Method and device for recognizing domain named entity
AssigneeBeijing Gridsum Technology Co., Ltd.
InventorsWenbin Xu, Xin He
Life of this patent
Estimating the term…
Abstract
The invention discloses a method and device for recognizing a domain named entity. The main technical solution is: conducting word segmentation on a text to be recognized; tagging each segmented word in the text to be recognized according to a tag set of a domain corresponding to the text to be recognized, where the tag set includes a basic tag set based on domain named entity recognition and a tag set belongs to the corresponding domain, and the basic tag set includes a location tag of related words which constitute the domain named entity; and extracting the tagged segmented words according to a domain named entity extraction rule and constituting the domain named entity.
Claims14
A method for recognizing a domain named entity, characterized by comprising:
- conducting word segmentation on a text to be recognized;
- tagging each segmented word in the text to be recognized according to a tag set of a domain corresponding to the text to be recognized, wherein the tag set comprises a basic tag set based on domain named entity recognition and a tag set belongs to the corresponding domain, and the basic tag set comprises a location tag of related words which constitute the domain named entity;
- extracting the tagged segmented words according to a domain named entity extraction rule;
- and constituting the domain named entity by the extracted segmented words,
- the location tag comprises incorrect word segmentation;
- and after tagging each segmented word in the text to be recognized according to the tag set of the domain corresponding to the text to be recognized, the method further comprises:
- detecting whether there is a word segmentation error tag in the tagged text;
- if the word segmentation error tag exists, conducting word segmentation error correction on a sentence in which the word segmentation error tag is located to obtain new segmented words;
- and tagging each of the new segmented words according to the tag set till there is no word segmentation error tag in the tagged text.
A device for recognizing a domain named entity, characterized by comprising:
- a processor, wherein the processor is configured to execute the following program units stored in a memory;
- a word segmenting unit, used for conducting word segmentation on a text to be recognized;
- a tagging unit, used for tagging each segmented word in the text to be recognized according to a tag set of a domain corresponding to the text to be recognized, wherein the tag set comprises a basic tag set based on domain named entity recognition and a tag set belongs to the corresponding domain, and the basic tag set comprises a location tag of related words which constitute the domain named entity;
- an extracting unit, used for extracting the tagged segmented words according to a domain named entity extraction rule;
- and a word combining unit, used for constituting the domain named entity by the extracted segmented words,
- the location tag comprises incorrect word segmentation;
- and the device further comprises:
- a detecting unit, used for detecting whether there is any word segmentation error tag in the tagged text after the tagging unit tags each segmented word in the text to be recognized according to the tag set of the domain corresponding to the text to be recognized;
- the word segmenting unit is further used for conducting word segmentation error correction on a sentence in which the word segmentation error tag is located to obtain new segmented words when the detecting unit detects the word segmentation error tag;
- the tagging unit is further used for tagging each of the new segmented words according to the tag set till there is no word segmentation error tag in the tagged text.
Dependencies are inferred from the claim text.