Learning to Detect Opinion Snippet for Aspect-Based Sentiment Analysis

Abstract

Aspect-based sentiment analysis (ABSA) is to predict the sentiment polarity towards a particular aspect in a sentence. Recently, this task has been widely addressed by the neural attention mechanism, which computes attention weights to softly select words for generating aspect-specific sentence representations. The attention is expected to concentrate on opinion words for accurate sentiment prediction. However, attention is prone to be distracted by noisy or misleading words, or opinion words from other aspects. In this paper, we propose an alternative hard-selection approach, which determines the start and end positions of the opinion snippet, and selects the words between these two positions for sentiment prediction. Specifically, we learn deep associations between the sentence and aspect, and the long-term dependencies within the sentence by leveraging the pre-trained BERT model. We further detect the opinion snippet by selfcritical reinforcement learning. Especially, experimental results demonstrate the effectiveness of our method and prove that our hardselection approach outperforms soft-selection approaches when handling multi-aspect sentences.

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

“…Thus, introducing a context-aware word embedding 3 layer pre-trained on large-scale datasets with deep LSTM (McCann et al, 2017;Peters et al, 2018;Howard and Ruder, 2018) or Transformer (Radford et al, 2018(Radford et al, , 2019Devlin et al, 2019; and Conneau, 2019; Yang et al, 2019;Dong et al, 2019) for fine-tuning a lightweight task-specific network using the labeled data has good potential for further enhancing the performance. Hu et al (2019a) have conducted some initial attempts to couple the deep contextualized word embedding layer with downstream neural models for the original ABSA task and establish the new state-of-the-art results. It encourages us to explore the potential of using such contextualized embeddings to the more difficult but practical task, i.e.…”

Context-Guided BERT for Targeted Aspect-Based Sentiment Analysis

“…Researchers have also tried to integrate attention mechanism with LSTMs to predict sentiment for target-aspect pairs (Ma, Peng, and Cambria 2018). With the recent success of BERT-based models, various papers have used BERT to generate contextualized embeddings for input sentences, which are then used to classify sentiment for target-aspect pairs (Huang and Carley 2019;Hu et al 2019). More recent papers have fine-tuned BERT for TABSA either by (i) constructing auxiliary sentences with different pairs of targets and aspects or (ii) modifying the top-most classification layer to also take in targets and aspects (Rietzler et al 2020;Sun, Huang, and Qiu 2019;.…”

Aspect-Based Sentiment Analysis in Hindi Language by Ensembling Pre-Trained mBERT Models

“…Most recently, the authors have used transfer-learning-based models. BERT has been used in various papers [27,28] to produce contextualized embeddings for input sentences, which were subsequently used to identify the sentiment for target-aspect pairs. The authors in [29,30] used BERT as the embedding layer, while the authors in [31] used a finetuning approach for BERT, with an additional layer acting as the classification layer.…”