Detecting Textual Adversarial Examples Based on Distributional Characteristics of Data Representations
Wei Emma Zhang
Proceedings of the 7th Workshop on Representation Learning for NLP
Although deep neural networks have achieved state-of-the-art performance in various machine learning tasks, adversarial examples, constructed by adding small non-random perturbations to correctly classified inputs, successfully fool highly expressive deep classifiers into incorrect predictions. Approaches to adversarial attacks in natural language tasks have boomed in the last five years using character-level, word-level, phrase-level, or sentence-level textual perturbations. While there is some work in NLP on defending against such attacks through proactive methods, like adversarial training, there is to our knowledge no effective general reactive approaches to defence via detection of textual adversarial examples such as is found in the image processing literature. In this paper, we propose two new reactive methods for NLP to fill this gap, which unlike the few limited application baselines from NLP are based entirely on distribution characteristics of learned representations”:" we adapt one from the image processing literature (Local Intrinsic Dimensionality (LID)), and propose a novel one (MultiDistance Representation Ensemble Method (MDRE)). Adapted LID and MDRE obtain state-of-the-art results on character-level, word-level, and phrase-level attacks on the IMDB dataset as well as on the later two with respect to the MultiNLI dataset. For future research, we publish our code .
ABSA-Bench: Towards the Unified Evaluation of Aspect-based Sentiment Analysis Research
Wei Emma Zhang
Proceedings of the The 18th Annual Workshop of the Australasian Language Technology Association
Aspect-Based Sentiment Analysis (ABSA)has gained much attention in recent years. It is the task of identifying fine-grained opinionpolarity towards a specific aspect associated with a given target. However, there is a lack of benchmarking platform to provide a unified environment under consistent evaluation criteria for ABSA, resulting in the difficulties for fair comparisons. In this work, we address this issue and define a benchmark, ABSA-Bench, by unifying the evaluation protocols and the pre-processed publicly available datasets in a Web-based platform. ABSA-Bench provides two means of evaluations for participants to submit their predictions or models for online evaluation. Performances are ranked in the leader board and a discussion forum is supported to serve as a collaborative platform for academics and researchers to discuss queries.
Aspect Extraction Using Coreference Resolution and Unsupervised Filtering
Wei Emma Zhang
Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing: Student Research Workshop
Aspect extraction is a widely researched field of natural language processing in which aspects are identified from the text as a means for information. For example, in aspect-based sentiment analysis (ABSA), aspects need to be first identified. Previous studies have introduced various approaches to increasing accuracy, although leaving room for further improvement. In a practical situation where the examined dataset is lacking labels, to fine-tune the process a novel unsupervised approach is proposed, combining a lexical rule-based approach with coreference resolution. The model increases accuracy through the recognition and removal of coreferring aspects. Experimental evaluations are performed on two benchmark datasets, demonstrating the greater performance of our approach to extracting coherent aspects through outperforming the baseline approaches.