Conference proceeding
Integrating Extra Knowledge into Word Embedding Models for Biomedical NLP Tasks
2017 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), pp 968-975
01 Jan 2017
Abstract
Word embedding in the NLP area has attracted increasing attention in recent years. The continuous bag-of-words model (CBOW) and the continuous Skip-gram model (Skip-gram) have been developed to learn distributed representations of words from a large amount of unlabeled text data. In this paper, we explore the idea of integrating extra knowledge to the CBOW and Skip-gram models and applying the new models to biomedical NLP tasks. The main idea is to construct a weighted graph from knowledge bases (KBs) to represent structured relationships among words/concepts. In particular, we propose a GCBOW model and a GSkip-gram model respectively by integrating such a graph into the original CBOW model and Skip-gram model via graph regularization. Our experiments on four general domain standard datasets show encouraging improvements with the new models. Further evaluations on two biomedical NLP tasks (biomedical similarity/relatedness task and biomedical Information Retrieval (IR) task) show that our methods have better performance than baselines.
Metrics
Details
- Title
- Integrating Extra Knowledge into Word Embedding Models for Biomedical NLP Tasks
- Creators
- Yuan Ling - Drexel Univ, Coll Comp & Informat, Philadelphia, PA 19104 USAYuan An - Drexel University, Information ScienceMengwen Liu - Drexel Univ, Coll Comp & Informat, Philadelphia, PA 19104 USASadid A. Hasan - Philips Res North Amer, Artificial Intelligence Lab, Cambridge, MA 02141 USAYetian Fan - Dalian Univ Technol, Sch Math Sci, Dalian 116023, Peoples R ChinaXiaohua Hu - Drexel University, Information Science
- Publication Details
- 2017 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), pp 968-975
- Series
- IEEE International Joint Conference on Neural Networks (IJCNN)
- Publisher
- IEEE
- Number of pages
- 8
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Information Science
- Web of Science ID
- WOS:000426968701031
- Scopus ID
- 2-s2.0-85030983763
- Other Identifier
- 991019170536104721
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Industry collaboration
- Domestic collaboration
- International collaboration
- Web of Science research areas
- Computer Science, Artificial Intelligence
- Computer Science, Hardware & Architecture
- Engineering, Electrical & Electronic