The aspect-based sentiment analysis (ABSA) consists of two conceptual tasks, namely an aspect extraction and an aspect sentiment classification. Rather than considering the tasks separately, we build an end-to-end ABSA solution. Previous works in ABSA tasks did not fully leverage the importance of syntactical information. Hence, the aspect extraction model often failed to detect the boundaries of multi-word aspect terms. On the other hand, the aspect sentiment classifier was unable to account for the syntactical correlation between aspect terms and the context words. This paper explores the grammatical aspect of the sentence and employs the self-attention mechanism for syntactical learning. We combine part-of-speech embeddings, dependency-based embeddings and contextualized embeddings (e.g. BERT, RoBERTa) to enhance the performance of the aspect extractor. We also propose the syntactic relative distance to de-emphasize the adverse effects of unrelated words, having weak syntactic connection with the aspect terms. This increases the accuracy of the aspect sentiment classifier. Our solutions outperform the state-of-the-art models on SemEval-2014 dataset in both two subtasks.

/pdf/modelling-context-and-syntactical-features-for-aspect-based-snjxs08e56.pdf

Modelling Context and Syntactical Features for Aspect-based Sentiment Analysis.

A multi-task learning model for Chinese-oriented aspect polarity classification and aspect term extraction

Aspect-based (aspect-level) sentiment analysis is an important task in fine-grained sentiment analysis, which aims to automatically infer the sentiment towards an aspect in its context Previous studies have shown that utilizing the attention-based method can effectively improve the accuracy of the aspect-based sentiment analysis Despite the outstanding progress, aspect-based sentiment analysis in the real-world remains several challenges (1) The current attention-based method may cause a given aspect to incorrectly focus on syntactically unrelated words (2) Conventional methods fail to identify the sentiment with the special sentence structure, such as double negatives (3) Most of the studies leverage only one vector to represent context and target However, utilizing one vector to represent the sentence is limited, as the natural languages are delicate and complex In this paper, we propose a knowledge guided capsule network (KGCapsAN), which can address the above deficiencies Our method is composed of two parts, a Bi-LSTM network and a capsule attention network The capsule attention network implements the routing method by attention mechanism Moreover, we utilize two prior knowledge to guide the capsule attention process, which are syntactical and n-gram structures Extensive experiments are conducted on six datasets, and the results show that the proposed method yields the state-of-the-art

Knowledge Guided Capsule Attention Network for Aspect-Based Sentiment Analysis

Targeted sentiment classification predicts the sentiment polarity on given target mentions in input texts. Dominant methods employ neural networks for encoding the input sentence and extracting relations between target mentions and their contexts. Recently, graph neural network has been investigated for integrating dependency syntax for the task, achieving the state-of-the-art results. However, existing methods do not consider dependency label information, which can be intuitively useful. To solve the problem, we investigate a novel relational graph attention network that integrates typed syntactic dependency information. Results on standard benchmarks show that our method can effectively leverage label information for improving targeted sentiment classification performances. Our final model significantly outperforms state-of-the-art syntax-based approaches.

Investigating Typed Syntactic Dependencies for Targeted Sentiment Classification Using Graph Attention Neural Network

Aspect-based sentiment analysis (ABSA) task is a multi-grained task of natural language processing and consists of two subtasks: aspect term extraction (ATE) and aspect polarity classification (APC). Most of the existing work focuses on the subtask of aspect term polarity inferring and ignores the significance of aspect term extraction. Besides, the existing researches do not pay attention to the research of the Chinese-oriented ABSA task. Based on the local context focus (LCF) mechanism, this paper firstly proposes a multi-task learning model for Chinese-oriented aspect-based sentiment analysis, namely LCF-ATEPC. Compared with existing models, this model equips the capability of extracting aspect term and inferring aspect term polarity synchronously, moreover, this model is effective to analyze both Chinese and English comments simultaneously and the experiment on a multilingual mixed dataset proved its availability. By integrating the domain-adapted BERT model, the LCF-ATEPC model achieved the state-of-the-art performance of aspect term extraction and aspect polarity classification in four Chinese review datasets. Besides, the experimental results on the most commonly used SemEval-2014 task4 Restaurant and Laptop datasets outperform the state-of-the-art performance on the ATE and APC subtask.

A Multi-task Learning Model for Chinese-oriented Aspect Polarity Classification and Aspect Term Extraction

Text augmentation is one of the most effec- tive techniques to solve the critical problem of 002 insufficient data in text classification. Exist- 003 ing text augmentation methods achieve hopeful 004 performance in few-shot text data augmenta- 005 tion. However, these methods usually lead to 006 performance degeneration on public datasets 007 due to poor quality augmentation instances. 008 Our study shows that even employing pre- 009 trained language models, existing text augmen- 010 tation methods generate numerous low-quality 011 instances and lead to the feature space shift 012 problem in augmentation instances. However, 013 we note that the pre-trained language model 014 is good at finding low-quality instances pro- 015 vided that it has been fine-tuned on the target 016 dataset. To alleviate the feature space shift and 017 performance degeneration in existing text aug- 018 mentation methods, we propose B OOST A UG , 019 which reconsiders the role of the language 020 model in text augmentation and emphasizes 021 the augmentation instance filtering rather than 022 generation. We evaluate B OOST A UG on both 023 sentence-level text classification and aspect- 024 based sentiment classification. The experimen- 025 tal results on seven commonly used text clas- 026 sification datasets show that our augmentation 027 method obtains state-of-the-art performance. 028 Moreover, B OOST A UG is a flexible framework; 029 we release the code which can help improve 030 existing augmentation methods. 031

Augmentor or Filter? Reconsider the Role of Pre-trained Language Model in Text Classification Augmentation

The advancement of aspect-based sentiment analysis (ABSA) has urged the lack of a user-friendly framework that can largely lower the difficulty of reproducing state-of-the-art ABSA performance, especially for beginners. To meet the demand, we present \our, a modularized framework built on PyTorch for reproducible ABSA. To facilitate ABSA research, PyABSA supports several ABSA subtasks, including aspect term extraction, aspect sentiment classification, and end-to-end aspect-based sentiment analysis. Concretely, PyABSA integrates 29 models and 26 datasets. With just a few lines of code, the result of a model on a specific dataset can be reproduced. With a modularized design, PyABSA can also be flexiblely extended to considered models, datasets, and other related tasks. Besides, PyABSA highlights its data augmentation and annotation features, which significantly address data scarity. All are welcome to have a try at \url{https://github.com/yangheng95/PyABSA}.

PyABSA: A Modularized Framework for Reproducible Aspect-based Sentiment Analysis

Aspect-based Sentiment Classification (ABSC) is a challenging sub-task of traditional sentiment analysis. Due to the difficulty of handling potential correlations among sentiment polarities of multiple aspects, i.e., sentiment dependency, recent popular works tend to exploit syntactic information guiding sentiment dependency parsing. However, syntax information (e.g., syntactic dependency trees) usually occupies expensive computational resources in terms of the operation of the adjacent matrix. Instead, we define the consecutive aspects with the same sentiment as the sentiment cluster in the case that we find that most sentiment dependency occurs between adjacent aspects. Motivated by this finding, we propose the sentiment patterns (SP) to guide the model dependency learning. Thereafter, we introduce the local sentiment aggregating (LSA) mechanism to focus on learning the sentiment dependency in the sentiment cluster. The LSA is more efficient than existing dependency tree-based models due to the absence of additional dependency matrix constructing and modeling. Furthermore, we propose differential weighting for aggregation window building to measure the importance of sentiment dependency. Experiments on four public datasets show that our models achieve state-of-the-art performance with especially improvement on learning sentiment cluster.

Back to Reality: Leveraging Pattern-driven Modeling to Enable Affordable Sentiment Dependency Learning

Boosting Text Augmentation via Hybrid Instance Filtering Framework

Recent studies have shown that large pre-trained language models are vulnerable to adversarial attacks. Existing methods attempt to reconstruct the adversarial examples. However, these methods usually have limited performance in defense against adversarial examples, while also negatively impacting the performance on natural examples. To overcome this problem, we propose a method called Reactive Perturbation Defocusing (RPD). RPD uses an adversarial detector to identify adversarial examples and reduce false defenses on natural examples. Instead of reconstructing the adversaries, RPD injects safe perturbations into adversarial examples to distract the objective models from the malicious perturbations. Our experiments on three datasets, two objective models, and various adversarial attacks show that our proposed framework successfully repairs up to approximately 97% of correctly identified adversarial examples with only about a 2% performance decrease on natural examples. We also provide a demo of adversarial detection and repair based on our work.

Heng Yang

Papers

Augmentor or Filter? Reconsider the Role of Pre-trained Language Model in Text Classification Augmentation

PyABSA: A Modularized Framework for Reproducible Aspect-based Sentiment Analysis

Back to Reality: Leveraging Pattern-driven Modeling to Enable Affordable Sentiment Dependency Learning

Boosting Text Augmentation via Hybrid Instance Filtering Framework

Reactive Perturbation Defocusing for Textual Adversarial Defense