Qimin Zhou


pdf bib
ZQM at SemEval-2019 Task9: A Single Layer CNN Based on Pre-trained Model for Suggestion Mining
Qimin Zhou | Zhengxin Zhang | Hao Wu | Linmao Wang
Proceedings of the 13th International Workshop on Semantic Evaluation

This paper describes our system that competed at SemEval 2019 Task 9 - SubTask A: ”Sug- gestion Mining from Online Reviews and Forums”. Our system fuses the convolutional neural network and the latest BERT model to conduct suggestion mining. In our system, the input of convolutional neural network is the embedding vectors which are drawn from the pre-trained BERT model. And to enhance the effectiveness of the whole system, the pre-trained BERT model is fine-tuned by provided datasets before the procedure of embedding vectors extraction. Empirical results show the effectiveness of our model which obtained 9th position out of 34 teams with F1 score equals to 0.715.


pdf bib
NLPZZX at SemEval-2018 Task 1: Using Ensemble Method for Emotion and Sentiment Intensity Determination
Zhengxin Zhang | Qimin Zhou | Hao Wu
Proceedings of The 12th International Workshop on Semantic Evaluation

In this paper, we put forward a system that competed at SemEval-2018 Task 1: “Affect in Tweets”. Our system uses a simple yet effective ensemble method which combines several neural network components. We participate in two subtasks for English tweets: EI-reg and V-reg. For two subtasks, different combinations of neural components are examined. For EI-reg, our system achieves an accuracy of 0.727 in Pearson Correlation Coefficient (all instances) and an accuracy of 0.555 in Pearson Correlation Coefficient (0.5-1). For V-reg, the achieved accuracy scores are respectively 0.835 and 0.670

pdf bib
NLP at IEST 2018: BiLSTM-Attention and LSTM-Attention via Soft Voting in Emotion Classification
Qimin Zhou | Hao Wu
Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis

This paper describes our method that competed at WASSA2018 Implicit Emotion Shared Task. The goal of this task is to classify the emotions of excluded words in tweets into six different classes: sad, joy, disgust, surprise, anger and fear. For this, we examine a BiLSTM architecture with attention mechanism (BiLSTM-Attention) and a LSTM architecture with attention mechanism (LSTM-Attention), and try different dropout rates based on these two models. We then exploit an ensemble of these methods to give the final prediction which improves the model performance significantly compared with the baseline model. The proposed method achieves 7th position out of 30 teams and outperforms the baseline method by 12.5% in terms of macro F1.