A Knowledge-Poor Approach to BioCreative V DNER and CID Tasks

Firoj Alam; Anna Corazza; R Zanoli; Alberto Lavelli; Roberto Zanoli

A Knowledge-Poor Approach to BioCreative V DNER and CID Tasks

Firoj Alam
, Anna Corazza
, R Zanoli
, Alberto Lavelli
, Roberto Zanoli

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The report describes our participation in the BioCreative V track #3, both in Disease Named Entity Recognition and Normalization (DNER) and in Chemical-induced diseases relation extraction (CID). For both tasks, we have adopted a general-purpose approach based on machine learning techniques integrated with a limited number of domain specific knowledge resources and using freely available tools for preprocessing data. Crucially, the system only uses the data sets provided by the organizers. After comparing different configurations, the one giving the best compromise between effectiveness and efficiency has been chosen. We report the results of the experiments performed during the development phase for comparing different configurations. The results of the official submission are in line with those on the development set.

Original language	English
Title of host publication	Proceedings of the fifth BioCreative challenge evaluation workshop
Publication status	Published - 2015
Externally published	Yes

Access to Document

https://scholar.google.com/citations?view_op=view_citation&hl=en&user=j-RtwDQAAAAJ&cstart=100&pagesize=100&citation_for_view=j-RtwDQAAAAJ:qxL8FJ1GzNcC

Cite this

@inproceedings{131eaa30daf84bd2a2cf609e43dde822,

title = "A Knowledge-Poor Approach to BioCreative V DNER and CID Tasks",

abstract = "The report describes our participation in the BioCreative V track \#3, both in Disease Named Entity Recognition and Normalization (DNER) and in Chemical-induced diseases relation extraction (CID). For both tasks, we have adopted a general-purpose approach based on machine learning techniques integrated with a limited number of domain specific knowledge resources and using freely available tools for preprocessing data. Crucially, the system only uses the data sets provided by the organizers. After comparing different configurations, the one giving the best compromise between effectiveness and efficiency has been chosen. We report the results of the experiments performed during the development phase for comparing different configurations. The results of the official submission are in line with those on the development set.",

author = "Firoj Alam and Anna Corazza and R Zanoli and Alberto Lavelli and Roberto Zanoli",

year = "2015",

language = "English",

booktitle = "Proceedings of the fifth BioCreative challenge evaluation workshop",

}

TY - GEN

T1 - A Knowledge-Poor Approach to BioCreative V DNER and CID Tasks

AU - Alam, Firoj

AU - Corazza, Anna

AU - Zanoli, R

AU - Lavelli, Alberto

AU - Zanoli, Roberto

PY - 2015

Y1 - 2015

N2 - The report describes our participation in the BioCreative V track #3, both in Disease Named Entity Recognition and Normalization (DNER) and in Chemical-induced diseases relation extraction (CID). For both tasks, we have adopted a general-purpose approach based on machine learning techniques integrated with a limited number of domain specific knowledge resources and using freely available tools for preprocessing data. Crucially, the system only uses the data sets provided by the organizers. After comparing different configurations, the one giving the best compromise between effectiveness and efficiency has been chosen. We report the results of the experiments performed during the development phase for comparing different configurations. The results of the official submission are in line with those on the development set.

AB - The report describes our participation in the BioCreative V track #3, both in Disease Named Entity Recognition and Normalization (DNER) and in Chemical-induced diseases relation extraction (CID). For both tasks, we have adopted a general-purpose approach based on machine learning techniques integrated with a limited number of domain specific knowledge resources and using freely available tools for preprocessing data. Crucially, the system only uses the data sets provided by the organizers. After comparing different configurations, the one giving the best compromise between effectiveness and efficiency has been chosen. We report the results of the experiments performed during the development phase for comparing different configurations. The results of the official submission are in line with those on the development set.

M3 - Conference contribution

BT - Proceedings of the fifth BioCreative challenge evaluation workshop

ER -

A Knowledge-Poor Approach to BioCreative V DNER and CID Tasks

Abstract

Access to Document

Fingerprint

Cite this