Improving biomedical named entity recognition with syntactic information

Biomedical Named Entity Recognition System

We propose a machine learning approach, using a Maximum Entropy (ME) model to construct a Named Entity Recognition (NER) classifier to retrieve biomedical names from texts. In experiments, we utilize a blend of various linguistic features incorporated into the ME model to assign class labels and location within an entity sequence, and a postprocessing strategy for corrections to sequences of ta...

Unsupervised Biomedical Named Entity Recognition

Improving English Named Entity Recognition

In recent years much of the work in named entity recognition has been focused on tackling entities in different languages or domains. However the task of English named entity recognition still remains to be solved. In this paper we explore more ways to improve the English named entity recognition system beyond just distributional semantics and the use of external gazetteer. These ways include p...

Improving named entity recognition with prosodic features

In natural language processing (NLP) the problem of named entity (NE) recognition in speech is well known, yet remains a challenge where performance is dependent on automatic speech recognition (ASR) system error rates. NEs are often foreign or out-of-vocabulary (OOV) words, leaving conventional ASR systems unable to recognize them. In our research, we improve a CRF-based NE recognition system ...

Biomedical Named Entity Recognition Using Neural Networks

We investigate the task of Named Entity Recognition (NER) in the domain of biomedical text. There is little published work employing modern neural network techniques in this domain, probably due to the small sizes of human-labeled data sets, as non-trivial neural models would have great difficulty avoiding overfitting. In this work we follow a semi-supervised learning approach: We first train s...