July 25, 2017, 7:49 a.m.
The Annual Meeting of the Association for Computational Linguistics is the premier conference of the field of computational linguistics, covering a broad spectrum of diverse research areas that are concerned with computational approaches to natural language.
The 55th annual meeting of the Association for Computational Linguistics (ACL) will take place in Vancouver, Canada from July 30th through August 4th, 2017. As in previous years, the program of the conference includes poster sessions, tutorials, workshops, and demonstrations in addition to the main conference.
This year our researcher frpm the University Pompeu Fabra of Barcelona (UPF) Simon Mille will take part to the event presenting two papers:
Mille, S., R. Carlini, A. Burga and L. Wanner. FORGe at SemEval-2017 Task 9: Deep sentence generation based on a sequence of graph transducers. In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), 920-923, Vancouver, Canada, August 2017. This paper is going to be presented as a contribution of the University Pompeu Fabra's NLP group to the SemEval task 9.2. The proposed generation pipeline comprises (i) a series of rule-based grpah transducers for the syntacticization of the input graphs and the resolution of morphological agreements, and 8(ii) an off-the-shelf statistical linearization component.
A. Öktem, M. Farrús, L. Wanner. Automatic extraction of parallel speech corpora from dubbed movies. Proceedings of the 10th ACL Workshop on Building and Using Comparable Corpora (BUCC), Vancouver, Canada, August 2017: this paper presents a methodology for the extraction of multimodal speech, text and prosody parallel corpora from dubbed movies, which contain large samples of conversational speech. The obtained corpus is especially useful for speech-to-speech applications and also for other research fields such as large comparative linguistic and prosodic studies.
See you in Vancouver!