Co-guiding Net: Achieving Mutual Guidances between Multiple Intent Detection and Slot Filling via Heterogeneous Semantics-Label Graphs

• URL: http://arxiv.org/abs/2210.10375v1
• Date: Wed, 19 Oct 2022 08:34:51 GMT
• Title: Co-guiding Net: Achieving Mutual Guidances between Multiple Intent Detection and Slot Filling via Heterogeneous Semantics-Label Graphs
• Authors: Bowen Xing and Ivor W. Tsang
• Abstract summary: We propose a novel model termed Co-guiding Net, which implements a two-stage framework achieving the textitmutual guidances between the two tasks. Specifically, we propose two textitheterogeneous graph attention networks working on the proposed two textitheterogeneous semantics-label graphs. Experiment results show that our model outperforms existing models by a large margin, obtaining a relative improvement of 19.3% over the previous best model on MixATIS dataset.
• Score: 39.76268402567324
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent graph-based models for joint multiple intent detection and slot filling have obtained promising results through modeling the guidance from the prediction of intents to the decoding of slot filling. However, existing methods (1) only model the \textit{unidirectional guidance} from intent to slot; (2) adopt \textit{homogeneous graphs} to model the interactions between the slot semantics nodes and intent label nodes, which limit the performance. In this paper, we propose a novel model termed Co-guiding Net, which implements a two-stage framework achieving the \textit{mutual guidances} between the two tasks. In the first stage, the initial estimated labels of both tasks are produced, and then they are leveraged in the second stage to model the mutual guidances. Specifically, we propose two \textit{heterogeneous graph attention networks} working on the proposed two \textit{heterogeneous semantics-label graphs}, which effectively represent the relations among the semantics nodes and label nodes. Experiment results show that our model outperforms existing models by a large margin, obtaining a relative improvement of 19.3\% over the previous best model on MixATIS dataset in overall accuracy.

Related papers

• Leveraging Graph Diffusion Models for Network Refinement Tasks [72.54590628084178]
  We propose a novel graph generative framework, SGDM, based on subgraph diffusion. Our framework not only improves the scalability and fidelity of graph diffusion models, but also leverages the reverse process to perform novel, conditional generation tasks.
  arXiv  Detail & Related papers  (2023-11-29T18:02:29Z)
• 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)
• GrannGAN: Graph annotation generative adversarial networks [72.66289932625742]
  We consider the problem of modelling high-dimensional distributions and generating new examples of data with complex relational feature structure coherent with a graph skeleton. The model we propose tackles the problem of generating the data features constrained by the specific graph structure of each data point by splitting the task into two phases. In the first it models the distribution of features associated with the nodes of the given graph, in the second it complements the edge features conditionally on the node features.
  arXiv  Detail & Related papers  (2022-12-01T11:49:07Z)
• 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)
• Message Passing Neural Networks for Hypergraphs [6.999112784624749]
  We present the first graph neural network based on message passing capable of processing hypergraph-structured data. We show that the proposed model defines a design space for neural network models for hypergraphs, thus generalizing existing models for hypergraphs.
  arXiv  Detail & Related papers  (2022-03-31T12:38:22Z)
• Joint Graph Learning and Matching for Semantic Feature Correspondence [69.71998282148762]
  We propose a joint emphgraph learning and matching network, named GLAM, to explore reliable graph structures for boosting graph matching. The proposed method is evaluated on three popular visual matching benchmarks (Pascal VOC, Willow Object and SPair-71k) It outperforms previous state-of-the-art graph matching methods by significant margins on all benchmarks.
  arXiv  Detail & Related papers  (2021-09-01T08:24:02Z)
• A Graph-based Interactive Reasoning for Human-Object Interaction Detection [71.50535113279551]
  We present a novel graph-based interactive reasoning model called Interactive Graph (abbr. in-Graph) to infer HOIs. We construct a new framework to assemble in-Graph models for detecting HOIs, namely in-GraphNet. Our framework is end-to-end trainable and free from costly annotations like human pose.
  arXiv  Detail & Related papers  (2020-07-14T09:29:03Z)
• Contextualised Graph Attention for Improved Relation Extraction [18.435408046826048]
  A novel method is proposed to use multiple sub-graphs to learn rich node representations in graph-based networks. Two types of edge features are proposed, which are effectively combined with GAT and GCN models to apply for relation extraction. The proposed model achieves state-of-the-art performance on Semeval 2010 Task 8 dataset, achieving an F1-score of 86.3.
  arXiv  Detail & Related papers  (2020-04-22T15:04:52Z)
• Jointly Modeling Aspect and Sentiment with Dynamic Heterogeneous Graph Neural Networks [27.59070337052869]
  Target-Based Sentiment Analysis aims to detect the opinion aspects (aspect extraction) and the sentiment polarities (sentiment detection) towards them. Both the previous pipeline and integrated methods fail to precisely model the innate connection between these two objectives. We propose a novel dynamic heterogeneous graph to jointly model the two objectives in an explicit way.
  arXiv  Detail & Related papers  (2020-04-14T11:27:30Z)

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.