Cross-lingual Approaches for Task-specific Dialogue Act Recognition.
作者： Christophe Cerisara , Ladislav Lenc , Pavel Král , Jiří Martínek
DOI:
关键词:
摘要: In this paper we exploit cross-lingual models to enable dialogue act recognition for specific tasks with a small number of annotations. We design transfer learning approach and validate it on two different target languages domains. compute turn embeddings both CNN multi-head self-attention model show that the best results are obtained by combining all sources transferred information. further demonstrate proposed methods significantly outperform related DA approaches.
arxiv.org参考文章(17)
Jana Klecková, Christophe Cerisara, Pavel Král, Combination of classifiers for automatic recognition of dialog acts conference of the international speech communication association. pp. 825- 828 ,(2005)
Iñigo López de Letona, Eduardo Lleida, José-Miguel Benedí, Antonio Miguel, Raquel Justo, María José Castro, Isabel Galiano, Amparo Varona, Design and acquisition of a telephone spontaneous speech dialogue corpus in Spanish: DIHANA. language resources and evaluation. pp. 1636- 1639 ,(2006)
Jian Sun, Xudong Cao, David Wipf, Fang Wen, Genquan Duan, A Practical Transfer Learning Algorithm for Face Verification international conference on computer vision. pp. 3208- 3215 ,(2013) , 10.1109/ICCV.2013.398
Susanne Johanna Jekat, J. Joachim Quantz, Elisabeth Maier, Alexandra Klein, Marion Mast, Ilona Maleck, Dialogue Acts in VERBMOBIL Universität Hamburg, DFKI Saarbrücken, Universität Erlangen, TU Berlin. ,(1995) , 10.22028/D291-25152
Claire Gardent, Lina M. Rojas-Barahona, Alejandra Lorenzo, Building and Exploiting a Corpus of Dialog Interactions between French Speaking Virtual and Human Agents language resources and evaluation. pp. 1428- 1435 ,(2012)
Christophe Cerisara, Ladislav Lenc, Pavel Král, On the Effects of Using word2vec Representations in Neural Networks for Dialogue Act Recognition Computer Speech & Language. ,vol. 47, pp. 175- 193 ,(2018) , 10.1016/J.CSL.2017.07.009
Kasthurirangan Gopalakrishnan, Siddhartha K. Khaitan, Alok Choudhary, Ankit Agrawal, Deep Convolutional Neural Networks with transfer learning for computer vision-based data-driven pavement distress detection Construction and Building Materials. ,vol. 157, pp. 322- 330 ,(2017) , 10.1016/J.CONBUILDMAT.2017.09.110
Rich Caruana, Multitask Learning Machine Learning - Special issue on inductive transfer archive. ,vol. 28, pp. 41- 75 ,(1997) , 10.1023/A:1007379606734
Eugénio Ribeiro, Ricardo Ribeiro, David de Matos, A Multilingual and Multidomain Study on Dialog Act Recognition Using Character-Level Tokenization Information-an International Interdisciplinary Journal. ,vol. 10, pp. 94- ,(2019) , 10.3390/INFO10030094
Tomas Mikolov, Kai Chen, Greg Corrado, Jeffrey Dean, None, Efficient Estimation of Word Representations in Vector Space arXiv: Computation and Language. ,(2013)