Exploiting BERT for End-to-End Aspect-based Sentiment Analysis

By Xin Li, Lidong Bing, Wenxuan Zhang, Wai Lam. Conference on Empirical Methods in Natural Language Processing, 2019

322 citations recorded by the source corpus.

In this paper, we investigate the modeling power of contextualized embeddings from pre-trained language models, e.g. BERT, on the E2E-ABSA task. Specifically, we build a series of simple yet insightful neural baselines to deal with E2E-ABSA. The experimental results show that even with a simple linear classification layer, our BERT-based architecture can outperform state-of-the-art works. Besides, we also standardize the comparative study by consistently utilizing a hold-out validation dataset for model selection, which is largely ignored by previous works. Therefore, our work can serve as a BERT-based benchmark for E2E-ABSA.

Subfields: Artificial Intelligence, Information Systems

View Paper: https://www.semanticscholar.org/paper/a23975683b044a871e39afb7781662f5eccaa4ba

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Yulia Tsvetkov
2. Lidong Bing
3. Wenxuan Zhang
4. Frank K. Soong
5. Lei He
6. Wai Lam
7. Xin Li
8. Yang Deng

In Information Systems

1. Wenxuan Zhang
2. Saif M. Mohammad
3. Wai Lam
4. Yulia Tsvetkov
5. Lidong Bing
6. Chaitanya Kulkarni
7. Chan Young Park
8. Mayur Wankhade

Citations in the corpus

• A survey on sentiment analysis methods, applications, and challenges (2022, methodology): “Their (Li et al. 2019a) linear SVM model performed marvelously with an F1 score of 83.4 percent and a mean AUC of 0.896.”
• Ranking Transfer Languages with Pragmatically-Motivated Features for Multilingual Sentiment Analysis (2020, background): “…in Appendix A.1 task, as it showed strong results in various text classification tasks in cross-lingual settings (Sun et al., 2019; Xu et al., 2019; Li et al., 2019). mBERT is a multilingual extension of BERT pretrained with 104 different languages, including the 16 languages we used throughout…”
• Sentiment Analysis: Detecting Valence, Emotions, and Other Affectual States from Text (2016, background): “An offshoot of work on the sentiment analysis of streams of text is work on visualizing emotion in these text streams Lu, Hu, Wang, Kumar, Liu, and Maciejewski (2015) visualized sentiment in geolocated ebola tweets; Gregory, Chinchor, Whitney, Carter, Hetzler, and Turner (2006) visualized reviews of”
• Aspect Sentiment Quad Prediction as Paraphrase Generation (2021, methodology): “We adopt two types of baselines: 1) pipeline-based methods including CMLA+ (Wang et al., 2017), Li-unified-R (Li et al., 2019a), Peng-pipeline (Peng et al., 2020) which firstly extract aspect and opinion terms separately, then conduct the pairing; Two-stage (Huang et al., 2021) which proposes a two-st”
• Improving Prosody with Linguistic and Bert Derived Features in Multi-Speaker Based Mandarin Chinese Neural TTS (2020, methodology): “Similar Bert-CRF model has been applied to tasks like Named Entity Recognition (NER) [23] and sentiment analysis [24].”