侯文娟Wen-Juan Hou班法Bamfa Ceesay2020-10-19不公開2020-10-192020http://etds.lib.ntnu.edu.tw/cgi-bin/gs32/gsweb.cgi?o=dstdcdr&s=id=%22G080347008S%22.&%22.id.&http://rportal.lib.ntnu.edu.tw:80/handle/20.500.12235/111752noneBiomedical text mining (including biomedical natural language processing or BioNLP) refers to the methods and study of how text mining may be applied to texts and literature of the biomedical and molecular biology domains. As a field of research, biomedical text mining incorporates ideas from natural language processing, bioinformatics, medical informatics and computational linguistics. With the enormous volume of biological literature, an increasing growth phenomenon due to the high rate of new publications is one of the most common motivations for the biomedical text mining. Using these massive literatures available, biological information could be extracted using various research algorithms and text mining techniques. Recent studies have seen significant adaption of neural methods in many machine learning methods. Significant results and performance improvements have been achieved with neural networks. In this PhD dissertation, we intend to explore a general perspective of BioIE in NLP and the application of neural methodologies in BioNLP. We shall survey and set up experimental models to investigate NLP methodologies and approaches in BioIE.noneDDI extractionBiomedical TextAdaptation of RNNTransfer learningDomain transformationUnstable gradientBioNLPNeural embedding