Learning Relations from Biomedical Corpora Using Dependency Trees

Katrenko, Sophia; Adriaans, Pieter

doi:10.1007/978-3-540-71037-0_5

Cited by 33 publications

(41 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These feature vectors are used to train an SVM based classier with a linear kernel. More complex feature vectors are used in [10], where the local contexts of the protein names, the root verbs of the sentence, and the parent of the protein nodes in the dependency tree are taken into account by a BayesNet classier. In [7], syntactic information preprocessing, hand-made rules, and a domain vocabulary are used to extract gene interactions.…”

Section: Related Workmentioning

confidence: 99%

DEEPER: A Full Parsing Based Approach to Protein Relation Extraction

Fayruzov

Cock

Cornelis

et al. 2008

Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics

View full text Add to dashboard Cite

Abstract. Lexical variance in biomedical texts poses a challenge to automatic protein relation mining. We therefore propose a new approach that relies only on more general language structures such as parsing and dependency information for the construction of feature vectors that can be used by standard machine learning algorithms in deciding whether a sentence describes a protein interaction or not. As our approach is not dependent on the use of specic interaction keywords, it is applicable to heterogeneous corpora. Evaluation on benchmark datasets shows that our method is competitive with existing state-of-the-art algorithms for the extraction of protein interactions.

show abstract

Section: Related Workmentioning

confidence: 99%

DEEPER: A Full Parsing Based Approach to Protein Relation Extraction

Fayruzov

Cock

Cornelis

et al. 2008

Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics

View full text Add to dashboard Cite

show abstract

“…Machine Learning is the science of building hardware or software that can achieve tasks by learning from examples (Katrenko and Adriaans 2006). The examples often come as {input, output} pairs.…”

Section: Machine Learningmentioning

confidence: 99%

Technological research plan for active ageing

Msanjila

Camarinha-Matos

2011

Inf Syst Front

View full text Add to dashboard Cite

The ePAL initiative aimed at developing a roadmap for extension of professional active life of the retiring and retired knowledge workers in developed countries and specifically in Europe. Three main perspectives are identified in this roadmap, and defined to comprehensively address relevant dimensions of the ePAL environment. These three perspectives consist of: (1) the technological perspective that addresses the needed technology and the support services, (2) the societal perspective that addresses both the human factors and the societal aspects, and (3) the organizational perspective that addresses both the economic / managerial and governmental aspects of these environments. This document however aims to zoom in on the technological perspective of the roadmap. Following a brief description of the three main perspectives of the ePAL environment, it introduces the four main ICT research and development areas that are identified for strengthening and realization of active ageing. The technological perspective of the ePAL's vision constitutes a substantial part of the roadmap recommendations.This article further addresses the state of the art in each of these four areas and exemplifies their application needs in the ePAL environment.

show abstract

“…Named entity recognition is a whole separate area of text mining which is commonly treated separately from the relation mining task (see e.g. [3,9,10,14]). Example 1.…”

Section: Problem Descriptionmentioning

confidence: 99%

“…Method Information Algorithm Datasets [3] lexical SVM AIMed [10] lexical Hand-built rules HPRD50 shallow deep [9] shallow C4.5 AIMed deep BayesNet LLL [11] lexical SVM AIMed shallow LLL [14] lexical deep BayesNet AIMed deep NaiveBayes K-nearest neighbour Ensembles [21] lexical SVM AIMed shallow HPRD50 deep IEPA LLL [22] lexical Maximum entropy IEPA shallow deep [23] lexical SVM AIMed shallow deep Table 1: General approaches for protein interaction extraction…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

The role of syntactic features in protein interaction extraction

Fayruzov

Cock

Cornelis

et al. 2008

Proceedings of the 2nd International Workshop on Data and Text Mining in Bioinformatics

View full text Add to dashboard Cite

Most approaches for protein interaction mining from biomedical texts use both lexical and syntactic features. However, the individual impact of these two kinds of features on the effectiveness of the mining process has not yet been thoroughly studied. In this work we perform such a study on a recently published state of the art support vector machine approach that uses both lexical and syntactic features. To this end, we strip this approach down to an algorithm that uses only a subset of the initial syntactic features. Next, we compare the original and the stripped-down method by evaluating them on 5 benchmark datasets as well as by performing 5 additional cross-dataset experiments. Although the original method exploits a very rich feature set including words, parts-of-speech and grammatical relations, it is not significantly better than the stripped-down version; in fact, the former does not even consistently outperform the latter.

show abstract

Learning Relations from Biomedical Corpora Using Dependency Trees

Cited by 33 publications

References 12 publications

DEEPER: A Full Parsing Based Approach to Protein Relation Extraction

DEEPER: A Full Parsing Based Approach to Protein Relation Extraction

Technological research plan for active ageing

The role of syntactic features in protein interaction extraction

Contact Info

Product

Resources

About