Neural Fine-Grained Sentiment Analysis With Unsupervised and Transfer Learning Approaches
Dr Ng Hwee Tou, Provost'S Chair Professor, School of Computing
Dr Daniel Dahlmeier, SAP
COM2 Level 4
Executive Classroom, COM2-04-02
Abstract:
We study the problem of aspect-based sentiment analysis, also referred to as fine-grained sentiment analysis, which is an important area in sentiment analysis that has seen a lot of research effort and real-world applications. Different from document-level and sentence-level sentiment analysis which only assign an overall polarity score to an input text, aspect-level analysis is based on the idea that an opinion should include a sentiment and a target; therefore, it aims to identify the sentiment-target pairs from a given text. For example, the review sentence "Great food but the service is dreadful" evaluates two targets -- "food' (positive) and 'service' (negative).
The development of aspect-based sentiment analysis systems generally faces two major challenges. First, this problem is naturally more difficult compared to coarse-grained sentiment analysis because more fine-grained features are needed for aspect-level predictions. Second, the training resources for this task are limited as it is expensive to obtain fine-grained annotated data. Therefore, in this thesis, we focus on two objectives: (1) designing flexible and effective models for fine-grained sentiment analysis; (2) leverage cheaply available resources, such as unlabeled data and transfer learning approaches.
Specifically, we study two core problems of aspect-based sentiment analysis -- aspect extraction and aspect-dependent sentiment classification. The former aims to extract aspects from opinionated corpus, while the latter aims to predict the sentiments on extracted aspects. In this thesis, we first describe a novel neural attention approach for extracting aspects in an unsupervised learning setting. We demonstrate that the proposed model is able to extract highly meaningful and coherent aspects.
For aspect-dependent sentiment classification, we first propose an effective attention modeling approach to more accurately assign the right opinion context for each target in a sentence. We further propose approaches to transfer knowledge from document-level annotated corpora to boost the performance of aspect-dependent sentiment classification.
Finally, we develop an end-to-end solution that simultaneously performs the two fine-grained tasks. It also allows the fine-grained tasks to be trained together with the relevant coarse-grained tasks, leveraging the knowledge from larger corpora to alleviate the issue of limited fine-grained training resources. The proposed model explicitly enables the informative interactions between different tasks to better exploit the joint information.