Towards preserving word order importance through Forced Invalidation
This addresses a key limitation in widely used models like BERT for natural language processing, though it is incremental as it builds on existing methods.
The paper tackles the problem that pre-trained language models are insensitive to word order, which harms natural language understanding tasks, and proposes Forced Invalidation to improve sensitivity, showing significant improvements in experiments.
Large pre-trained language models such as BERT have been widely used as a framework for natural language understanding (NLU) tasks. However, recent findings have revealed that pre-trained language models are insensitive to word order. The performance on NLU tasks remains unchanged even after randomly permuting the word of a sentence, where crucial syntactic information is destroyed. To help preserve the importance of word order, we propose a simple approach called Forced Invalidation (FI): forcing the model to identify permuted sequences as invalid samples. We perform an extensive evaluation of our approach on various English NLU and QA based tasks over BERT-based and attention-based models over word embeddings. Our experiments demonstrate that Forced Invalidation significantly improves the sensitivity of the models to word order.