Vietnamese event entity recognition method fusing dictionary and adversarial migration

Abstract

The invention relates to a Vietnamese event entity recognition method fusing a dictionary and adversarial migration. The Vietnamese is taken as the target language, the English and the Chinese are respectively taken as the source languages, and the entity identification effect of the target language is improved by utilizing the entity labeling information of the source languages and the bilingual dictionary. According to the method, firstly, semantic space sharing of a source language and a target language is achieved through word-level adversarial migration, then multi-granularity feature embedding is conducted by fusing a bilingual dictionary to enrich semantic representation of target language words, then sequence features irrelevant to languages are extracted through sentence-level adversarial migration, and finally an entity recognition result is marked through CRF. Experimental results on a Vietnamese news data set show that under the condition that source languages are English and Chinese, compared with a monolingual entity recognition model and a current mainstream transfer learning model, the model has the advantages that the entity recognition effect of the provided model is improved, and compared with the monolingual entity recognition model, the model has the advantages that F1 values are increased by 19.61 and 18.73 respectively.

Description

technical field [0001] The invention relates to a Vietnamese event entity recognition method that integrates dictionaries and confrontation migration, and belongs to the technical field of natural language processing. Background technique [0002] The goal of Vietnamese event entity recognition is to identify and assign specific types of labels in Vietnamese news texts, such as names of people, places, organizations, and specific political concepts. At present, most event entity recognition systems use a combination of BiLSTM-CRF based on bidirectional long-short-term memory (BiLSTM) network and conditional random field (CRF) for entity recognition, but this method requires a large amount of training annotation corpus to make entity recognition better. Very low performance on low-resource linguistic entity recognition tasks. At present, the method with good effect on the task of entity recognition of low-resource language events is to use the idea of ​​transfer learning, th...

AI Technical Summary

Problems solved by technology

[0003] Multi-task learning is that all tasks share a coding layer, and knowledge transfer can be performed through the shared coding layer. However, due to the different sequence structures of different languages, when encoding the language information of two different resources at the same time, the encoder cannot guarantee to extract language-independent information. The sequence information of the high-resource language can be better transferred to the label information of the high-resource language; the word-level confrontation realizes the bilingual word embedding representation and only performs confrontation training on the pre-trained word vectors of the two languages ​​to map the two languages ​​​​into the same semantic space. The sequence feature information of the two languages ​​is ignored, and the sequence features of the source language cannot be fully used to assist the target language for entity recognition; bilingual dictionaries realize bilingual word embedding representations, and use large-scale bilingual dictionaries to align the word vector spaces of the source language and the target language, thereby Migrate the source language annotation information to the target language space, but it is relatively difficult to artificially construct a large-scale bilingual dictionary and this method does not consider the polysemy problem of bilingual translation; the two-layer confrontation transfer is based on the BiLSTM-CRF network, using word-level confrontation transfer Integrate two languages ​​into the same semantic space, and use sentence-level adversarial transfer to extract language-independent sequence features, but the semantic representation of target language words is single and the effect of extracting language-independent sequence features is poor

Images