TY - GEN
T1 - Sanaphor++
T2 - 11th International Conference on Language Resources and Evaluation, LREC 2018
AU - Plu, Julien
AU - Prokofyev, Roman
AU - Tonon, Alberto
AU - Cudré-Mauroux, Philippe
AU - Difallah, Djellel Eddine
AU - Troncy, Raphaël
AU - Rizzo, Giuseppe
N1 - Funding Information:
We would like to thank Kevin Clark for his help in understanding and using Stanford deep-coref. This work has been partially supported by the French National Research Agency (ANR) within the ASRAEL project (ANR-15-CE23-0018), the French Fonds Unique Interministériel (FUI) within the NexGen-TV project and the innovation activities 3cixty (14523) and PasTime (17164) of EIT Digital (https://www.eitdigital.eu).
Publisher Copyright:
© LREC 2018 - 11th International Conference on Language Resources and Evaluation. All rights reserved.
PY - 2019
Y1 - 2019
N2 - Coreference resolution has always been a challenging task in Natural Language Processing. Machine learning and semantic techniques have improved the state of the art over the time, though since a few years, the biggest step forward has been made using deep neural networks. In this paper, we describe Sanaphor++, which is an improvement of a top-level deep neural network system for coreference resolution-namely Stanford deep-coref-through the addition of semantic features. The goal of Sanaphor++ is to improve the clustering part of the coreference resolution in order to know if two clusters have to be merged or not once the pairs of mentions have been identified. We evaluate our model over the CoNLL 2012 Shared Task dataset and compare it with the state-of-the-art system (Stanford deep-coref) where we demonstrated an average gain of 1.13% of the average F1 score.
AB - Coreference resolution has always been a challenging task in Natural Language Processing. Machine learning and semantic techniques have improved the state of the art over the time, though since a few years, the biggest step forward has been made using deep neural networks. In this paper, we describe Sanaphor++, which is an improvement of a top-level deep neural network system for coreference resolution-namely Stanford deep-coref-through the addition of semantic features. The goal of Sanaphor++ is to improve the clustering part of the coreference resolution in order to know if two clusters have to be merged or not once the pairs of mentions have been identified. We evaluate our model over the CoNLL 2012 Shared Task dataset and compare it with the state-of-the-art system (Stanford deep-coref) where we demonstrated an average gain of 1.13% of the average F1 score.
KW - Coreference Resolution
KW - Deep Learning
KW - Entity Linking
UR - http://www.scopus.com/inward/record.url?scp=85059881713&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85059881713&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85059881713
T3 - LREC 2018 - 11th International Conference on Language Resources and Evaluation
SP - 412
EP - 417
BT - LREC 2018 - 11th International Conference on Language Resources and Evaluation
A2 - Isahara, Hitoshi
A2 - Maegaard, Bente
A2 - Piperidis, Stelios
A2 - Cieri, Christopher
A2 - Declerck, Thierry
A2 - Hasida, Koiti
A2 - Mazo, Helene
A2 - Choukri, Khalid
A2 - Goggi, Sara
A2 - Mariani, Joseph
A2 - Moreno, Asuncion
A2 - Calzolari, Nicoletta
A2 - Odijk, Jan
A2 - Tokunaga, Takenobu
PB - European Language Resources Association (ELRA)
Y2 - 7 May 2018 through 12 May 2018
ER -