corpus, we then train and evaluate personalised classifiers for each ambiguous subordinator, in order to set apart temporal usages. Several classifiers are evaluated, and the best performing ones achieve an average accuracy of 89.23% across the set of ambiguous connectives.