Cross-lingual intent classification in a low resource industrial setting

Khalil, Talaat; Kiełczewski, Kornel; Christos, Chouliaras, Georgios; Keldibek, Amina; Versteegh, Maarten

doi:10.18653/v1/d19-1676

Cited by 13 publications

(14 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This work has also empirically validated that there is still ample room for improvement in the intent detection task especially in low-data regimes. Therefore, similar to recent work (Upadhyay et al, 2018;Khalil et al, 2019;Liu et al, 2019c), we will also investigate how to transfer intent detectors to low-resource target languages in few-shot and zero-shot scenarios. We also plan to extend the models to handle out-of-scope prediction (Larson et al, 2019).…”

Section: Discussionmentioning

confidence: 93%

Efficient Intent Detection with Dual Sentence Encoders

Casanueva¹,

Temčinas²,

Gerz³

et al. 2020

Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI

191

137

View full text Add to dashboard Cite

Building conversational systems in new domains and with added functionality requires resource-efficient models that work under lowdata regimes (i.e., in few-shot setups). Motivated by these requirements, we introduce intent detection methods backed by pretrained dual sentence encoders such as USE and Con-veRT. We demonstrate the usefulness and wide applicability of the proposed intent detectors, showing that: 1) they outperform intent detectors based on fine-tuning the full BERT-Large model or using BERT as a fixed black-box encoder on three diverse intent detection data sets; 2) the gains are especially pronounced in few-shot setups (i.e., with only 10 or 30 annotated examples per intent); 3) our intent detectors can be trained in a matter of minutes on a single CPU; and 4) they are stable across different hyperparameter settings. In hope of facilitating and democratizing research focused on intention detection, we release our code, as well as a new challenging single-domain intent detection dataset comprising 13,083 annotated examples over 77 intents.

show abstract

Section: Discussionmentioning

confidence: 93%

Efficient Intent Detection with Dual Sentence Encoders

Casanueva¹,

Temčinas²,

Gerz³

et al. 2020

Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI

191

137

View full text Add to dashboard Cite

show abstract

“…Sources for parallel text can be the OPUS project (Tiedemann, 2012), Bible corpora (Mayer and Cysouw, 2014;Christodoulopoulos and Steedman, 2015) or the recent JW300 corpus (Agić and Vulić, 2019). Instead of using parallel corpora, existing high-resource labeled datasets can also be machine-translated into the low-resource language (Khalil et al, 2019;Zhang et al, 2019a;Fei et al, 2020;Amjad et al, 2020). Cross-lingual projections have even been used with English as a target language for detecting linguistic phenomena like modal sense and telicity that are easier to identify in a different language (Zhou et al, 2015;Marasović et al, 2016;Friedrich and Gateva, 2017).…”

Section: Cross-lingual Annotation Projectionsmentioning

confidence: 99%

A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios

Hedderich¹,

Lange²,

Adel³

et al. 2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

137

View full text Add to dashboard Cite

Deep neural networks and huge language models are becoming omnipresent in natural language applications. As they are known for requiring large amounts of training data, there is a growing body of work to improve the performance in low-resource settings. Motivated by the recent fundamental changes towards neural models and the popular pre-train and fine-tune paradigm, we survey promising approaches for low-resource natural language processing. After a discussion about the different dimensions of data availability, we give a structured overview of methods that enable learning when training data is sparse. This includes mechanisms to create additional labeled data like data augmentation and distant supervision as well as transfer learning settings that reduce the need for target supervision. A goal of our survey is to explain how these methods differ in their requirements as understanding them is essential for choosing a technique suited for a specific low-resource setting. Further key aspects of this work are to highlight open issues and to outline promising directions for future research.

show abstract

“…Compared with English, other languages rarely have datasets with semantic slot values and generally only contain intent category labels. Khalil et al [31] explored the intention classification based on the multilingual transfer ability of English and French. Xie et al [32] used the multiple semantic features to study Chinese user intention classification based on ECDT [33] dataset.…”

Section: Complexitymentioning

confidence: 99%

A Hybrid Neural Network BERT-Cap Based on Pre-Trained Language Model and Capsule Network for User Intent Classification

Liu

Wong

et al. 2020

Complexity

View full text Add to dashboard Cite

User intent classification is a vital component of a question-answering system or a task-based dialogue system. In order to understand the goals of users’ questions or discourses, the system categorizes user text into a set of pre-defined user intent categories. User questions or discourses are usually short in length and lack sufficient context; thus, it is difficult to extract deep semantic information from these types of text and the accuracy of user intent classification may be affected. To better identify user intents, this paper proposes a BERT-Cap hybrid neural network model with focal loss for user intent classification to capture user intents in dialogue. The model uses multiple transformer encoder blocks to encode user utterances and initializes encoder parameters with a pre-trained BERT. Then, it extracts essential features using a capsule network with dynamic routing after utterances encoding. Experiment results on four publicly available datasets show that our model BERT-Cap achieves a F1 score of 0.967 and an accuracy of 0.967, outperforming a number of baseline methods, indicating its effectiveness in user intent classification.

show abstract

Cross-lingual intent classification in a low resource industrial setting

Cited by 13 publications

References 10 publications

Efficient Intent Detection with Dual Sentence Encoders

Efficient Intent Detection with Dual Sentence Encoders

A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios

A Hybrid Neural Network BERT-Cap Based on Pre-Trained Language Model and Capsule Network for User Intent Classification

Contact Info

Product

Resources

About