Meng Li


2023

pdf bib
Target-to-Source Augmentation for Aspect Sentiment Triplet Extraction
Yice Zhang | Yifan Yang | Meng Li | Bin Liang | Shiwei Chen | Ruifeng Xu
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Aspect Sentiment Triplet Extraction (ASTE) is an important task in sentiment analysis, aiming to extract aspect-level opinions and sentiments from user-generated reviews. The fine-grained nature of ASTE incurs a high annotation cost, while the scarcity of annotated data limits the performance of existing methods. This paper exploits data augmentation to address this issue. Traditional augmentation methods typically modify the input sentences of existing samples via heuristic rules or language models, which have shown success in text classification tasks. However, applying these methods to fine-grained tasks like ASTE poses challenges in generating diverse augmented samples while maintaining alignment between modified sentences and origin labels. Therefore, this paper proposes a target-to-source augmentation approach for ASTE. Our approach focuses on learning a generator that can directly generate new sentences based on labels and syntactic templates. With this generator, we can generate a substantial number of diverse augmented samples by mixing labels and syntactic templates from different samples. Besides, to ensure the quality of the generated sentence, we introduce fluency and alignment discriminators to provide feedback on the generated sentence and then use this feedback to optimize the generator via a reinforcement learning framework. Experiments demonstrate that our approach significantly enhances the performance of existing ASTE models.

2018

pdf bib
ISCLAB at SemEval-2018 Task 1: UIR-Miner for Affect in Tweets
Meng Li | Zhenyuan Dong | Zhihao Fan | Kongming Meng | Jinghua Cao | Guanqi Ding | Yuhan Liu | Jiawei Shan | Binyang Li
Proceedings of the 12th International Workshop on Semantic Evaluation

This paper presents a UIR-Miner system for emotion and sentiment analysis evaluation in Twitter in SemEval 2018. Our system consists of three main modules: preprocessing module, stacking module to solve the intensity prediction of emotion and sentiment, LSTM network module to solve multi-label classification, and the hierarchical attention network module for solving emotion and sentiment classification problem. According to the metrics of SemEval 2018, our system gets the final scores of 0.636, 0.531, 0.731, 0.708, and 0.408 on 5 subtasks, respectively.