Utilizing BERT Intermediate Layers for Aspect Based Sentiment Analysis and Natural Language Inference
This work addresses a specific bottleneck in NLP tasks for researchers and practitioners by improving model efficiency and performance, though it is incremental as it builds on existing BERT-based methods.
The paper tackles the problem of aspect-based sentiment analysis and natural language inference by utilizing intermediate layers of BERT, which are typically ignored, to enhance fine-tuning performance, achieving improved results as demonstrated in experiments.
Aspect based sentiment analysis aims to identify the sentimental tendency towards a given aspect in text. Fine-tuning of pretrained BERT performs excellent on this task and achieves state-of-the-art performances. Existing BERT-based works only utilize the last output layer of BERT and ignore the semantic knowledge in the intermediate layers. This paper explores the potential of utilizing BERT intermediate layers to enhance the performance of fine-tuning of BERT. To the best of our knowledge, no existing work has been done on this research. To show the generality, we also apply this approach to a natural language inference task. Experimental results demonstrate the effectiveness and generality of the proposed approach.