A Contrastive Cross-Channel Data Augmentation Framework for Aspect-based Sentiment Analysis

• URL: http://arxiv.org/abs/2204.07832v1
• Date: Sat, 16 Apr 2022 16:05:58 GMT
• Title: A Contrastive Cross-Channel Data Augmentation Framework for Aspect-based Sentiment Analysis
• Authors: Bing Wang, Liang Ding, Qihuang Zhong, Ximing Li, Dacheng Tao
• Abstract summary: We propose a novel training framework to mitigate the multi-aspect challenge of sentiment analysis. A source sentence is fed a domain-specific generator to obtain some synthetic sentences. The generator generates aspect-specific sentences and a Polarity Augmentation (PAC) to generate polarity-inverted sentences. Our framework can outperform those baselines without any augmentations by about 1% on accuracy and Macro-F1.
• Score: 91.83895509731144
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Aspect-Based Sentiment Analysis is a fine-grained sentiment analysis task, which focuses on detecting the sentiment polarity towards the aspect in a sentence. However, it is always sensitive to the multi-aspect challenge, where features of multiple aspects in a sentence will affect each other. To mitigate this issue, we design a novel training framework, called Contrastive Cross-Channel Data Augmentation (C3DA). A source sentence will be fed a domain-specific generator to obtain some synthetic sentences and is concatenated with these generated sentences to conduct supervised training and proposed contrastive training. To be specific, considering the limited ABSA labeled data, we also introduce some parameter-efficient approaches to complete sentences generation. This novel generation method consists of an Aspect Augmentation Channel (AAC) to generate aspect-specific sentences and a Polarity Augmentation (PAC) to generate polarity-inverted sentences. According to our extensive experiments, our C3DA framework can outperform those baselines without any augmentations by about 1\% on accuracy and Macro-F1.

Related papers

• Amplifying Aspect-Sentence Awareness: A Novel Approach for Aspect-Based Sentiment Analysis [2.9045498954705886]
  Aspect-Based Sentiment Analysis (ABSA) is increasingly crucial in Natural Language Processing (NLP) ABSA goes beyond traditional sentiment analysis by extracting sentiments related to specific aspects mentioned in the text. We propose Amplifying Aspect-Sentence Awareness (A3SN), a novel technique designed to enhance ABSA through amplifying aspect-sentence awareness attention.
  arXiv  Detail & Related papers  (2024-05-14T10:29:59Z)
• Let's Rectify Step by Step: Improving Aspect-based Sentiment Analysis with Diffusion Models [36.482634643246264]
  We propose a novel diffusion model tailored for ABSA, which extracts the aspects progressively step by step. DiffusionABSA gradually adds noise to the aspect terms in the training process, subsequently learning a denoising process that progressively restores these terms in a reverse manner. To estimate the boundaries, we design a denoising neural network enhanced by a syntax-aware temporal attention mechanism.
  arXiv  Detail & Related papers  (2024-02-23T12:35:43Z)
• Aspect-oriented Opinion Alignment Network for Aspect-Based Sentiment Classification [14.212306015270208]
  We propose a novel Aspect-oriented Opinion Alignment Network (AOAN) to capture the contextual association between opinion words and the corresponding aspect. In addition, we design a multi-perspective attention mechanism that align relevant opinion information with respect to the given aspect. Our model achieves state-of-the-art results on three benchmark datasets.
  arXiv  Detail & Related papers  (2023-08-22T13:55:36Z)
• A Novel Counterfactual Data Augmentation Method for Aspect-Based Sentiment Analysis [7.921043998643318]
  We propose a novel and simple counterfactual data augmentation method to generate opinion expressions with reversed sentiment polarity. The experimental results show the proposed counterfactual data augmentation method performs better than current augmentation methods on three ABSA datasets.
  arXiv  Detail & Related papers  (2023-06-20T03:25:51Z)
• Generate, Discriminate and Contrast: A Semi-Supervised Sentence Representation Learning Framework [68.04940365847543]
  We propose a semi-supervised sentence embedding framework, GenSE, that effectively leverages large-scale unlabeled data. Our method include three parts: 1) Generate: A generator/discriminator model is jointly trained to synthesize sentence pairs from open-domain unlabeled corpus; 2) Discriminate: Noisy sentence pairs are filtered out by the discriminator to acquire high-quality positive and negative sentence pairs; 3) Contrast: A prompt-based contrastive approach is presented for sentence representation learning with both annotated and synthesized data.
  arXiv  Detail & Related papers  (2022-10-30T10:15:21Z)
• AdAUC: End-to-end Adversarial AUC Optimization Against Long-tail Problems [102.95119281306893]
  We present an early trial to explore adversarial training methods to optimize AUC. We reformulate the AUC optimization problem as a saddle point problem, where the objective becomes an instance-wise function. Our analysis differs from the existing studies since the algorithm is asked to generate adversarial examples by calculating the gradient of a min-max problem.
  arXiv  Detail & Related papers  (2022-06-24T09:13:39Z)
• A Simple Information-Based Approach to Unsupervised Domain-Adaptive Aspect-Based Sentiment Analysis [58.124424775536326]
  We propose a simple but effective technique based on mutual information to extract their term. Experiment results show that our proposed method outperforms the state-of-the-art methods for cross-domain ABSA by 4.32% Micro-F1.
  arXiv  Detail & Related papers  (2022-01-29T10:18:07Z)
• Auto-ABSA: Cross-Domain Aspect Detection and Sentiment Analysis Using Auxiliary Sentences [1.368483823700914]
  We proposed a method that uses an auxiliary sentence about aspects that the sentence contains to help sentiment prediction. The first is aspect detection, which uses a multi-aspects detection model to predict all aspects that the sentence has. The second is to do out-of-domain aspect-based sentiment analysis(ABSA), train sentiment classification model with one kind of dataset and validate it with another kind of dataset.
  arXiv  Detail & Related papers  (2022-01-05T04:23:29Z)
• Aspect Sentiment Quad Prediction as Paraphrase Generation [53.33072918744124]
  We introduce the Aspect Sentiment Quad Prediction (ASQP) task, aiming to jointly detect all sentiment elements in quads for a given opinionated sentence. We propose a novel textscParaphrase modeling paradigm to cast the ASQP task to a paraphrase generation process. On the other hand, the semantics of the sentiment elements can be fully exploited by learning to generate them in the natural language form.
  arXiv  Detail & Related papers  (2021-10-02T12:57:27Z)
• Weakly-Supervised Aspect-Based Sentiment Analysis via Joint Aspect-Sentiment Topic Embedding [71.2260967797055]
  We propose a weakly-supervised approach for aspect-based sentiment analysis. We learn sentiment, aspect> joint topic embeddings in the word embedding space. We then use neural models to generalize the word-level discriminative information.
  arXiv  Detail & Related papers  (2020-10-13T21:33:24Z)

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.