Stateful Memory-Augmented Transformers for Dialogue Modeling

15 Sep 2022  ·  Qingyang Wu, Zhou Yu ·

Transformer encoder-decoder models have shown impressive performance in dialogue modeling. However, as Transformers are inefficient in processing long sequences, dialogue history length often needs to be truncated. To address this problem, we propose a new memory-augmented Transformer that is compatible with existing pre-trained encoder-decoder models and enables efficient preservation of history information. It incorporates a separate memory module alongside the pre-trained Transformer to effectively interchange information between the memory states and the current input context. We evaluate our model on three dialogue datasets and two language modeling datasets. Experimental results show that our method has achieved superior efficiency and performance compared to other pre-trained Transformer baselines.

PDF Abstract
No code implementations yet. Submit your code now


Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.