SA-ASBA: a hybrid model for aspect-based sentiment analysis using synthetic attention in pre-trained language BERT model with extreme gradient boosting

Aspect-based sentiment analysis (ABSA) has become a prevalent task in recent years. How-ever, the absence of a uniﬁed framework in the present ABSA research makes it chal-lenging to compare different models’ performance fairly. Therefore, we develop an open-source ABSA framework, namely P Y ABSA . Besides, previous efforts usually neglect the precursor aspect term extraction (ASC) subtask and focus on the aspect sentiment classiﬁcation (ATE) subtask, while P Y ABSA includes the features of aspect term extraction, aspect sentiment classiﬁcation, and text classiﬁcation. Furthermore, multiple ABSA subtasks can be adapted to P Y ABSA owing to its modular architecture. To facilitate ABSA applications, P Y ABSA seamless integrates multilingual modelling, automated dataset annotation, etc., which are helpful in deploying ABSA services. In ASC and ATE, P Y ABSA provides up to 33 and 7 built-in models, respectively, while all the models provide quick training and instant inference. Besides, P Y ABSA contains to 180 K + ABSA examples from 21 augmented ABSA datasets for applications and studies. P Y ABSA is available at https://github. com/yangheng95/PyABSA .

PyABSA: Open Framework for Aspect-based Sentiment Analysis

A knowledge-enhanced interactive graph convolutional network for aspect-based sentiment analysis

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 analysis(ABSA) aims to identify the sentiment polarity of specific aspects in sentences, which can more accurately mine the sentiment polarity of users towards different aspects. Most of the existing works derive the sentiment features of specific aspects by interactively learning the dependencies between different aspects of the context. However, the above work has neglected to use the external affective commonsense knowledge to augment the ability of the Graph Convolutional Networks(GCNs) to interactively capture sentiment dependencies of the inter-aspect words in different contexts. In addition, compared to the ABSA research in English, the existing research pays less attention to the Chinese-oriented research. Meanwhile, multi-head self-sttention(MHSA) is applied to extract richer context syntax and semantic interaction features. In this paper, we propose a novel knowledge-aware model in which affective knowledge augments interactive GCN for Chinese-oriented ABSA, namely AKM-IGCN. Moreover, this model can be applied to effectively analyze both Chinese and English comments simultaneously. Hence, we conducted experiments on four Chinese datasets(Camera, Phone, Notebook and Car) and six English benchmark datasets(Restaurant14, Restaurant15, Restaurant16, Twitter, MAMS, Tshirt). Experimental results illustrate that our proposed model outperforms or approaches state-of-the-art models.

https://ieeexplore.ieee.org/ielx7/6287639/6514899/09980354.pdf

Affective Knowledge Augmented Interactive Graph Convolutional Network for Chinese-Oriented Aspect-Based Sentiment Analysis

Combining dynamic local context focus and dependency cluster attention for aspect-level sentiment classification

Despite the rapid utilization of immunotherapy, emerging challenges to the current immune checkpoint blockade need to be resolved. Here, we report that elevation of CD73 levels due to its aberrant turnover is correlated with poor prognosis in immune-cold triple-negative breast cancers (TNBCs). We have identified TRIM21 as an E3 ligase that governs CD73 destruction. Disruption of TRIM21 stabilizes CD73 that in turn enhances CD73-catalyzed production of adenosine, resulting in the suppression of CD8+ T cell function. Replacement of lysine 133, 208, 262, and 321 residues by arginine on CD73 attenuated CD73 ubiquitylation and degradation. Diminishing of CD73 ubiquitylation remarkably promotes tumor growth and impedes antitumor immunity. In addition, a TRIM21high/CD73low signature in a subgroup of human breast malignancies was associated with a favorable immune profile. Collectively, our findings uncover a mechanism that governs CD73 proteolysis and point to a new therapeutic strategy by modulating CD73 ubiquitylation.

https://www.science.org/doi/pdf/10.1126/sciadv.add6626?download=true

Junlong Chi

Papers

Combining dynamic local context focus and dependency cluster attention for aspect-level sentiment classification

Proteolytic regulation of CD73 by TRIM21 orchestrates tumor immunogenicity

Abstract 1818: Development of MGAT1 Inhibitors Based on a Novel High-throughput Screening System to Promote Breast Cancer Immunotherapy