A3: Modelling the Information Density of Event Sequences in Texts
Project A3 proposes to build a model of how expected or surprising an event is within an textual description of an event sequence, and will test whether textual references to expected events differ systematically from textual references to surprising events, in a way predicted by the uniform information density hypothesis. The key resource for estimating event sequence surprisal will consist of the probabilistic script automata developed in A2. The challenge then consists of developing an incremental alignment model that maps text spans of a discourse with appropriate events in script automata. While the project will begin with the narrations from a restricted set of domains, the longer term goal is to apply the model to natural texts. The development of this model will be informed by psycholinguistic experiments carried out within the project, as well as in A1.
Frontiers in Psychology, 7 (844), 2016, ISSN: 1664-1078.
Calzolari, Nicoletta ; Choukri, Khalid ; Declerck, Thierry ; Grobelnik, Marko ; Maegaard, Bente ; Mariani, Joseph ; Moreno, Asuncion ; Odijk, Jan ; Piperidis, Stelios (Ed.): Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016), European Language Resources Association (ELRA), Portorož, Slovenia, 2016, ISBN: 978-2-9517408-9-1.
Informational status of redundant event mentions mediates pragmatic interpretation Miscellaneous
Poster presented at Events in Language and Cognition workshop at 29th CUNY Conference on Human Sentence Processing, University of Florida, March 2016, 2016.
Event Embeddings for Semantic Script Modeling Inproceedings
Proceedings of the Conference on Computational Natural Language Learning (CoNLL), Berlin, Germany, 2016.
Modeling Semantic Expectations: Using Script Knowledge for Referent Prediction Journal Article
Transactions of ACL, 2016.
Proc. of the 15th European Workshop on Natural Language Generation, Association for Computational Linguistics, Brighton, England, UK, 2015.
Learning to Predict Script Events from Domain-Specific Text Journal Article
Lexical and Computational Semantics (* SEM 2015), pp. 205, 2015.
Taming the TAME systems. Cahiers Chronos 27, pp. 161–187, Rodopi, Amsterdam/Philadelphia, 2015.
Annual Conference of the Cognitive Science Society, CogSci Mind, Technology, and Society Pasadena Convention Center, 2015.
KI - Künstliche Intelligenz, 2015, ISSN: 1610-1987.
Word Structure and Word Usage. Proceedings of the NetWordS Final Conference. Pisa, March 30-April 1, 2015, pp. 91–94, Pisa, Italy, 2015.