Spoken Language Understanding-Cross-lingual口语语言理解(Spoken Language Understanding,SLU)作为任务型对话系统的核心组件,目的是为了获取用户询问语句的框架语义表示(semantics frame)信息,进而将这些信息为对话状态追踪模块(DST)以及自然语言生成模块(NLG)所使用。SLU任务通常包含以下两个任务:意图识别任务(intent detection)和槽位填充任务(slot filling),本论文集跨语言的口语语言理解论文。
IJCAI 2020, pp.3853-3860, (2020)
We proposed an augmentation framework to generate multilingual code-switching data to fine-tune mBERT for aligning representations from source and multiple target languages
Cited by7BibtexViews470DOI
0
0
Xu Weijia, Haider Batool, Mansour Saab
empirical methods in natural language processing, pp.5052-5063, (2020)
We introduce MultiATIS++, a multilingual natural language understanding corpus that extends the Multilingual ATIS corpus to nine languages across four language families
Cited by1BibtexViews12DOI
0
0
national conference on artificial intelligence, (2020)
We propose attention-informed mixed-language training, a novel zero-shot adaptation method for crosslingual task-oriented dialogue systems using code-switching sentences
Cited by1BibtexViews20
0
0
Zihan Liu, Genta Indra Winata,Peng Xu,Zhaojiang Lin, Pascale Fung
EMNLP 2020, pp.7241-7251, (2020)
To cope with this issue, we propose a regularization approach to further align word-level and sentence-level representations across languages without any external resource
Cited by0BibtexViews26DOI
0
0
Haoran Li, Abhinav Arora, Shuohui Chen, Anchit Gupta, Sonal Gupta, Yashar Mehdad
We provided strong benchmarks for both representations using state-of-the-art multilingual pre-trained models in both: zero-shot and with target language settings
Cited by0BibtexViews8
0
0
Quynh Do, Judith Gaspers
EMNLP/IJCNLP (1), pp.1455-1460, (2019)
We presented an efficient approach to select source data for cross-lingual transfer learning in largescale Spoken Language Understanding
Cited by0BibtexViews5DOI
0
0
Valentina Bellomaria, Giuseppe Castellucci,Andrea Favalli, Raniero Romagnoli
CLiC-it, (2019)
We show an evaluation carried out with models trained on three different split of reduced size derived from the whole dataset
Cited by0BibtexViews8
0
0
EMNLP/IJCNLP (1), pp.1297-1303, (2019)
We propose a zero-shot adaptation of task-oriented dialogue system to lowresource languages
Cited by0BibtexViews19DOI
0
0
Castellucci Giuseppe, Bellomaria Valentina,Favalli Andrea, Romagnoli Raniero
We provided an extensive evaluation in the English language: BERTbased approaches performs very well on the intent detection and slot filling tasks
Cited by0BibtexViews7
0
0
arXiv: Computation and Language, (2018)
We present a new data set of 57k annotated utterances in English, Spanish and Thai across the domains weather, alarm, and reminder
Cited by29BibtexViews56
0
0
ACL, pp.38-44, (2017)
We address multilingual semantic parsing – the task of mapping natural language sentences coming from multiple different languages into their corresponding formal semantic representations
Cited by16BibtexViews8
0
0