Filters








6 Hits in 2.4 sec

XL-NBT: A Cross-lingual Neural Belief Tracking Framework [article]

Wenhu Chen, Jianshu Chen, Yu Su, Xin Wang, Dong Yu, Xifeng Yan and William Yang Wang
2018 arXiv   pre-print
In order to bypass the expensive human annotation and achieve the first step towards the ultimate goal of building a universal dialog system, we set out to build a cross-lingual state tracking framework  ...  Specifically, we assume that there exists a source language with dialog belief tracking annotations while the target languages have no annotated dialog data of any form.  ...  We are also very thankful for the public belief tracking code and multilingual state-tracking datasets released by Nikola Mrksic from the University of Cambridge.  ... 
arXiv:1808.06244v2 fatcat:ousmc2ltlndrvjyx73l6rbpdva

XL-NBT: A Cross-lingual Neural Belief Tracking Framework

Wenhu Chen, Jianshu Chen, Yu Su, Xin Wang, Dong Yu, Xifeng Yan, William Yang Wang
2018 Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing  
In order to bypass the expensive human annotation and achieve the first step towards the ultimate goal of building a universal dialog system, we set out to build a cross-lingual state tracking framework  ...  Specifically, we assume that there exists a source language with dialog belief tracking annotations while the target languages have no annotated dialog data of any form.  ...  We are also very thankful for the public belief tracking code and multilingual state-tracking datasets released by Nikola Mrksic from the University of Cambridge.  ... 
doi:10.18653/v1/d18-1038 dblp:conf/emnlp/ChenCSWYYW18 fatcat:6r6bo2ezbbe5hjymr7aos3igu4

Attention-Informed Mixed-Language Training for Zero-Shot Cross-Lingual Task-Oriented Dialogue Systems

Zihan Liu, Genta Indra Winata, Zhaojiang Lin, Peng Xu, Pascale Fung
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Finally, with very few word pairs, our model achieves significant zero-shot adaptation performance improvements in both cross-lingual dialogue state tracking and natural language understanding (i.e., intent  ...  In order to circumvent the expensive and time-consuming data collection, we introduce Attention-Informed Mixed-Language Training (MLT), a novel zero-shot adaptation method for cross-lingual task-oriented  ...  Chen et al. (2018) proposed a teacher-student framework for cross-lingual neural belief tracking (i.e., dialogue state tracking) by leveraging a bilingual corpus or bilingual dictionary.  ... 
doi:10.1609/aaai.v34i05.6362 fatcat:h322k7c6zfa5rnfy2g5vnxs2pe

Attention-Informed Mixed-Language Training for Zero-shot Cross-lingual Task-oriented Dialogue Systems [article]

Zihan Liu, Genta Indra Winata, Zhaojiang Lin, Peng Xu, Pascale Fung
2019 arXiv   pre-print
Finally, with very few word pairs, our model achieves significant zero-shot adaptation performance improvements in both cross-lingual dialogue state tracking and natural language understanding (i.e., intent  ...  In order to circumvent the expensive and time-consuming data collection, we introduce Attention-Informed Mixed-Language Training (MLT), a novel zero-shot adaptation method for cross-lingual task-oriented  ...  Chen et al. (2018) proposed a teacher-student framework for cross-lingual neural belief tracking (i.e., dialogue state tracking) by leveraging a bilingual corpus or bilingual dictionary.  ... 
arXiv:1911.09273v1 fatcat:bazx4femujbntnwgb4j6bjmfxm

Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systems [article]

Evgeniia Razumovskaia, Goran Glavaš, Olga Majewska, Edoardo M. Ponti, Anna Korhonen, Ivan Vulić
2022 arXiv   pre-print
Hence, state-of-the-art approaches to multilingual ToD mostly rely on (zero- or few-shot) cross-lingual transfer from resource-rich languages (almost exclusively English), either by means of machine translation  ...  In task-oriented dialogue (ToD), a user holds a conversation with an artificial agent to complete a concrete task.  ...  The Neural Belief Tracker (NBT; ) is a DST model that updates its internal representation of the state of a conversation at every dialogue turn in a fully data-driven fashion.  ... 
arXiv:2104.08570v3 fatcat:a6vfgcvgqvhllfkgfwcr3mptgq

Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systems

Evgeniia Razumovskaia, Goran Glavas, Olga Majewska, Edoardo M. Ponti, Anna Korhonen, Ivan Vulic
2022 The Journal of Artificial Intelligence Research  
Hence, state-of-the-art approaches to multilingual ToD mostly rely on (zero- or few-shot) cross-lingual transfer from resource-rich languages (almost exclusively English), either by means of (i) machine  ...  In task-oriented dialogue (ToD), a user holds a conversation with an artificial agent with the aim of completing a concrete task.  ...  The Neural Belief Tracker (NBT; ) is a DST model that updates its internal representation of the state of a conversation at every dialogue turn in a fully data-driven fashion.  ... 
doi:10.1613/jair.1.13083 fatcat:54a6w62wxvbvvigh32zkmtwwqq