A Unified Model for Opinion Target Extraction and Target Sentiment Prediction

By Xin Li, Lidong Bing, Piji Li, Wai Lam. AAAI Conference on Artificial Intelligence, 2018

354 citations recorded by the source corpus.

Target-based sentiment analysis involves opinion target extraction and target sentiment classification. However, most of the existing works usually studied one of these two sub-tasks alone, which hinders their practical use. This paper aims to solve the complete task of target-based sentiment analysis in an end-to-end fashion, and presents a novel unified model which applies a unified tagging scheme. Our framework involves two stacked recurrent neural networks: The upper one predicts the unified tags to produce the final output results of the primary target-based sentiment analysis; The lower one performs an auxiliary target boundary prediction aiming at guiding the upper network to improve the performance of the primary task. To explore the inter-task dependency, we propose to explicitly model the constrained transitions from target boundaries to target sentiment polarities. We also propose to maintain the sentiment consistency within an opinion target via a gate mechanism which models the relation between the features for the current word and the previous word. We conduct extensive experiments on three benchmark datasets and our framework achieves consistently superior results.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/e200b89dec14afe304e0e11ad0c7df07a50f0244

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

Citations in the corpus

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”
Position-Aware Tagging for Aspect Sentiment Triplet Extraction (2020, background): “…and Li, 2018; Wang and Lu, 2018; Wang et al., 2018; Li et al., 2018a; Peng et al., 2018; Xu et al., 2020) or joint extraction of targets as well as sentiment associated with each target (Mitchell et al., 2013; Zhang et al., 2015; Li and Lu, 2017; Ma et al., 2018; Li and Lu, 2019; Li et al., 2019).”
Beneath the Tip of the Iceberg: Current Challenges and New Directions in Sentiment Analysis Research (2020, background): “, 2016), and CRF-based approaches by framing both the sub-tasks as sequence labeling problems (Li et al., 2019; Luo et al., 2019).”
Exploiting BERT for End-to-End Aspect-based Sentiment Analysis (2019, methodology): “Existing Models (Li et al., 2019a)\ 61.”
Knowing What, How and Why: A Near Complete Solution for Aspect-based Sentiment Analysis (2019, methodology): “Speciﬁcally, we couple a uniﬁed tagging system by following (Li et al. 2019a) for aspect extraction and sentiment classiﬁcation, and a BIO-like tagging system for opinion extraction, as shown in Table 1.”