paper-with-me

홈 › Papers

Group is better than individual: Exploiting Label Topologies and Label Relations for Joint Multiple Intent Detection and Slot Filling

2022-10-19 · Bowen Xing, Ivor W. Tsang

Recent joint multiple intent detection and slot filling models employ label embeddings to achieve the semantics-label interactions. However, they treat all labels and label embeddings as uncorrelated individuals, ignoring the dependencies among them. Besides, they conduct the decoding for the two tasks independently, without leveraging the correlations between them. Therefore, in this paper, we first construct a Heterogeneous Label Graph (HLG) containing two kinds of topologies: (1) statistical dependencies based on labels' co-occurrence patterns and hierarchies in slot labels; (2) rich relations among the label nodes. Then we propose a novel model termed ReLa-Net. It can capture beneficial correlations among the labels from HLG. The label correlations are leveraged to enhance semantic-label interactions. Moreover, we also propose the label-aware inter-dependent decoding mechanism to further exploit the label correlations for decoding. Experiment results show that our ReLa-Net significantly outperforms previous models. Remarkably, ReLa-Net surpasses the previous best model by over 20\% in terms of overall accuracy on MixATIS dataset.

📄 PDF Abstract BibTeX arXiv:2210.10369

Code (0)

등록된 구현이 없습니다.

Tasks

Intent Detectionslot-fillingSlot Filling

Similar Papers 제목 키워드 기반

Ballpark Crowdsourcing: The Wisdom of Rough Group Comparisons

2017-12-13 · Tom Hope, Dafna Shahaf

Crowdsourcing has become a popular method for collecting labeled training data. However, in many practical scenarios traditional labeling can be difficult for crowdworkers (for example, if the data is high-dimensional or…

BIG-bench Machine Learning

Markedness in Visual Semantic AI

2022-05-23 · Robert Wolfe, Aylin Caliskan

We evaluate the state-of-the-art multimodal "visual semantic" model CLIP ("Contrastive Language Image Pretraining") for biases related to the marking of age, gender, and race or ethnicity. Given the option to label an im…

WoCE: a framework for clustering ensemble by exploiting the wisdom of Crowds theory

2016-12-20 · Muhammad Yousefnezhad, Sheng-Jun Huang, Daoqiang Zhang

The Wisdom of Crowds (WOC), as a theory in the social science, gets a new paradigm in computer science. The WOC theory explains that the aggregate decision made by a group is often better than those of its individual mem…

ClusteringClustering EnsembleDiversity

On Classification with Bags, Groups and Sets

2014-06-02 · Veronika Cheplygina, David M. J. Tax, Marco Loog

Many classification problems can be difficult to formulate directly in terms of the traditional supervised setting, where both training and test samples are individual feature vectors. There are cases in which samples ar…

ClassificationGeneral Classification

Group Preserving Label Embedding for Multi-Label Classification

2018-12-24 · Vikas Kumar, Arun K Pujari, Vineet Padmanabhan, Venkateswara Rao Kagita

Multi-label learning is concerned with the classification of data with multiple class labels. This is in contrast to the traditional classification problem where every data instance has a single label. Due to the exponen…

ClassificationDimensionality Reductionfeature selectionGeneral Classification+3