Building Language Models for Text with Named Entities

Md Rizwan Parvez, Saikat Chakraborty, Baishakhi Ray, Kai-Wei Chang
5/13/2018
cs.CL

Official code: uclanlp/NamedEntityLanguageModel (32 stars, BSD-3-Clause, last commit 2019-06-14).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

uclanlp/NamedEntityLanguageModelOfficial100%
BSD-3-Clause
325Shell, PythonMay 11, 20187 years agoBSD-3-Clause

Similar Papers

ToNER: Type-oriented Named Entity Recognition with Generative Language Model

86% match1 repo62024

Informed Named Entity Recognition Decoding for Generative Language Models

85% match2023

Inspire the Large Language Model by External Knowledge on BioMedical Named Entity Recognition

84% match2023

UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition

84% match2023

Deep Learning Based Named Entity Recognition Models for Recipes

83% match2024

All Entities are Not Created Equal: Examining the Long Tail for Ultra-Fine Entity Typing

82% match1 repo2024

Cite this paper

@article{parvez2018building,
  title  = {Building Language Models for Text with Named Entities},
  author = {Md Rizwan Parvez and Saikat Chakraborty and Baishakhi Ray and Kai-Wei Chang},
  year   = {2018},
  eprint = {1805.04836},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1805.04836}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1805.04836.svg)](https://codeofpaper.com/paper/1805.04836)

Discussion