An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis

Aspect-based sentiment analysis produces a list of aspect terms and their corresponding sentiments for a natural language sentence. This task is usually done in a pipeline manner, with aspect term extraction performed first, followed by sentiment predictions toward the extracted aspect terms. While easier to develop, such an approach does not fully exploit joint information from the two subtasks and does not use all available sources of training information that might be helpful, such as document-level labeled sentiment corpus. In this paper, we propose an interactive multi-task learning network (IMN) which is able to jointly learn multiple related tasks simultaneously at both the token level as well as the document level. Unlike conventional multi-task learning methods that rely on learning common features for the different tasks, IMN introduces a message passing architecture where information is iteratively passed to different tasks through a shared set of latent variables. Experimental results demonstrate superior performance of the proposed method against multiple baselines on three benchmark datasets.

PDF Abstract ACL 2019 PDF ACL 2019 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Aspect Term Extraction and Sentiment Classification SemEval IMN-BERT Avg F1 64.23 # 5
Restaurant 2014 (F1) 70.72 # 5
Laptop 2014 (F1) 61.73 # 4
Restaurant 2015 (F1) 60.22 # 5
Aspect-Based Sentiment Analysis SemEval 2014 Task 4 Laptop IMN F1 58.37 # 5
Sentiment Analysis SemEval 2014 Task 4 Subtask 1+2 IMN F1 58.37 # 6
Aspect-Based Sentiment Analysis SemEval 2014 Task 4 Subtask 1+2 IMN F1 58.37 # 6
Aspect-Based Sentiment Analysis SemEval 2014 Task 4 Sub Task 2 IMN Restaurant (Acc) 83.89 # 12
Laptop (Acc) 75.36 # 20
Mean Acc (Restaurant + Laptop) 79.63 # 15

Methods


No methods listed for this paper. Add relevant methods here