Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces

Coucke, Alice; Saade, Alaa; Ball, Adrien; Bluche, Théodore; Caulier, Alexandre; Luque, David; Doumouro, Clément; Gisselbrecht, Thibault; Caltagirone, Francesco; Lavril, Thibaut; Primet, Maël; Dureau, Joseph

doi:10.48550/arxiv.1805.10190

Cited by 179 publications

(255 citation statements)

References 38 publications

Supporting

Mentioning

220

Contrasting

Order By: Relevance

“…Name # Utterance # Intent # Domain CLINC150 (Larson et al, 2019) 18200 150 10 BANKING77 (Casanueva et al, 2020) 10162 77 1 HWU64 (Liu et al, 2019) 10030 64 21 TOP (Gupta et al, 2018) 35741 25 2 SNIPS (Coucke et al, 2018) 9888 5 -ATIS (Tur et al, 2010) 4978 21 -Table 1: Data statistics for intent detection datasets.…”

Section: Supervised Fine-tuningmentioning

confidence: 99%

Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning

Zhang¹,

Bui²,

Yoon³

et al. 2021

Preprint

View full text Add to dashboard Cite

In this work, we focus on a more challenging few-shot intent detection scenario where many intents are fine-grained and semantically similar. We present a simple yet effective fewshot intent detection schema via contrastive pre-training and fine-tuning. Specifically, we first conduct self-supervised contrastive pretraining on collected intent datasets, which implicitly learns to discriminate semantically similar utterances without using any labels. We then perform few-shot intent detection together with supervised contrastive learning, which explicitly pulls utterances from the same intent closer and pushes utterances across different intents farther. Experimental results show that our proposed method achieves state-of-the-art performance on three challenging intent detection datasets under 5shot and 10-shot settings.

show abstract

Section: Supervised Fine-tuningmentioning

confidence: 99%

Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning

Zhang¹,

Bui²,

Yoon³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Our platform supports standard benchmark datasets for intent recognition, including CLINC (Larson et al, 2019), BANKING (Casanueva et al, 2020), SNIPS (Coucke et al, 2018), and StackOverflow (Xu et al, 2015). They are all split into training, evaluation and test sets.…”

Section: Data Managementmentioning

confidence: 99%

TEXTOIR: An Integrated and Visualized Platform for Text Open Intent Recognition

Zhang,

Li,

et al. 2021

Preprint

View full text Add to dashboard Cite

TEXTOIR is the first integrated and visualized platform for text open intent recognition. It is composed of two main modules: open intent detection and open intent discovery. Each module integrates most of the state-of-the-art algorithms and benchmark intent datasets. It also contains an overall framework connecting the two modules in a pipeline scheme. In addition, this platform has visualized tools for data and model management, training, evaluation and analysis of the performance from different aspects. TEXTOIR provides useful toolkits and convenient visualized interfaces for each sub-module 1 , and designs a framework to implement a complete process to both identify known intents and discover open intents 2 .

show abstract

“…Dataset We conduct experiments on two public datasets: SNIPS [3] (in English) and Few-Joint [10] (in Chinese). For SNIPS, we use the data split 3 of 5-shot setting without intent classification task.…”

Section: Settingsmentioning

confidence: 99%

Few-Shot NLU with Vector Projection Distance and Abstract Triangular CRF

Zhu,

Chen,

Cao

et al. 2021

Preprint

View full text Add to dashboard Cite

Data sparsity problem is a key challenge of Natural Language Understanding (NLU), especially for a new target domain. By training an NLU model in source domains and applying the model to an arbitrary target domain directly (even without fine-tuning), few-shot NLU becomes crucial to mitigate the data scarcity issue. In this paper, we propose to improve prototypical networks with vector projection distance and abstract triangular Conditional Random Field (CRF) for the few-shot NLU. The vector projection distance exploits projections of contextual word embeddings on label vectors as word-label similarities, which is equivalent to a normalized linear model. The abstract triangular CRF learns domain-agnostic label transitions for joint intent classification and slot filling tasks. Extensive experiments demonstrate that our proposed methods can significantly surpass strong baselines. Specifically, our approach can achieve a new state-of-the-art on two few-shot NLU benchmarks (Few-Joint and SNIPS) in Chinese and English without fine-tuning on target domains.

show abstract

Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces

Cited by 179 publications

References 38 publications

Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning

Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning

TEXTOIR: An Integrated and Visualized Platform for Text Open Intent Recognition

Few-Shot NLU with Vector Projection Distance and Abstract Triangular CRF

Contact Info

Product

Resources

About