access icon free Integrated Chinese Segmentation, Parsing and Named Entity Recognition

Segmentation, named entity recognition and parsing are standalone techniques in natural language processing community, and their annotations are inconsistent. However, the joint output is needed in some practical use, and they rely on the result of each other to make more concise output. A unified model is learned to resolve these three tasks simultaneously. At the training stage, the joint annotation of the three tasks are employed to learn a unified model. At the decoding stage, the three tasks are carried out on a given text to provide a consistent output. Experiment results demonstrate the higher performance for each task and verify the benefits of the unified framework.

Inspec keywords: text analysis; learning (artificial intelligence); natural language processing; word processing

Other keywords: parsing; joint annotation; annotations; joint output; training stage; unified model; concise output; consistent output; natural language processing community; integrated chinese segmentation; named entity recognition

Subjects: Document processing and analysis techniques; Natural language interfaces; Knowledge engineering techniques

http://iet.metastore.ingenta.com/content/journals/10.1049/cje.2018.05.014
Loading

Related content

content/journals/10.1049/cje.2018.05.014
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading