Semantic and Syntactic Enhanced Aspect Sentiment Triplet Extraction

Abstract

Aspect Sentiment Triplet Extraction (ASTE) aims to extract triplets from sentences, where each triplet includes an entity, its associated sentiment, and the opinion span explaining the reason for the sentiment. Most existing research addresses this problem in a multi-stage pipeline manner, which neglects the mutual information between such three elements and has the problem of error propagation. In this paper, we propose a Semantic and Syntactic Enhanced aspect Sentiment triplet Extraction model (S 3 E 2 ) to fully exploit the syntactic and semantic relationships between the triplet elements and jointly extract them. Specifically, we design a Graph-Sequence duel representation and modeling paradigm for the task of ASTE: we represent the semantic and syntactic relationships between word pairs in a sentence by graph and encode it by Graph Neural Networks (GNNs), as well as modeling the original sentence by LSTM to preserve the sequential information. Under this setting, we further apply a more efficient inference strategy for the extraction of triplets. Extensive evaluations on four benchmark datasets show that S 3 E 2 significantly outperforms existing approaches, which proves our S 3 E 2 's superiority and flexibility in an end-to-end fashion.

Enhanced Multi-Channel Graph Convolutional Network for Aspect Sentiment Triplet Extraction

“…Peng-two-stage+IOG and IMN+IOG are proposed by Wu et al (2020a). 2) End-to-end methods: GTS-CNN, GTS-BiLSTM, GTS-BERT (Wu et al, 2020a), OTE-MTL , JET-BERT , S 3 E 2 (Chen et al, 2021b) and BART-ABSA (Yan et al, 2021). 3) MRCbased methods: BMRC (Chen et al, 2021a) is a multi-turn MRC-based model, which is end-to-end in the training phase, but works in pipeline during the inference phase.…”

“…To utilize the associations among the multiple subtasks, Mao et al (2021) and Chen et al (2021a) formulate the ASTE task as a multi-turn machine reading comprehension (MRC) problem and design a model based on BERT to jointly train multiple subtasks. Meanwhile, some efforts devote to extracting the triplets in an end-to-end framework Wu et al, 2020a;Chen et al, 2021b;Yan et al, 2021), which is constructed mainly by designing new tagging scheme. Although previous works have achieved significant fruits, there exists still several challenges.…”

Deep learning for aspect-based sentiment analysis: a review

“… Zhang et al (2020) proposed a multi-task learning framework to jointly extract aspect terms and opinion terms and simultaneously parses sentiment dependencies and used biaffine scorer ( Dozat & Manning, 2017 ) to capture the interaction of two words in each word pair. Chen et al (2021b) proposed an approach by considering the rich syntactic dependence and semantic word similarity in sentences (such as self-interaction relations, neighbor relations, and dependency relations), and adopted GraphSAGE ( Hamilton, Ying & Leskovec, 2017 ) to obtain the rich feature representation of words. Since there are too many aspect terms in the corpus , and the same aspect term may have different descriptions, Cai, Xia & Yu (2021) proposed ASQE task, took ACD task as an important sub-task of multi-task ABSA, and proposed four baseline methods.…”

Opinion Triplet Extraction for Aspect-Based Sentiment Analysis Using Co-Extraction Approach

“…The use of span representation with width representation and span pair representation with distance representation which proposed by Xu et al (2021) might give better representation and leads to better performance. A different approach might also leads to better performance in opinion triplet extraction, for example using Graph Neural Network (GNN) (Chen et al, 2021), using a generative text to text model (Zhang et al, 2021), decomposing triplet extraction into target tagging, opinion tagging and sentiment tagging (Chen et al, 2022), or uses span-sharing joint extraction (Li et al, 2022) . The importance of consistency in the data annotation process also needs to be emphasized, such as the various aspects that needs to be marked, ACKNOWLEDGMENT…”