Hybrid information extraction method and system for open domain

Abstract

The invention discloses a hybrid information extraction method and system oriented to an open domain. According to the method, firstly, through context clause decomposition and NLP preprocessing, a composite sentence is simplified, and language attributes of the sentence are obtained; then identifying explicit phrases in the sentences, and identifying implicit phrases by using the two defined extension rules; and finally, based on the defined six language scene rules or the combination thereof, extracting the relationship between the identified entities, and generating a relationship triple. Aiming at the defects of non-atomic extraction, implicit phrases in a text are expanded by utilizing dependency analysis and heuristic rules, long noun phrases and relation phrases can be further decomposed into meaningful and more compact phrases, and the atomic requirement of information extraction can be better met; for cross-clause extraction, co-reference resolution and context clause decomposition are adopted for compositing sentences, the relation on the simplified clauses is extracted in combination with dependency analysis, and the extraction capacity on a composite sentence pattern is improved.

Description

technical field [0001] The invention belongs to the technical field of open information extraction in natural language processing, and in particular relates to a hybrid information extraction method and system oriented to the open field. Background technique [0002] Open Information Extraction (OIE) in Natural Language Processing (NLP) is the task of transforming unstructured information represented by natural language text into structured information representation in an unsupervised and domain-independent manner . Different from traditional closed domain information extraction, a set of relational categories is given in advance and the corpus domain is limited, open information extraction does not specify relational categories and extracts structured information from multi-domain texts. In this way, it has facilitated the development of extracting information from text and has been extended to corpora such as the Web. [0003] The results of open information extraction ...

AI Technical Summary

Problems solved by technology

More seriously, Stanford OIE completely ignores this relationship, resulting in no results in the extraction of the second example sentence

In addition, it should be noted that in the output (13), although M^OIE can extract some cross-clause relations (such as "reopened"), it still cannot fully extract such relations (such as "redesigned")

Images