Implementation of a slogan generator

Tomašič, P., Žnidaršič, M., & Papa, G.. (2014). Implementation of a slogan generator. The Fifth International Conference on Computational Creativity, ICCC 2014. presented at the 2014, Ljubljana, Slovenia. Retrieved from http://kt.ijs.si/publ/iccc_2014_proceedings.pdf

Automated slogan production using a genetic algorithm

Tomašič, P., Papa, G., & Žnidaršič, M.. (2014). Automated slogan production using a genetic algorithm. Student Workshop on Bioinspired Optimization Methods and their Applications - BIOMA 2014. presented at the 2014, Ljubljana, Slovenia. Retrieved from http://bioma.ijs.si/conference/2014/BIOMA%202014%20Proceedings.pdf

Probabilistic Type Theory for Incremental Dialogue Processing

Hough, J., & Purver, M.. (2014). Probabilistic Type Theory for Incremental Dialogue Processing. EACL 2014 Workshop on Type Theory and Natural Language Semantics (TTNLS). presented at the 2014, Gothenburg, Sweden: Association for Computational Linguistics. Retrieved from http://www.aclweb.org/anthology/W14-1410

Strongly Incremental Repair Detection

Hough, J., & Purver, M.. (2014). Strongly Incremental Repair Detection. 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). presented at the to appear, Doha, Qatar: Association for Computational Linguistics. Retrieved from http://arxiv.org/abs/1408.6788

We present STIR (STrongly Incremental Repair detection), a system that detects speech repairs and edit terms on transcripts incrementally with minimal latency. STIR uses information-theoretic measures from n-gram models as its principal decision features in a pipeline of classifiers detecting the different stages of repairs. Results on the Switchboard disfluency tagged corpus show utterance-final accuracy on a par with state-of-the-art incremental repair detection methods, but with better incremental accuracy, faster time-to-detection and less computational overhead.

Document summarization based on word associations

Gross, O., Doucet, A., & Toivonen, H.. (2014). Document summarization based on word associations. 37th international ACM SIGIR conference on Research & development in information retrieval (SIGIR '14). NY, USA: ACM. doi:10.1145/2600428.2609500

Pages

Subscribe to ConCreTe RSS