A sequence tagging model and method based on a fine-grained word representation model

Abstract

The invention provides a sequence tagging model based on a fine-grained word representation model, which is used for sequence tagging tasks and belongs to the fields of computer application and natural language processing. The model structure of the present invention is mainly composed of three parts: feature representation layer, BiLSTM and CRF layer. When using this model for sequence tagging tasks, a character-level word representation model Finger based on the attention mechanism is firstly proposed to fuse morphological information and word character information, and then the Finger and BiLSTM-CRF models jointly complete the sequence tagging task, and finally The method achieves an F1 of 91.09% on the CoNLL 2003 dataset in an end-to-end manner without any feature engineering. Experiments show that the Finger model designed by the present invention significantly improves the recall rate of the sequence tagging system, thereby significantly improving the recognition ability of the model.

Description

technical field [0001] The invention belongs to the fields of computer application and natural language processing, and relates to a character-level model based on an attention mechanism and its application in sequence labeling tasks. The invention proposes a sequence labeling model based on a fine-grained word representation model. The main innovation is to design a fine-grained word representation model based on attention mechanism to describe the morphological information of words more accurately, globally and dynamically, and then propose a sequence tagging model based on the word representation model. The sequence annotation model not only has high sequence annotation ability, but also does not require feature engineering, and has strong interpretability. Background technique [0002] Sequence tagging tasks such as Part-of-Speech Tagging and Named Entity Recognition (NER) are the basic work in the field of natural language processing. Taking NER as an example, its mai...

AI Technical Summary

Problems solved by technology

Although the Attention mechanism has made some progress in NER tasks, how to effectively integrate the dynamics and globality of the Attention mechanism into the character-level model needs to be further explored.

Images