Biomedical Named Entity Recognition using Conditional Random Fields and Rich Feature Sets

By Burr Settles. NLPBA/BioNLP, 2004

663 citations recorded by the source corpus.

As the wealth of biomedical knowledge in the form of literature increases, there is a rising need for effective natural language processing tools to assist in organizing, curating, and retrieving this information. To that end, named entity recognition (the task of identifying words and phrases in free text that belong to certain classes of interest) is an important first step for many of these larger information management goals.

Subfields: Artificial Intelligence, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/c432268dd885d9ae02190d8662321f3a3e325a4a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

Citations in the corpus

Unsupervised biomedical named entity recognition: Experiments with clinical and biological texts (2013, methodology): “However, the supervised nature of CRF relies on a fairly large amount of training data which must be annotated by humans.”
BANNER: An Executable Survey of Advances in Biomedical Named Entity Recognition (2007, methodology): “The next-simplest model used is IOB [11], which indicates whether each token is at the Beginning of an entity, Inside an entity, or Outside.”
Accelerating the annotation of sparse named entities by dynamic sentence selection (2008, background): “Page 1 of 10 (page number not for citation purposes) However, the lack of annotated corpora, which are indispensable for training machine learning models, makes it difficult to broaden the scope of text mining applications.”
Effects of Semantic Features on Machine Learning-Based Drug Name Recognition Systems: Word Embeddings vs. Manually Constructed Dictionaries (2015, methodology): “CRF is the top choice for DNR since it is one of the most reliable sequence labeling algorithms and has shown good performances on a large number of NER tasks such as NER in the newswire domain [7,8], biomedical NER [9,10] and clinical NER [11,12].”
Named Entity Recognition in the Medical Domain with Constrained CRF Models (2017, methodology): “We initially propose using conditional random ﬁelds (CRF) (Lafferty et al., 2001) for this task as they have been successful for other related NLP sequence labeling tasks (Sha and Pereira, 2003; Settles, 2004).”
A Survey on Deep Learning for Named Entity Recognition (2018, methodology): “We note that CRF-based NER has been widely applied to texts in various domains, including biomedical text [57], [82], tweets [83], [84] and chemical text [85].”
A Brief Survey of Text Mining: Classification, Clustering and Extraction Techniques (2017, background): “[123] introduced a hybrid method in which they have use a dictionary-based method to locate known protein names along with a part-of-speech tagging (CRF-based method).”
A survey of named entity recognition and classification (2007, methodology): “…of the GENIA corpus (T. Ohta et al. 2002) led to many studies dedicated to types such as " protein " , " DNA " , " RNA " , " cell line " and " cell type " (e.g., D. Shen et al. 2003, B. Settles 2004) as well as studies targeted to " protein " recognition only (Y. Tsuruoka & Tsujii 2003).”
Accelerated training of conditional random fields with stochastic gradient methods (2006, methodology): “Following Settles (2004) we use binary orthographic features (AlphaNumeric, HasDash, RomanNumeral, etc.) based on regular expressions, though ours dier somewhat from those used by Settles (2004) .”
2010 i2b2/VA challenge on concepts, assertions, and relations in clinical text (2011, methodology): “utilized CRFs in an ensemble, either of existing named entity recognition systems and chunkers”
Multi-Task Active Learning for Linguistic Annotations (2008, methodology): “We employed a tagger similar to the one presented by Settles (2004). Our tagger has a performance of ≈ 84% f-score on the CoNLL-2003 data; inspection of the predicted entities on”
Algorithmic stemmers or morphological analysisq An evaluation (2009, background): “, 2001), shallow parsing (Sha and Pereira, 2003), and named-entity recognition in the biomedical domain (Settles, 2004).”
Evaluating Word Representation Features in Biomedical Named Entity Recognition Tasks (2014, methodology): “Various machine learning algorithms have been used in BNER, including hidden Markov models (HMM) [8, 9], maximum entropy Markov models (MEMM) [10, 11], conditional random fields (CRF) [12, 13], and support vector machines (SVM) [14, 15].”