paper-with-me

홈 › Papers

MISCA: A Joint Model for Multiple Intent Detection and Slot Filling with Intent-Slot Co-Attention

2023-12-10 · Thinh Pham, Chi Tran, Dat Quoc Nguyen

The research study of detecting multiple intents and filling slots is becoming more popular because of its relevance to complicated real-world situations. Recent advanced approaches, which are joint models based on graphs, might still face two potential issues: (i) the uncertainty introduced by constructing graphs based on preliminary intents and slots, which may transfer intent-slot correlation information to incorrect label node destinations, and (ii) direct incorporation of multiple intent labels for each token w.r.t. token-level intent voting might potentially lead to incorrect slot predictions, thereby hurting the overall performance. To address these two issues, we propose a joint model named MISCA. Our MISCA introduces an intent-slot co-attention mechanism and an underlying layer of label attention mechanism. These mechanisms enable MISCA to effectively capture correlations between intents and slot labels, eliminating the need for graph construction. They also facilitate the transfer of correlation information in both directions: from intents to slots and from slots to intents, through multiple levels of label-specific representations, without relying on token-level intent information. Experimental results show that MISCA outperforms previous models, achieving new state-of-the-art overall accuracy performances on two benchmark datasets MixATIS and MixSNIPS. This highlights the effectiveness of our attention mechanisms.

📄 PDF Abstract BibTeX arXiv:2312.05741

Code (1)

vinairesearch/misca 공식 구현 pytorch

Tasks

graph constructionIntent DetectionSemantic Frame Parsingslot-fillingSlot Filling

Similar Papers 제목 키워드 기반

Enhancing Joint Multiple Intent Detection and Slot Filling with Global Intent-Slot Co-occurrence

2022-12-01 · Conference on Empirical Methods in Natural Language Processing 2022 12 · Mengxiao Song, Bowen Yu, Li Quangang, Wang Yubin 외

Multi-intent detection and slot filling joint model attracts more and more attention since it can handle multi-intent utterances, which is closer to complex real-world scenarios. Most existing joint models rely entirely …

Graph Neural NetworkIntent DetectionSemantic Frame Parsingslot-filling+1

SLIM: Explicit Slot-Intent Mapping with BERT for Joint Multi-Intent Detection and Slot Filling

2021-08-26 · Fengyu Cai, Wanhao Zhou, Fei Mi, Boi Faltings

Utterance-level intent detection and token-level slot filling are two key tasks for natural language understanding (NLU) in task-oriented systems. Most existing approaches assume that only a single intent exists in an ut…

Intent DetectionNatural Language UnderstandingSemantic Frame Parsingslot-filling+1

GL-GIN: Fast and Accurate Non-Autoregressive Model for Joint Multiple Intent Detection and Slot Filling

2021-06-03 · ACL 2021 5 · Libo Qin, Fuxuan Wei, Tianbao Xie, Xiao Xu 외

Multi-intent SLU can handle multiple intents in an utterance, which has attracted increasing attention. However, the state-of-the-art joint models heavily rely on autoregressive approaches, resulting in two issues: slow …

Intent DetectionSemantic Frame Parsingslot-fillingSlot Filling

Joint Multiple Intent Detection and Slot Filling via Self-distillation

2021-08-18 · Lisong Chen, Peilin Zhou, Yuexian Zou

Intent detection and slot filling are two main tasks in natural language understanding (NLU) for identifying users' needs from their utterances. These two tasks are highly related and often trained jointly. However, most…

DecoderIntent DetectionMultiple Instance LearningNatural Language Understanding+2

Joint Intent Detection and Slot Filling with Wheel-Graph Attention Networks

2021-02-09 · Pengfei Wei, Bi Zeng, Wenxiong Liao

Intent detection and slot filling are two fundamental tasks for building a spoken language understanding (SLU) system. Multiple deep learning-based joint models have demonstrated excellent results on the two tasks. In th…

Graph AttentionIntent Detectionslot-fillingSlot Filling+1