TU Darmstadt / ULB / TUbiblio

EELECTION at SemEval-2017 Task 10: Ensemble of nEural Learners for kEyphrase ClassificaTION

Eger, Steffen and Do Dinh, Erik-Lân and Kuznetsov, Ilia and Kiaeeha, Masoud and Gurevych, Iryna (2017):
EELECTION at SemEval-2017 Task 10: Ensemble of nEural Learners for kEyphrase ClassificaTION.
In: Proceedings of the International Workshop on Semantic Evaluation, Association for Computational Linguistics, Vancouver, Canada, [Online-Edition: http://aclweb.org/anthology/S17-2163],
[Conference or Workshop Item]

Abstract

This paper describes our approach to the  SemEval 2017 Task 10: “Extracting Keyphrases and Relations from Scientific Publications”, specifically to Subtask (B): “Classification of identified keyphrases”. We explored three different deep learning approaches: a character-level convolutional neural network (CNN), a stacked learner with an MLP meta-classifier, and an attention based Bi-LSTM. From these approaches, we created an ensemble of differently hyper-parameterized systems, achieving a micro-F1-score of 0.63 on the test data. Our approach ranks 2nd (score of 1st placed system: 0.64) out of four according to this official score. However, we erroneously trained 2 out of 3 neural nets (the stacker and the CNN) on only roughly 15% of the full data, namely, the original development set.  When trained on the full data (training + development), our ensemble has a micro-F1-score of 0.69. Our code is available from https://github.com/UKPLab/semeval2017-scienceie.

Item Type: Conference or Workshop Item
Erschienen: 2017
Creators: Eger, Steffen and Do Dinh, Erik-Lân and Kuznetsov, Ilia and Kiaeeha, Masoud and Gurevych, Iryna
Title: EELECTION at SemEval-2017 Task 10: Ensemble of nEural Learners for kEyphrase ClassificaTION
Language: English
Abstract:

This paper describes our approach to the  SemEval 2017 Task 10: “Extracting Keyphrases and Relations from Scientific Publications”, specifically to Subtask (B): “Classification of identified keyphrases”. We explored three different deep learning approaches: a character-level convolutional neural network (CNN), a stacked learner with an MLP meta-classifier, and an attention based Bi-LSTM. From these approaches, we created an ensemble of differently hyper-parameterized systems, achieving a micro-F1-score of 0.63 on the test data. Our approach ranks 2nd (score of 1st placed system: 0.64) out of four according to this official score. However, we erroneously trained 2 out of 3 neural nets (the stacker and the CNN) on only roughly 15% of the full data, namely, the original development set.  When trained on the full data (training + development), our ensemble has a micro-F1-score of 0.69. Our code is available from https://github.com/UKPLab/semeval2017-scienceie.

Title of Book: Proceedings of the International Workshop on Semantic Evaluation
Publisher: Association for Computational Linguistics
Uncontrolled Keywords: UKP_a_DLinNLP;UKP_reviewed
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Ubiquitous Knowledge Processing
Event Location: Vancouver, Canada
Date Deposited: 28 Feb 2017 09:53
Official URL: http://aclweb.org/anthology/S17-2163
Identification Number: TUD-CS-2017-0047
Related URLs:
Export:
Suche nach Titel in: TUfind oder in Google

Optionen (nur für Redakteure)

View Item View Item