Bidirectional LSTM-CRF Models for Sequence Tagging

Code

• github.com/JZ-LIANG/CRF-LSTM-NER
  tf★ 0
• github.com/akshay-gupta123/BI-LSTM-CRF_Tensorflow
  tf★ 0
• github.com/ngoquanghuy99/POS-Tagging-BiLSTM-CRF
  tf★ 0
• github.com/MindSpore-paper-code-3/code9/tree/main/lstm_crf
  mindspore★ 0
• github.com/determined22/zh-ner-tf
  tf★ 0
• github.com/aonotas/deep-crf
  none★ 0
• github.com/UcasLzz/ChineseWordSeg-POS
  none★ 0
• github.com/sumehta/bilstm_crf_extract
  pytorch★ 0
• github.com/baiyang2464/chatbot-base-on-Knowledge-Graph
  tf★ 0
• github.com/DimasDMM/diseases-ner
  none★ 0

Abstract

In this paper, we propose a variety of Long Short-Term Memory (LSTM) based models for sequence tagging. These models include LSTM networks, bidirectional LSTM (BI-LSTM) networks, LSTM with a Conditional Random Field (CRF) layer (LSTM-CRF) and bidirectional LSTM with a CRF layer (BI-LSTM-CRF). Our work is the first to apply a bidirectional LSTM CRF (denoted as BI-LSTM-CRF) model to NLP benchmark sequence tagging data sets. We show that the BI-LSTM-CRF model can efficiently use both past and future input features thanks to a bidirectional LSTM component. It can also use sentence level tag information thanks to a CRF layer. The BI-LSTM-CRF model can produce state of the art (or close to) accuracy on POS, chunking and NER data sets. In addition, it is robust and has less dependence on word embedding as compared to previous observations.

Tasks

Benchmark Results

Reproductions