Improving Neural Language Models with a Continuous Cache
read the original abstract
We propose an extension to neural network language models to adapt their prediction to the recent history. Our model is a simplified version of memory augmented networks, which stores past hidden activations as memory and accesses them through a dot product with the current hidden activation. This mechanism is very efficient and scales to very large memory sizes. We also draw a link between the use of external memory in neural network and cache models used with count based language models. We demonstrate on several language model datasets that our approach performs significantly better than recent memory augmented networks.
This paper has not been read by Pith yet.
Forward citations
Cited by 3 Pith papers
-
On the Importance and Evaluation of Narrativity in Natural Language AI Explanations
XAI explanations should be narratives with continuous structure, cause-effect, fluency and diversity, and new metrics are needed to evaluate this better than standard NLP scores.
-
Compressive Transformers for Long-Range Sequence Modelling
Compressive Transformer sets new records on WikiText-103 (17.1 ppl) and Enwik8 (0.97 bpc) via memory compression and introduces the PG-19 long-range language benchmark.
-
ARMIN: Towards a More Efficient and Light-weight Recurrent Memory Network
ARMIN introduces auto-addressing via hidden states and a novel RNN cell to produce a lighter recurrent memory network with lower overhead than existing MANNs or vanilla LSTMs.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.