Multi-Granularity Semantic Aware Graph Model for Reducing Position Bias in Emotion-Cause Pair Extraction

• URL: http://arxiv.org/abs/2205.02132v1
• Date: Wed, 4 May 2022 15:39:46 GMT
• Title: Multi-Granularity Semantic Aware Graph Model for Reducing Position Bias in Emotion-Cause Pair Extraction
• Authors: Yinan Bao, Qianwen Ma, Lingwei Wei, Wei Zhou, Songlin Hu
• Abstract summary: The Emotion-Cause Pair Extraction (ECPE) task aims to extract emotions and causes as pairs from documents. Existing methods have set a fixed size window to capture relations between neighboring clauses. We propose a novel textbfMulti-textbfGranularity textbfSemantic textbfAware textbfGraph model (MGSAG) to incorporate fine-grained and coarse-grained semantic features jointly.
• Score: 23.93696773727978
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The Emotion-Cause Pair Extraction (ECPE) task aims to extract emotions and causes as pairs from documents. We observe that the relative distance distribution of emotions and causes is extremely imbalanced in the typical ECPE dataset. Existing methods have set a fixed size window to capture relations between neighboring clauses. However, they neglect the effective semantic connections between distant clauses, leading to poor generalization ability towards position-insensitive data. To alleviate the problem, we propose a novel \textbf{M}ulti-\textbf{G}ranularity \textbf{S}emantic \textbf{A}ware \textbf{G}raph model (MGSAG) to incorporate fine-grained and coarse-grained semantic features jointly, without regard to distance limitation. In particular, we first explore semantic dependencies between clauses and keywords extracted from the document that convey fine-grained semantic features, obtaining keywords enhanced clause representations. Besides, a clause graph is also established to model coarse-grained semantic relations between clauses. Experimental results indicate that MGSAG surpasses the existing state-of-the-art ECPE models. Especially, MGSAG outperforms other models significantly in the condition of position-insensitive data.

Related papers

• Emotion-cause pair extraction method based on multi-granularity information and multi-module interaction [0.6577148087211809]
  The purpose of emotion-cause pair extraction is to extract the pair of emotion clauses and cause clauses. Existing models do not adequately address the emotion and cause-induced locational imbalance of samples. We propose an end-to-end multitasking model (MM-ECPE) based on shared interaction between GRU, knowledge graph and transformer modules.
  arXiv  Detail & Related papers  (2024-04-10T08:00:26Z)
• Relation Rectification in Diffusion Model [64.84686527988809]
  We introduce a novel task termed Relation Rectification, aiming to refine the model to accurately represent a given relationship it initially fails to generate. We propose an innovative solution utilizing a Heterogeneous Graph Convolutional Network (HGCN) The lightweight HGCN adjusts the text embeddings generated by the text encoder, ensuring the accurate reflection of the textual relation in the embedding space.
  arXiv  Detail & Related papers  (2024-03-29T15:54:36Z)
• A Semantic Mention Graph Augmented Model for Document-Level Event Argument Extraction [12.286432133599355]
  Document-level Event Argument Extraction (DEAE) aims to identify arguments and their specific roles from an unstructured document. advanced approaches on DEAE utilize prompt-based methods to guide pre-trained language models (PLMs) in extracting arguments from input documents. We propose a semantic mention Graph Augmented Model (GAM) to address these two problems in this paper.
  arXiv  Detail & Related papers  (2024-03-12T08:58:07Z)
• Recognizing Conditional Causal Relationships about Emotions and Their Corresponding Conditions [37.16991100831717]
  We propose a new task to determine whether an input pair of emotion and cause has a valid causal relationship under different contexts. We use negative sampling to construct the final dataset to balance the number of documents with and without causal relationships.
  arXiv  Detail & Related papers  (2023-11-28T07:47:25Z)
• Unified Visual Relationship Detection with Vision and Language Models [89.77838890788638]
  This work focuses on training a single visual relationship detector predicting over the union of label spaces from multiple datasets. We propose UniVRD, a novel bottom-up method for Unified Visual Relationship Detection by leveraging vision and language models. Empirical results on both human-object interaction detection and scene-graph generation demonstrate the competitive performance of our model.
  arXiv  Detail & Related papers  (2023-03-16T00:06:28Z)
• Prototype-based Embedding Network for Scene Graph Generation [105.97836135784794]
  Current Scene Graph Generation (SGG) methods explore contextual information to predict relationships among entity pairs. Due to the diverse visual appearance of numerous possible subject-object combinations, there is a large intra-class variation within each predicate category. Prototype-based Embedding Network (PE-Net) models entities/predicates with prototype-aligned compact and distinctive representations. PL is introduced to help PE-Net efficiently learn such entitypredicate matching, and Prototype Regularization (PR) is devised to relieve the ambiguous entity-predicate matching.
  arXiv  Detail & Related papers  (2023-03-13T13:30:59Z)
• Pair-Based Joint Encoding with Relational Graph Convolutional Networks for Emotion-Cause Pair Extraction [25.101027960035147]
  Methods sequentially encode features with a specified order. They first encode emotion and cause features for clause extraction and then combine them for pair extraction. This lead to an imbalance in inter-task feature interaction where features extracted later have no direct contact with the former. We propose a novel Pair-Based Joint. Network, which generates pairs and clauses simultaneously in a joint feature manner to model the causal clauses. Experiments show PBN achieves state-of-the-art performance on the Chinese benchmark corpus.
  arXiv  Detail & Related papers  (2022-12-04T15:24:14Z)
• Graph Adaptive Semantic Transfer for Cross-domain Sentiment Classification [68.06496970320595]
  Cross-domain sentiment classification (CDSC) aims to use the transferable semantics learned from the source domain to predict the sentiment of reviews in the unlabeled target domain. We present Graph Adaptive Semantic Transfer (GAST) model, an adaptive syntactic graph embedding method that is able to learn domain-invariant semantics from both word sequences and syntactic graphs.
  arXiv  Detail & Related papers  (2022-05-18T07:47:01Z)
• Document-Level Relation Extraction with Sentences Importance Estimation and Focusing [52.069206266557266]
  Document-level relation extraction (DocRE) aims to determine the relation between two entities from a document of multiple sentences. We propose a Sentence Estimation and Focusing (SIEF) framework for DocRE, where we design a sentence importance score and a sentence focusing loss. Experimental results on two domains show that our SIEF not only improves overall performance, but also makes DocRE models more robust.
  arXiv  Detail & Related papers  (2022-04-27T03:20:07Z)
• Contextualized Semantic Distance between Highly Overlapped Texts [85.1541170468617]
  Overlapping frequently occurs in paired texts in natural language processing tasks like text editing and semantic similarity evaluation. This paper aims to address the issue with a mask-and-predict strategy. We take the words in the longest common sequence as neighboring words and use masked language modeling (MLM) to predict the distributions on their positions. Experiments on Semantic Textual Similarity show NDD to be more sensitive to various semantic differences, especially on highly overlapped paired texts.
  arXiv  Detail & Related papers  (2021-10-04T03:59:15Z)
• Position Bias Mitigation: A Knowledge-Aware Graph Model for Emotion Cause Extraction [24.288475819004034]
  We observe that a widely-used ECE dataset exhibits a bias that the majority of annotated cause clauses are either directly before their associated emotion clauses or are the emotion clauses themselves. Existing models for ECE tend to explore such relative position information and suffer from the dataset bias. We propose a novel strategy to generate adversarial examples in which the relative position information is no longer the indicative feature of cause clauses.
  arXiv  Detail & Related papers  (2021-06-07T11:14:58Z)

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.