BACKGROUND The chemical compound and drug name recognition plays an important role in chemical text mining, and it is the basis for automatic relation extraction and event identification in chemical information processing. So a high-performance named entity recognition system for chemical compound and drug names is necessary. METHODS We developed a CHEMDNER system based on mixed conditional r...

This paper describes our system developed for Biocreative V Chemical entity mention in patent (CEMP) task for identifying the chemical mentions from patent data. We have presented two systems which use Support vector machines (SVMs) and Conditional random fields (CRFs) algorithms. In this work we used a rich feature set that includes linguistic, orthographical and lexical clue features. We obta...

This paper presents a successful approach for domain adaptation of a dependency parser via self-training. We improve parsing accuracy for out-of-domain texts with a self-training approach that uses confidence-based methods to select additional training samples. We compare two confidence-based methods: The first method uses the parse score of the employed parser to measure the confidence into a ...

Chemical burns are slow healing injuries and their depth is difficult to assess. Tissue destruction continues as long as active material is present in the wound site. The routine therapy for treatment of full thickness chemical burns is early excision; it shortens hospitalization and reduces morbidity. However, presently there is no specific treatment for chemical burns of partial thickness. Th...

This experiment assessed the quality of Rossogolla (Balish) manufactured in the laboratory and collected from Netrokona district. Four types of Rossogolla, (A) Laboratory made Rossogolla, (B) Rossogolla from Mukti Mistanno vander, (C) Rossogolla from Gwyneth Mistanno vander, (D) Rossogolla from Khan Mistanno vander were used in this experiment. Quality of Rossogolla were evaluated by physical, ...

Chemical patents contain detailed information on novel chemical compounds that is valuable to the chemical and pharmaceutical industries. In this paper, we introduce a system, NERChem that can recognize chemical named entity mentions in chemical patents. NERChem is based on the conditional random fields model (CRF). Our approach incorporates (1) class composition, which is used for combining ch...