Biomedical named entity recognition using two-phase model based on SVMs

Lee, Ki-Joong; Hwang, Young-Sook; Kim, Seon Ho; Rim, Hae-Chang

doi:10.1016/j.jbi.2004.08.012

Cited by 103 publications

(60 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Head nouns were used in [37] and [38]; word lists that are highly associated to classes are extracted as lexicons in [52]; keyword lexicons are statistically computed in [39]; keyword and boundary lists in [50].…”

Section: Jnlpba'04 Corpus and Current Solutionsmentioning

confidence: 99%

“…Six of the eight systems in the challenge used at least one type of external resources: 1) corpora such as the British National Corpus, the MedLine abstracts and the Penn Treebank for computing frequencies and trigger word extraction; 2) personalized gazetteers extracted from Swissport, LocusLink, Gene Ontology, etc., for keyword identification; 3) specialized taggers to increase the accuracy of certain types of entities (for example, in [52] two gene/protein taggers were used even though the accuracy of protein type extraction was not highly improved by this solution); 4) web searching of entity patterns was exploited by various systems in order to compute lexicons and/or assign weights to words associated to entities. From the challenge, it was not clear which (set of) features, external resources, or classification models really contributed to obtaining the best performances.…”

Section: Jnlpba'04 Corpus and Current Solutionsmentioning

confidence: 99%

See 1 more Smart Citation

Towards a Protein–Protein Interaction information extraction system: Recognizing named entities

Dánger

Pla

Molina

et al. 2014

Knowledge-Based Systems

View full text Add to dashboard Cite

The majority of biological functions of any living being are related to ProteinProtein Interactions (PPI). PPI discoveries are reported in form of research publications whose volume grows day after day. Consequently, automatic PPI information extraction systems are a pressing need for biologists. In this paper we are mainly concerned with the named entity detection module of PPIES (the PPI Information extraction system we are implementing) which recognizes twelve entity types relevant in PPI context. It is composed of two sub-modules: a dictionary look-up with extensive normalization and acronym detection, and a Conditional Random Field classifier. The dictionary look-up module has been tested with Interaction Method Task (IMT), and it improves by approximately 10% the current solutions that do not use Machine Learning (ML). The second module has been used to create a classifier using the Joint Workshop on Natural Language Processing in Biomedicine and its Applications (JNLPBA'04) data set. It does not use any external resources, or complex or ad-hoc post-processing, and obtains 77.25%, 75.04% and 76.13 for precision, recall, and F1-measure, respectively, improving all previous results obtained for this data set.

show abstract

Section: Jnlpba'04 Corpus and Current Solutionsmentioning

confidence: 99%

Section: Jnlpba'04 Corpus and Current Solutionsmentioning

confidence: 99%

Towards a Protein–Protein Interaction information extraction system: Recognizing named entities

Dánger

Pla

Molina

et al. 2014

Knowledge-Based Systems

View full text Add to dashboard Cite

show abstract

“…Learning with the complete training dataset completed in 97 hours on a Xeon quad-processor 3.6 GHz machine. [23] 67.4 / 61.0 / 64.0 Habib [8] 62.3 / 64.5 / 63.4 Park [21] 66.5 / 59.8 / 63.0 Lee [18] 50.8 / 47.6 / 49.1 Baseline [16] 52.6 / 43.6 / 47.7…”

Section: Baseline Experimentsmentioning

confidence: 99%

Scalable biomedical Named Entity Recognition: investigation of a database-supported SVM approach

Habib

Kalita

2010

IJBRA

View full text Add to dashboard Cite

Abstract-This paper explores the scalability issues associated with solving the Named Entity Recognition (NER) problem using Support Vector Machines (SVM) and high-dimensional features and presents two implementations to address these issues. The NER domain chosen for these experiments is the biomedical publications domain, especially selected due to its importance and inherent challenges. The performance results of a set of experiments conducted using existing binary and multiclass SVM with increasing training data sizes are examined and compared to results obtained using our new implementations. Our baseline machine learning approach eliminates prior language or domain-specific knowledge and achieves good outof-the-box accuracy measures that are comparable to those obtained using more complex approaches. The training time of multi-class SVM is reduced by several orders of magnitude, which would make support vector machines a more viable and practical machine learning solution for real-world problems with large datasets. The first implementation -SVM-PerfMulti -is a new instantiation of SVM-Struct v3.0 built as a standalone C executable. The second implementation -SVMMultiDB -is an embedded database solution for both binary and multi-class SVM, built as a server-side extension of PostgreSQL.

show abstract

“…In this work, we do not distinguish between proteins and other named entities(NEs), since it is difficult to make such a distinction. Each word is represented by a binary feature vector, which consists of lexical features, orthographical and morphological features, Part-of-Speech features, and context features(as in [13]). The basic idea is that using these features, the SVM will be able to determine whether the word is a biomedical named entity.…”

Section: Biomedical Named Entity Recognition (Ner)mentioning

confidence: 99%

Mining Protein Interactions from Text Using Convolution Kernels

Narayanan

Misra

Lin³

et al. 2010

New Frontiers in Applied Data Mining

View full text Add to dashboard Cite

Abstract. As the sizes of biomedical literature databases increase, there is an urgent need to develop intelligent systems that automatically discover Protein-Protein interactions from text. Despite resource-intensive efforts to create manually curated interaction databases, the sheer volume of biological literature databases makes it impossible to achieve significant coverage. In this paper, we describe a scalable hierarchical Support Vector Machine(SVM) based framework to efficiently mine protein interactions with high precision. In addition, we describe a convolution tree-vector kernel based on syntactic similarity of natural language text to further enhance the mining process. By using the inherent syntactic similarity of interaction phrases as a kernel method, we are able to significantly improve the classification quality. Our hierarchical framework allows us to reduce the search space dramatically with each stage, while sustaining a high level of accuracy. We test our framework on a corpus of over 10000 manually annotated phrases gathered from various sources. The convolution kernel technique identifies sentences describing interactions with a precision of 95% and a recall of 92%, yielding significant improvements over previous machine learning techniques.

show abstract

Biomedical named entity recognition using two-phase model based on SVMs

Cited by 103 publications

References 8 publications

Towards a Protein–Protein Interaction information extraction system: Recognizing named entities

Towards a Protein–Protein Interaction information extraction system: Recognizing named entities

Scalable biomedical Named Entity Recognition: investigation of a database-supported SVM approach

Mining Protein Interactions from Text Using Convolution Kernels

Contact Info

Product

Resources

About