Towards Generative Aspect-Based Sentiment Analysis

Zhang, Wenxuan; Li, Xin; Deng, Yang; Lam, Wai

doi:10.18653/v1/2021.acl-short.64

Cited by 81 publications

(80 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…TwoStage [12], JET [91], GTS [75], OTE-MTL [92], BMRC [93] Dual-MRC [94], GAS [95], Gen-ABSA [96], Span-ASTE [97], NAG-ASTE [98], PASTE [99] Aspect-Category-Sentiment Detection (ACSD) TAS-BERT [46], MEJD [100], GAS [95], Paraphrase [7] Quad Extraction Aspect Sentiment Quad Prediction (ASQP) Extract-Classify-ACOS [101], Paraphrase [7] Fig. 2.…”

Section: Aspect Sentiment Triplet Extraction (Aste)mentioning

confidence: 99%

“…Since extracting mentioned aspects and classifying their sentiments lies in the core of ABSA problem [1], it is often directly referred to as the "ABSA problem". In recent years, to differentiate this task from the general ABSA problem (consisting of multiple tasks), it is called end-toend ABSA [19,82] or unified ABSA [84,95]. Following this convention, we thus take the name E2E-ABSA here to denote this task.…”

Section: End-to-end Absa (E2e-absa)mentioning

confidence: 99%

See 1 more Smart Citation

A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges

Zhang¹,

Li²,

Yang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

As an important fine-grained sentiment analysis problem, aspect-based sentiment analysis (ABSA), aiming to analyze and understand people's opinions at the aspect level, has been attracting considerable interest in the last decade. To handle ABSA in different scenarios, various tasks have been introduced for analyzing different sentiment elements and their relations, including the aspect term, aspect category, opinion term, and sentiment polarity. Unlike early ABSA works focusing on a single sentiment element, many compound ABSA tasks involving multiple elements have been studied in recent years for capturing more complete aspect-level sentiment information. However, a systematic review of various ABSA tasks and their corresponding solutions is still lacking, which we aim to fill in this survey. More specifically, we provide a new taxonomy for ABSA which organizes existing studies from the axes of concerned sentiment elements, with an emphasis on recent advances of compound ABSA tasks. From the perspective of solutions, we summarize the utilization of pre-trained language models for ABSA, which improved the performance of ABSA to a new stage. Besides, techniques for building more practical ABSA systems in cross-domain/lingual scenarios are discussed. Finally, we review some emerging topics and discuss some open challenges to outlook potential future directions of ABSA.

show abstract

Section: Aspect Sentiment Triplet Extraction (Aste)mentioning

confidence: 99%

Section: End-to-end Absa (E2e-absa)mentioning

confidence: 99%

A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges

Zhang¹,

Li²,

Yang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…These studies either adopt a unified tagging scheme (Li et al, 2019b,a;Hu et al, 2019) or solving them in a multi-task learning paradigm with shared feature representations (He et al, 2019;. Recently, there are also some attempts of combining another related task, namely opinion term extraction (OTE), with the ATE and/or ASC tasks to provide a more complete understanding of the aspect-level user sentiment Zhao et al, 2020;Chen and Qian, 2020b;Liang et al, 2020;Zhang et al, 2021).…”

Section: Related Workmentioning

confidence: 99%

“…", ATE is to detect the mentioned aspects "feel" and "food", whereas supposing aspects are given, ASC predicts their sentiment polarities as negative and positive respectively. Given the broad application scenarios, the two sub-tasks (He et al, 2017;Tulkens and van Cranenburgh, 2020) and their joint prediction (Li et al, 2019a;Chen and Qian, 2020a;Mao et al, 2021;Zhang et al, 2021) have received increasing attention in recent years.…”

Section: Introductionmentioning

confidence: 99%

Aspect-based Sentiment Analysis in Question Answering Forums

Zhang¹,

Deng²,

Li³

et al. 2021

Findings of the Association for Computational Linguistics: EMNLP 2021

Self Cite

View full text Add to dashboard Cite

Aspect-based sentiment analysis (ABSA) typically focuses on extracting aspects and predicting their sentiments on individual sentences such as customer reviews. Recently, another kind of opinion sharing platform, namely question answering (QA) forum, has received increasing popularity, which accumulates a large number of user opinions towards various aspects. This motivates us to investigate the task of ABSA on QA forums (ABSA-QA), aiming to jointly detect the discussed aspects and their sentiment polarities for a given QA pair. Unlike review sentences, a QA pair is composed of two parallel sentences, which requires interaction modeling to align the aspect mentioned in the question and the associated opinion clues in the answer. To this end, we propose a model with a specific design of crosssentence aspect-opinion interaction modeling to address this task. The proposed method is evaluated on three real-world datasets and the results show that our model outperforms several strong baselines adopted from related state-of-the-art models.

show abstract

“…Consider the following example, "The food is great, but the service is kinda disappointing", we can detect two mentioned aspect terms "food" and "service", and judge their corresponding sentiments as positive and negative, respectively. Given its wide application scenarios, it has attracted lots of attention in the NLP community in recent years (Li et al, 2019a;He et al, 2019;Hu et al, 2019;Chen and Qian, 2020;Liang et al, 2020;Mao et al, 2021;Zhang et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Cross-lingual Aspect-based Sentiment Analysis with Aspect Term Code-Switching

Zhang¹,

He²,

Peng³

et al. 2021

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Self Cite

View full text Add to dashboard Cite

Many efforts have been made in solving the Aspect-based sentiment analysis (ABSA) task. While most existing studies focus on English texts, handling ABSA in resource-poor languages remains a challenging problem. In this paper, we consider the unsupervised crosslingual transfer for the ABSA task, where only labeled data in the source language is available and we aim at transferring its knowledge to the target language having no labeled data. To this end, we propose an alignment-free label projection method to obtain high-quality pseudolabeled data of the target language with the help of the translation system, which could preserve more accurate task-specific knowledge in the target language. For better utilizing the source and translated data, as well as enhancing the cross-lingual alignment, we design an aspect code-switching mechanism to augment the training data with code-switched bilingual sentences. To further investigate the importance of language-specific knowledge in solving the ABSA problem, we distill the above model on the unlabeled target language data which improves the performance to the same level of the supervised method.

show abstract

Towards Generative Aspect-Based Sentiment Analysis

Cited by 81 publications

References 28 publications

A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges

A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges

Aspect-based Sentiment Analysis in Question Answering Forums

Cross-lingual Aspect-based Sentiment Analysis with Aspect Term Code-Switching

Contact Info

Product

Resources

About