Eliminating Sentiment Bias for Aspect-Level Sentiment Classification
with Unsupervised Opinion Extraction
- URL: http://arxiv.org/abs/2109.02403v2
- Date: Tue, 7 Sep 2021 06:28:40 GMT
- Title: Eliminating Sentiment Bias for Aspect-Level Sentiment Classification
with Unsupervised Opinion Extraction
- Authors: Bo Wang, Tao Shen, Guodong Long, Tianyi Zhou, Yi Chang
- Abstract summary: ALSC aims at identifying the sentiment polarity of a specified aspect in a sentence.
Recent works fine-tune pre-trained Transformer encoders for ALSC to extract an aspect-centric dependency tree.
We propose a span-based anti-bias aspect representation learning framework.
- Score: 47.09579655541417
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Aspect-level sentiment classification (ALSC) aims at identifying the
sentiment polarity of a specified aspect in a sentence. ALSC is a practical
setting in aspect-based sentiment analysis due to no opinion term labeling
needed, but it fails to interpret why a sentiment polarity is derived for the
aspect. To address this problem, recent works fine-tune pre-trained Transformer
encoders for ALSC to extract an aspect-centric dependency tree that can locate
the opinion words. However, the induced opinion words only provide an intuitive
cue far below human-level interpretability. Besides, the pre-trained encoder
tends to internalize an aspect's intrinsic sentiment, causing sentiment bias
and thus affecting model performance. In this paper, we propose a span-based
anti-bias aspect representation learning framework. It first eliminates the
sentiment bias in the aspect embedding by adversarial learning against aspects'
prior sentiment. Then, it aligns the distilled opinion candidates with the
aspect by span-based dependency modeling to highlight the interpretable opinion
terms. Our method achieves new state-of-the-art performance on five benchmarks,
with the capability of unsupervised opinion extraction.
Related papers
- Enhanced Coherence-Aware Network with Hierarchical Disentanglement for Aspect-Category Sentiment Analysis [12.024076910894417]
We propose an enhanced coherence-aware network with hierarchical disentanglement (ECAN) for ACSA tasks.
Our ECAN effectively decouples multiple categories and sentiments entangled in the coherence representations and achieves state-of-the-art (SOTA) performance.
arXiv Detail & Related papers (2024-03-15T11:32:44Z) - 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) - Sentiment-Aware Word and Sentence Level Pre-training for Sentiment
Analysis [64.70116276295609]
SentiWSP is a Sentiment-aware pre-trained language model with combined Word-level and Sentence-level Pre-training tasks.
SentiWSP achieves new state-of-the-art performance on various sentence-level and aspect-level sentiment classification benchmarks.
arXiv Detail & Related papers (2022-10-18T12:25:29Z) - Learning Implicit Sentiment in Aspect-based Sentiment Analysis with
Supervised Contrastive Pre-Training [18.711698114617526]
We propose Supervised Contrastive Pre-training on large-scale sentiment-annotated corpora.
By aligning the representation of implicit sentiment expressions to those with the same sentiment label, the pre-training process leads to better capture of both implicit and explicit sentiment orientation towards aspects in reviews.
arXiv Detail & Related papers (2021-11-03T13:03:17Z) - Fine-Grained Opinion Summarization with Minimal Supervision [48.43506393052212]
FineSum aims to profile a target by extracting opinions from multiple documents.
FineSum automatically identifies opinion phrases from the raw corpus, classifies them into different aspects and sentiments, and constructs multiple fine-grained opinion clusters under each aspect/sentiment.
Both automatic evaluation on the benchmark and quantitative human evaluation validate the effectiveness of our approach.
arXiv Detail & Related papers (2021-10-17T15:16:34Z) - 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) - SentiPrompt: Sentiment Knowledge Enhanced Prompt-Tuning for Aspect-Based
Sentiment Analysis [22.758661494710047]
We propose SentiPrompt to tune the language model in the unified framework.
We inject sentiment knowledge regarding aspects, opinions, and polarities into prompt and explicitly model term relations.
Our approach can outperform strong baselines on Triplet Extraction, Pair Extraction, and Aspect Term Extraction with Sentiment Classification.
arXiv Detail & Related papers (2021-09-17T01:56:06Z) - A Weak Supervised Dataset of Fine-Grained Emotions in Portuguese [0.0]
This research describes an approach to create a lexical-based weak supervised corpus for fine-grained emotion in Portuguese.
Our results suggest lexical-based weak supervision as an appropriate strategy for initial work in low resources environment.
arXiv Detail & Related papers (2021-08-17T14:08:23Z) - 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) - GRACE: Gradient Harmonized and Cascaded Labeling for Aspect-based
Sentiment Analysis [90.43089622630258]
We propose a GRadient hArmonized and CascadEd labeling model (GRACE) to solve these problems.
The proposed model achieves consistency improvement on multiple benchmark datasets and generates state-of-the-art results.
arXiv Detail & Related papers (2020-09-22T13:55:34Z)
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.