Thanh-Son Nguyen


2020

pdf bib
Structured Self-AttentionWeights Encode Semantics in Sentiment Analysis
Zhengxuan Wu | Thanh-Son Nguyen | Desmond Ong
Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP

Neural attention, especially the self-attention made popular by the Transformer, has become the workhorse of state-of-the-art natural language processing (NLP) models. Very recent work suggests that the self-attention in the Transformer encodes syntactic information; Here, we show that self-attention scores encode semantics by considering sentiment analysis tasks. In contrast to gradient-based feature attribution methods, we propose a simple and effective Layer-wise Attention Tracing (LAT) method to analyze structured attention weights. We apply our method to Transformer models trained on two tasks that have surface dissimilarities, but share common semantics—sentiment analysis of movie reviews and time-series valence prediction in life story narratives. Across both tasks, words with high aggregated attention weights were rich in emotional semantics, as quantitatively validated by an emotion lexicon labeled by human annotators. Our results show that structured attention weights encode rich semantics in sentiment analysis, and match human interpretations of semantics.

pdf bib
Multimodal Review Generation with Privacy and Fairness Awareness
Xuan-Son Vu | Thanh-Son Nguyen | Duc-Trong Le | Lili Jiang
Proceedings of the 28th International Conference on Computational Linguistics

Users express their opinions towards entities (e.g., restaurants) via online reviews which can be in diverse forms such as text, ratings, and images. Modeling reviews are advantageous for user behavior understanding which, in turn, supports various user-oriented tasks such as recommendation, sentiment analysis, and review generation. In this paper, we propose MG-PriFair, a multimodal neural-based framework, which generates personalized reviews with privacy and fairness awareness. Motivated by the fact that reviews might contain personal information and sentiment bias, we propose a novel differentially private (dp)-embedding model for training privacy guaranteed embeddings and an evaluation approach for sentiment fairness in the food-review domain. Experiments on our novel review dataset show that MG-PriFair is capable of generating plausibly long reviews while controlling the amount of exploited user data and using the least sentiment biased word embeddings. To the best of our knowledge, we are the first to bring user privacy and sentiment fairness into the review generation task. The dataset and source codes are available at https://github.com/ReML-AI/MG-PriFair.