Learning to Bridge Metric Spaces: Few-shot Joint Learning of Intent Detection and Slot Filling

Hou, Yutai; Lai, Yongkui; Cheng, Chen; Che, Wanxiang; Liu, Ting

doi:10.18653/v1/2021.findings-acl.282

Cited by 9 publications

(6 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A graph neural network was also utilized to directly model the interactions. To adaptively model the interaction, Hou et al [35] proposed a similarity-based learning framework, and Cai et al [36] incorporated a slot-intent classifier. Different from our method, these approaches primarily focus on the model structure; researchers have not fully explored the potential of PLMs.…”

Section: Joint Model In Natural Language Understandingmentioning

confidence: 99%

Promoting Unified Generative Framework with Descriptive Prompts for Joint Multi-Intent Detection and Slot Filling

Ma,

Qin,

Pan

et al. 2024

Electronics

View full text Add to dashboard Cite

Natural language understanding is a crucial aspect of task-oriented dialogue systems, encompassing intent detection (ID) and slot filling (SF). Conventional approaches for ID and SF solve the problems in a separate manners, while recent studies are now leaning toward joint modeling to tackle multi-intent detection and SF. Although the advancements in prompt learning offer a unified framework for ID and SF, current prompt-based methods fail to fully exploit the semantics of intent and slot labels. Additionally, the potential of using prompt learning to model the correlation between ID and SF in multi-intent scenarios remains unexplored. To address the issue, we propose a text-generative framework that unifies ID and SF. The prompt templates are constructed with label semantical descriptions. Moreover, we introduce an auxiliary task to explicitly capture the correlation between ID and SF. The experimental results on two benchmark datasets show that our method achieves an overall accuracy improvement of 0.4–1.5% in a full-data scenario and 1.4–2.7% in a few-shot setting compared with a prior method, establishing it as a new state-of-the-art approach.

show abstract

Section: Joint Model In Natural Language Understandingmentioning

confidence: 99%

Promoting Unified Generative Framework with Descriptive Prompts for Joint Multi-Intent Detection and Slot Filling

Ma,

Qin,

Pan

et al. 2024

Electronics

View full text Add to dashboard Cite

show abstract

“…Therefore, it is reasonable to transfer the general semantic representation from source domains to target domains, while it is difficult to transfer the domainspecific knowledge. Despite a few work has noticed the differences between the two parts, they still tried to conduct the transferring as a whole (Hou et al 2021;Liu et al 2021), which may be inefficient.…”

Section: Source Targetmentioning

confidence: 99%

“…• JointProto (Krone, Zhang, and Diab 2020) jointly learns the intent and slot representations by sharing a single BERT encoder on source domains, without fine-tuning on target domains. • ConProm (Hou et al 2021) merges the intent and slot representations into one space and learns the representations by contrastive learning. • ConProm+TR+FT, where FT denotes fine-tuning models, and TR denotes the transition rules of BIO annotation, which ban illegal slot predictions from left to right during target-domain evaluation.…”

Section: Baselines and Evaluation Metricsmentioning

confidence: 99%

Decoupling Representation and Knowledge for Few-Shot Intent Classification and Slot Filling

Han,

Zou,

Wang

et al. 2024

AAAI

View full text Add to dashboard Cite

Few-shot intent classification and slot filling are important but challenging tasks due to the scarcity of finely labeled data. Therefore, current works first train a model on source domains with sufficiently labeled data, and then transfer the model to target domains where only rarely labeled data is available. However, experience transferring as a whole usually suffers from gaps that exist among source domains and target domains. For instance, transferring domain-specific-knowledge-related experience is difficult. To tackle this problem, we propose a new method that explicitly decouples the transferring of general-semantic-representation-related experience and the domain-specific-knowledge-related experience. Specifically, for domain-specific-knowledge-related experience, we design two modules to capture intent-slot relation and slot-slot relation respectively. Extensive experiments on Snips and FewJoint datasets show that our method achieves state-of-the-art performance. The method improves the joint accuracy metric from 27.72% to 42.20% in the 1-shot setting, and from 46.54% to 60.79% in the 5-shot setting.

show abstract

“…. Hou et al (2021) improves few-shot slot tagging performance by jointly learning it with intent detection.…”

mentioning

confidence: 99%

Inverse is Better! Fast and Accurate Prompt for Few-shot Slot Tagging

Hou¹,

Chen²,

Li³

et al. 2022

Findings of the Association for Computational Linguistics: ACL 2022

View full text Add to dashboard Cite

Prompting methods recently achieve impressive success in few-shot learning. These methods modify input samples with prompt sentence pieces, and decode label tokens to map samples to corresponding labels. However, such a paradigm is very inefficient for the task of slot tagging. Since slot tagging samples are multiple consecutive words in a sentence, the prompting methods have to enumerate all n-grams token spans to find all the possible slots, which greatly slows down the prediction. To tackle this, we introduce an inverse paradigm for prompting. Different from the classic prompts mapping tokens to labels, we reversely predict slot values given slot types. Such inverse prompting only requires a oneturn prediction for each slot type and greatly speeds up the prediction. Besides, we propose a novel Iterative Prediction Strategy, from which the model learns to refine predictions by considering the relations between different slot types. We find, somewhat surprisingly, the proposed method not only predicts faster but also significantly improves the effect (improve over 6.1 F1-scores on 10-shot setting) and achieves new state-of-the-art performance.

show abstract

Learning to Bridge Metric Spaces: Few-shot Joint Learning of Intent Detection and Slot Filling

Cited by 9 publications

References 33 publications

Promoting Unified Generative Framework with Descriptive Prompts for Joint Multi-Intent Detection and Slot Filling

Promoting Unified Generative Framework with Descriptive Prompts for Joint Multi-Intent Detection and Slot Filling

Decoupling Representation and Knowledge for Few-Shot Intent Classification and Slot Filling

Inverse is Better! Fast and Accurate Prompt for Few-shot Slot Tagging

Contact Info

Product

Resources

About