CoreLM: Coreference-aware Language Model Fine-Tuning

TL;DR

CoreLM enhances language models by integrating explicit entity information through coreference-aware fine-tuning, improving performance on NLP tasks with reduced computational costs.

Contribution

This paper introduces CoreLM, a novel fine-tuning framework that incorporates entity representations into pretrained language models like GPT2, enabling better understanding of long texts efficiently.

Findings

Lower perplexity on GUMBY and LAMBDADA datasets

Improved accuracy on LAMBADA and Children's Book Test

Effective incorporation of coreference information

Abstract

Language Models are the underpin of all modern Natural Language Processing (NLP) tasks. The introduction of the Transformers architecture has contributed significantly into making Language Modeling very effective across many NLP task, leading to significant advancements in the field. However, Transformers come with a big computational cost, which grows quadratically with respect to the input length. This presents a challenge as to understand long texts requires a lot of context. In this paper, we propose a Fine-Tuning framework, named CoreLM, that extends the architecture of current Pretrained Language Models so that they incorporate explicit entity information. By introducing entity representations, we make available information outside the contextual space of the model, which results in a better Language Model for a fraction of the computational cost. We implement our approach using GPT2 and compare the fine-tuned model to the original. Our proposed model achieves a lower Perplexity in GUMBY and LAMBDADA datasets when compared to GPT2 and a fine-tuned version of GPT2 without any changes. We also compare the models' performance in terms of Accuracy in LAMBADA and Children's Book Test, with and without the use of model-created coreference annotations.