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

• URL: http://arxiv.org/abs/2106.01925v1
• Date: Thu, 3 Jun 2021 15:22:38 GMT
• Title: GL-GIN: Fast and Accurate Non-Autoregressive Model for Joint Multiple Intent Detection and Slot Filling
• Authors: Libo Qin, Fuxuan Wei, Tianbao Xie, Xiao Xu, Wanxiang Che, Ting Liu
• Abstract summary: Multi-intent SLU can handle multiple intents in an utterance, which has attracted increasing attention. In this paper, we explore a non-autoregressive model for joint multiple intent detection and slot filling. Our framework achieves state-of-the-art performance while being 11.5 times faster.
• Score: 31.833158491112005
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: 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 inference speed and information leakage. In this paper, we explore a non-autoregressive model for joint multiple intent detection and slot filling, achieving more fast and accurate. Specifically, we propose a Global-Locally Graph Interaction Network (GL-GIN) where a local slot-aware graph interaction layer is proposed to model slot dependency for alleviating uncoordinated slots problem while a global intent-slot graph interaction layer is introduced to model the interaction between multiple intents and all slots in the utterance. Experimental results on two public datasets show that our framework achieves state-of-the-art performance while being 11.5 times faster.

Related papers

• MISCA: A Joint Model for Multiple Intent Detection and Slot Filling with Intent-Slot Co-Attention [9.414164374919029]
  Recent advanced approaches, which are joint models based on graphs, might still face two potential 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.
  arXiv  Detail & Related papers  (2023-12-10T03:38:41Z)
• Co-guiding for Multi-intent Spoken Language Understanding [53.30511968323911]
  We propose a novel model termed Co-guiding Net, which implements a two-stage framework achieving the mutual guidances between the two tasks. For the first stage, we propose single-task supervised contrastive learning, and for the second stage, we propose co-guiding supervised contrastive learning. Experiment results on multi-intent SLU show that our model outperforms existing models by a large margin.
  arXiv  Detail & Related papers  (2023-11-22T08:06:22Z)
• Local-Global Information Interaction Debiasing for Dynamic Scene Graph Generation [51.92419880088668]
  We propose a novel DynSGG model based on multi-task learning, DynSGG-MTL, which introduces the local interaction information and global human-action interaction information. Long-temporal human actions supervise the model to generate multiple scene graphs that conform to the global constraints and avoid the model being unable to learn the tail predicates.
  arXiv  Detail & Related papers  (2023-08-10T01:24:25Z)
• A Dynamic Graph Interactive Framework with Label-Semantic Injection for Spoken Language Understanding [43.48113981442722]
  We propose a framework termed DGIF, which first leverages the semantic information of labels to give the model additional signals and enriched priors. We propose a novel approach to construct the interactive graph based on the injection of label semantics, which can automatically update the graph to better alleviate error propagation.
  arXiv  Detail & Related papers  (2022-11-08T05:57:46Z)
• Representing Videos as Discriminative Sub-graphs for Action Recognition [165.54738402505194]
  We introduce a new design of sub-graphs to represent and encode theriminative patterns of each action in the videos. We present MUlti-scale Sub-Earn Ling (MUSLE) framework that novelly builds space-time graphs and clusters into compact sub-graphs on each scale.
  arXiv  Detail & Related papers  (2022-01-11T16:15:25Z)
• Joint Intent Detection and Slot Filling with Wheel-Graph Attention Networks [6.939768185086755]
  We propose a new joint model with a wheel-graph attention network (Wheel-GAT) which is able to model interrelated connections directly for intent detection and slot filling. To construct a graph structure for utterances, we create intent nodes, slot nodes, and directed edges.
  arXiv  Detail & Related papers  (2021-02-09T02:37:56Z)
• SlotRefine: A Fast Non-Autoregressive Model for Joint Intent Detection and Slot Filling [22.6796529031142]
  Slot filling and intent detection are two main tasks in spoken language understanding (SLU) system. We propose a novel non-autoregressive model named SlotRefine for joint intent detection and slot filling.
  arXiv  Detail & Related papers  (2020-10-06T13:16:53Z)
• Jointly Cross- and Self-Modal Graph Attention Network for Query-Based Moment Localization [77.21951145754065]
  We propose a novel Cross- and Self-Modal Graph Attention Network (CSMGAN) that recasts this task as a process of iterative messages passing over a joint graph. Our CSMGAN is able to effectively capture high-order interactions between two modalities, thus enabling a further precise localization.
  arXiv  Detail & Related papers  (2020-08-04T08:25:24Z)
• Disentangled Graph Collaborative Filtering [100.26835145396782]
  Disentangled Graph Collaborative Filtering (DGCF) is a new model for learning informative representations of users and items from interaction data. By modeling a distribution over intents for each user-item interaction, we iteratively refine the intent-aware interaction graphs and representations. DGCF achieves significant improvements over several state-of-the-art models like NGCF, DisenGCN, and MacridVAE.
  arXiv  Detail & Related papers  (2020-07-03T15:37:25Z)
• AGIF: An Adaptive Graph-Interactive Framework for Joint Multiple Intent Detection and Slot Filling [69.59096090788125]
  In this paper, we propose an Adaptive Graph-Interactive Framework (AGIF) for joint multiple intent detection and slot filling. We introduce an intent-slot graph interaction layer to model the strong correlation between the slot and intents. Such an interaction layer is applied to each token adaptively, which has the advantage to automatically extract the relevant intents information.
  arXiv  Detail & Related papers  (2020-04-21T15:07:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.