Open-Domain Targeted Sentiment Analysis via Span-Based Extraction and Classification

Abstract

Open-domain targeted sentiment analysis aims to detect opinion targets along with their sentiment polarities from a sentence. Prior work typically formulates this task as a sequence tagging problem. However, such formulation suffers from problems such as huge search space and sentiment inconsistency. To address these problems, we propose a span-based extract-then-classify framework, where multiple opinion targets are directly extracted from the sentence under the supervision of target span boundaries, and corresponding polarities are then classified using their span representations. We further investigate three approaches under this framework, namely the pipeline, joint, and collapsed models. Experiments on three benchmark datasets show that our approach consistently outperforms the sequence tagging baseline. Moreover, we find that the pipeline model achieves the best performance compared with the other two models.

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

“…Such setting makes them less practical in real-world scenarios since manual annotation of the finegrained aspect mentions/categories is quite expensive. 5 Hu et al (2019b) introduce BERT to handle the E2E-ABSA problem but their focus is to design a task-specific architecture rather than exploring the potential of BERT. Figure 1: Overview of the designed model.…”

Knowledge-Guided Sentiment Analysis Via Learning From Natural Language Explanations

“…In this section, we will briefly review related works on the sentiment classification [11,13], knowledge-aware sentiment analysis [9,14], and natural language explanation [5,16,23] classification. Sentiment Analysis Sentiment analysis and emotion recognition have always attracted attention in multiple fields such as NL processing, psychology, and cognitive science.…”

A Question Answering-Based Framework for One-Step Event Argument Extraction

“…Inspired by span-based methods [49], we adopt a heuristic decoding method to choose the answer spans from top-K spans, as shown in Algorithm 1. First, Top-M indices are chosen from the predicted start and end positions according to their logits f s and f e (line 2).…”