TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Code Generation	Android Repos	Entity Type Model	Perplexity	2.65	# 1
Recipe Generation	Now You're Cooking!	Entity Type Model	Perplexity	9.67	# 1

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/building-language-models-for-text-with-named/code-generation-on-android-repos)](https://paperswithcode.com/sota/code-generation-on-android-repos?p=building-language-models-for-text-with-named)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/building-language-models-for-text-with-named/recipe-generation-on-now-youre-cooking)](https://paperswithcode.com/sota/recipe-generation-on-now-youre-cooking?p=building-language-models-for-text-with-named)`

Building Language Models for Text with Named Entities

ACL 2018 · Md. Rizwan Parvez, Saikat Chakraborty, Baishakhi Ray, Kai-Wei Chang ·

Text in many domains involves a significant amount of named entities. Predict- ing the entity names is often challenging for a language model as they appear less frequent on the training corpus. In this paper, we propose a novel and effective approach to building a discriminative language model which can learn the entity names by leveraging their entity type information. We also introduce two benchmark datasets based on recipes and Java programming codes, on which we evalu- ate the proposed model. Experimental re- sults show that our model achieves 52.2% better perplexity in recipe generation and 22.06% on code generation than the state-of-the-art language models.