Go Forth and Prosper: Language Modeling with Ancient Textual History
This addresses the challenge of limited context windows in language modeling for applications like text generation and analysis, though it is incremental as it builds on existing pretrained models.
The paper tackles the problem of improving document-level language models by using text outside the current context window, resulting in a 7% perplexity reduction on Wikipedia and 12% on scientific texts.
We introduce a technique for improving document-level language models (LM) by leveraging "ancient history": text that is outside the LM's current context window. We learn an auxiliary function to select spans from the ancient history which can help the LM to predict future text. The selected text spans are then copied directly into the LM's context window, replacing less predictive spans. This method can improve perplexity of pretrained LMs with no updates to the LM's own parameters. We further observe that an auxiliary function trained in a specific textual domain like Wikipedia will also work in a substantially different domain such as scientific publications. With this technique we see a 7 percent perplexity reduction on Wikipedia articles, and a 12 percent perplexity reduction on scientific texts.