Label Enhanced Event Detection with Heterogeneous Graph Attention
Networks
- URL: http://arxiv.org/abs/2012.01878v1
- Date: Thu, 3 Dec 2020 12:49:22 GMT
- Title: Label Enhanced Event Detection with Heterogeneous Graph Attention
Networks
- Authors: Shiyao Cui, Bowen Yu, Xin Cong, Tingwen Liu, Quangang Li and Jinqiao
Shi
- Abstract summary: Event Detection (ED) aims to recognize instances of specified types of event triggers in text.
We propose a novel architecture named Label enhanced Heterogeneous Graph Attention Networks (L-HGAT)
Specifically, we transform each sentence into a graph, where character nodes and word nodes are connected with different types of edges.
A heterogeneous graph attention networks is then introduced to propagate relational message and enrich information interaction.
- Score: 7.13278850115938
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Event Detection (ED) aims to recognize instances of specified types of event
triggers in text. Different from English ED, Chinese ED suffers from the
problem of word-trigger mismatch due to the uncertain word boundaries. Existing
approaches injecting word information into character-level models have achieved
promising progress to alleviate this problem, but they are limited by two
issues. First, the interaction between characters and lexicon words is not
fully exploited. Second, they ignore the semantic information provided by event
labels. We thus propose a novel architecture named Label enhanced Heterogeneous
Graph Attention Networks (L-HGAT). Specifically, we transform each sentence
into a graph, where character nodes and word nodes are connected with different
types of edges, so that the interaction between words and characters is fully
reserved. A heterogeneous graph attention networks is then introduced to
propagate relational message and enrich information interaction. Furthermore,
we convert each label into a trigger-prototype-based embedding, and design a
margin loss to guide the model distinguish confusing event labels. Experiments
on two benchmark datasets show that our model achieves significant improvement
over a range of competitive baseline methods.
Related papers
- Description-Enhanced Label Embedding Contrastive Learning for Text
Classification [65.01077813330559]
Self-Supervised Learning (SSL) in model learning process and design a novel self-supervised Relation of Relation (R2) classification task.
Relation of Relation Learning Network (R2-Net) for text classification, in which text classification and R2 classification are treated as optimization targets.
external knowledge from WordNet to obtain multi-aspect descriptions for label semantic learning.
arXiv Detail & Related papers (2023-06-15T02:19:34Z) - AnnoBERT: Effectively Representing Multiple Annotators' Label Choices to
Improve Hate Speech Detection [18.823219608659986]
AnnoBERT is a first-of-its-kind architecture integrating annotator characteristics and label text to detect hate speech.
During training, the model associates annotators with their label choices given a piece of text.
During evaluation, when label information is not available, the model predicts the aggregated label given by the participating annotators.
arXiv Detail & Related papers (2022-12-20T16:30:11Z) - 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) - Group is better than individual: Exploiting Label Topologies and Label
Relations for Joint Multiple Intent Detection and Slot Filling [39.76268402567324]
We construct a Heterogeneous Label Graph (HLG) containing two kinds of topologies.
Label correlations are leveraged to enhance semantic-label interactions.
We also propose the label-aware inter-dependent decoding mechanism to further exploit the label correlations for decoding.
arXiv Detail & Related papers (2022-10-19T08:21:43Z) - Hierarchical Heterogeneous Graph Representation Learning for Short Text
Classification [60.233529926965836]
We propose a new method called SHINE, which is based on graph neural network (GNN) for short text classification.
First, we model the short text dataset as a hierarchical heterogeneous graph consisting of word-level component graphs.
Then, we dynamically learn a short document graph that facilitates effective label propagation among similar short texts.
arXiv Detail & Related papers (2021-10-30T05:33:05Z) - Why Propagate Alone? Parallel Use of Labels and Features on Graphs [42.01561812621306]
Graph neural networks (GNNs) and label propagation represent two interrelated modeling strategies designed to exploit graph structure in tasks such as node property prediction.
We show that a label trick can be reduced to an interpretable, deterministic training objective composed of two factors.
arXiv Detail & Related papers (2021-10-14T07:34:11Z) - R$^2$-Net: Relation of Relation Learning Network for Sentence Semantic
Matching [58.72111690643359]
We propose a Relation of Relation Learning Network (R2-Net) for sentence semantic matching.
We first employ BERT to encode the input sentences from a global perspective.
Then a CNN-based encoder is designed to capture keywords and phrase information from a local perspective.
To fully leverage labels for better relation information extraction, we introduce a self-supervised relation of relation classification task.
arXiv Detail & Related papers (2020-12-16T13:11:30Z) - GNN-XML: Graph Neural Networks for Extreme Multi-label Text
Classification [23.79498916023468]
Extreme multi-label text classification (XMTC) aims to tag a text instance with the most relevant subset of labels from an extremely large label set.
GNN-XML is a scalable graph neural network framework tailored for XMTC problems.
arXiv Detail & Related papers (2020-12-10T18:18:34Z) - ConsNet: Learning Consistency Graph for Zero-Shot Human-Object
Interaction Detection [101.56529337489417]
We consider the problem of Human-Object Interaction (HOI) Detection, which aims to locate and recognize HOI instances in the form of human, action, object> in images.
We argue that multi-level consistencies among objects, actions and interactions are strong cues for generating semantic representations of rare or previously unseen HOIs.
Our model takes visual features of candidate human-object pairs and word embeddings of HOI labels as inputs, maps them into visual-semantic joint embedding space and obtains detection results by measuring their similarities.
arXiv Detail & Related papers (2020-08-14T09:11:18Z) - Few-shot Slot Tagging with Collapsed Dependency Transfer and
Label-enhanced Task-adaptive Projection Network [61.94394163309688]
We propose a Label-enhanced Task-Adaptive Projection Network (L-TapNet) based on the state-of-the-art few-shot classification model -- TapNet.
Experimental results show that our model significantly outperforms the strongest few-shot learning baseline by 14.64 F1 scores in the one-shot setting.
arXiv Detail & Related papers (2020-06-10T07:50:44Z) - Iterative Context-Aware Graph Inference for Visual Dialog [126.016187323249]
We propose a novel Context-Aware Graph (CAG) neural network.
Each node in the graph corresponds to a joint semantic feature, including both object-based (visual) and history-related (textual) context representations.
arXiv Detail & Related papers (2020-04-05T13:09:37Z)
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.