ASTE Transformer Modelling Dependencies in Aspect-Sentiment Triplet Extraction

• URL: http://arxiv.org/abs/2409.15202v2
• Date: Fri, 4 Oct 2024 06:09:15 GMT
• Title: ASTE Transformer Modelling Dependencies in Aspect-Sentiment Triplet Extraction
• Authors: Iwo Naglik, Mateusz Lango,
• Abstract summary: Aspect-Sentiment Triplet Extraction (ASTE) is a recently proposed task that consists in extracting (aspect phrase, opinion phrase, sentiment polarity) triples from a given sentence. Recent state-of-the-art methods approach this task by first extracting all possible spans from a given sentence.
• Score: 2.07180164747172
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Aspect-Sentiment Triplet Extraction (ASTE) is a recently proposed task of aspect-based sentiment analysis that consists in extracting (aspect phrase, opinion phrase, sentiment polarity) triples from a given sentence. Recent state-of-the-art methods approach this task by first extracting all possible text spans from a given text, then filtering the potential aspect and opinion phrases with a classifier, and finally considering all their pairs with another classifier that additionally assigns sentiment polarity to them. Although several variations of the above scheme have been proposed, the common feature is that the final result is constructed by a sequence of independent classifier decisions. This hinders the exploitation of dependencies between extracted phrases and prevents the use of knowledge about the interrelationships between classifier predictions to improve performance. In this paper, we propose a new ASTE approach consisting of three transformer-inspired layers, which enables the modelling of dependencies both between phrases and between the final classifier decisions. Experimental results show that the method achieves higher performance in terms of F1 measure than other methods studied on popular benchmarks. In addition, we show that a simple pre-training technique further improves the performance of the model.

Related papers

• Coherent Entity Disambiguation via Modeling Topic and Categorical Dependency [87.16283281290053]
  Previous entity disambiguation (ED) methods adopt a discriminative paradigm, where prediction is made based on matching scores between mention context and candidate entities. We propose CoherentED, an ED system equipped with novel designs aimed at enhancing the coherence of entity predictions. We achieve new state-of-the-art results on popular ED benchmarks, with an average improvement of 1.3 F1 points.
  arXiv  Detail & Related papers  (2023-11-06T16:40:13Z)
• Controllable Data Augmentation for Few-Shot Text Mining with Chain-of-Thought Attribute Manipulation [35.33340453046864]
  Chain-of-Thought Attribute Manipulation (CoTAM) is a novel approach that generates new data from existing examples. We leverage the chain-of-thought prompting to directly edit the text in three steps, (1) attribute decomposition, (2) manipulation proposal, and (3) sentence reconstruction.
  arXiv  Detail & Related papers  (2023-07-14T00:10:03Z)
• A Pairing Enhancement Approach for Aspect Sentiment Triplet Extraction [3.5838781091072143]
  Aspect Sentiment Triplet Extraction aims to extract the triplet of an aspect term, an opinion term, and their corresponding sentiment polarity from the review texts. Due to the complexity of language and the existence of multiple aspect terms and opinion terms in a single sentence, current models often confuse the connections between an aspect term and the opinion term describing it. We propose a pairing enhancement approach for ASTE, which incorporates contrastive learning during the training stage to inject aspect-opinion pairing knowledge into the triplet extraction model.
  arXiv  Detail & Related papers  (2023-06-11T07:32:10Z)
• Reflection Invariance Learning for Few-shot Semantic Segmentation [53.20466630330429]
  Few-shot semantic segmentation (FSS) aims to segment objects of unseen classes in query images with only a few annotated support images. This paper proposes a fresh few-shot segmentation framework to mine the reflection invariance in a multi-view matching manner. Experiments on both PASCAL-$5textiti$ and COCO-$20textiti$ datasets demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2023-06-01T15:14:58Z)
• Diffusion Action Segmentation [63.061058214427085]
  We propose a novel framework via denoising diffusion models, which shares the same inherent spirit of such iterative refinement. In this framework, action predictions are iteratively generated from random noise with input video features as conditions.
  arXiv  Detail & Related papers  (2023-03-31T10:53:24Z)
• Understanding and Constructing Latent Modality Structures in Multi-modal Representation Learning [53.68371566336254]
  We argue that the key to better performance lies in meaningful latent modality structures instead of perfect modality alignment. Specifically, we design 1) a deep feature separation loss for intra-modality regularization; 2) a Brownian-bridge loss for inter-modality regularization; and 3) a geometric consistency loss for both intra- and inter-modality regularization.
  arXiv  Detail & Related papers  (2023-03-10T14:38:49Z)
• Part-guided Relational Transformers for Fine-grained Visual Recognition [59.20531172172135]
  We propose a framework to learn the discriminative part features and explore correlations with a feature transformation module. Our proposed approach does not rely on additional part branches and reaches state-the-of-art performance on 3-of-the-level object recognition.
  arXiv  Detail & Related papers  (2022-12-28T03:45:56Z)
• Span-level Bidirectional Cross-attention Framework for Aspect Sentiment Triplet Extraction [10.522014946035664]
  Aspect Sentiment Triplet Extraction (ASTE) is a new fine-grained sentiment analysis task that aims to extract triplets of aspect terms, sentiments, and opinion terms from review sentences. We propose a span-level bidirectional cross-attention framework for ASTE. Our framework significantly outperforms state-of-the-art methods, achieving better performance in predicting triplets with multi-token entities.
  arXiv  Detail & Related papers  (2022-04-27T02:55:43Z)
• PASTE: A Tagging-Free Decoding Framework Using Pointer Networks for Aspect Sentiment Triplet Extraction [12.921737393688245]
  Aspect Sentiment Triplet Extraction (ASTE) deals with extracting opinion triplets, consisting of an opinion target or aspect, its associated sentiment, and the corresponding opinion term/span. We adapt an encoder-decoder architecture with a Pointer Network-based decoding framework that generates an entire opinion triplet at each time step.
  arXiv  Detail & Related papers  (2021-10-10T13:39:39Z)
• Parameter Decoupling Strategy for Semi-supervised 3D Left Atrium Segmentation [0.0]
  We present a novel semi-supervised segmentation model based on parameter decoupling strategy to encourage consistent predictions from diverse views. Our method has achieved a competitive result over the state-of-the-art semisupervised methods on the Atrial Challenge dataset.
  arXiv  Detail & Related papers  (2021-09-20T14:51:42Z)
• Improving Aspect-based Sentiment Analysis with Gated Graph Convolutional Networks and Syntax-based Regulation [89.38054401427173]
  Aspect-based Sentiment Analysis (ABSA) seeks to predict the sentiment polarity of a sentence toward a specific aspect. dependency trees can be integrated into deep learning models to produce the state-of-the-art performance for ABSA. We propose a novel graph-based deep learning model to overcome these two issues.
  arXiv  Detail & Related papers  (2020-10-26T07:36:24Z)

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.