The LIG (Laboratoire d'Informatique de Grenoble) laboratory proposes the
following M2 stage (research)

Title:
Neural coreference resolution

Description:
Coreference resolution aims at detecting chains of coreference mentions 
in a text, that is mentions in the text that refer to the same entity.
While at first coreference resolution was split into two separated 
sub-problems, i.e. mention detections and resolution of coreferent 
mentions [1], thanks to the development of sophisticated neural models 
[2,3,4], end-to-end coreference resolution system can be based on a 
whole single model.
The aim of this stage is to study Sequence-to-Sequence [5] and 
Transformer [6] neural models for coreference resolution, integrating 
different types of attention mechanisms and possibly arbitrarily-long 
context [8], with the goal of understanding their impact in dealing with 
this complex NLP problem.

In this internship the student will implement parts of the systems for 
coreference resolution with Sequence-to-Sequence and Transformer neural 
models.
The student will run experiments on his own using GPUs, and the systems 
will be tested on the CoNLL Semeval 2012 benchmark [7].

Profile:
- Student for internship level stage (Master 2) in computer science, or 
  from engineering school
- Computer science skills:
     Python programming with good knowledge of deep learning libraries 
     (TensorFlow or PyTorch)
     Textual data manipulation (xml format, tabular format, CoNLL
     format)
- Interested in Natural Language Processing
- Skills in machine learning for probabilistic models

The internship may last from 4 up to 6 months, it will take place at LIG
laboratory, GETALP team (http://lig-getalp.imag.fr/), starting from
January/February 2019.
The student will be tutored by Marco Dinarelli (www.marcodinarelli.it) 
and Laurent Besacier (http://lig-membres.imag.fr/besacier/).
Interested candidates must send a CV and a motivation letter to
marco.dinarelli@ens.fr and laurent.besacier@univ-grenoble-alpes.fr.

[1] Vincent Ng
     Supervised noun phrase coreference research: The first fifteen 
     years.
     Proceedings of ACL, 2010

[2] Sam Wiseman, Alexander M. Rush, Stuart M. Shieber
     Learning Global Features for Coreference Resolution
     Proceedings of NAACL-HLT, 2016

[3] Kenton Leey, Luheng Hey, Mike Lewisz, and Luke Zettlemoyer
     End-to-end Neural Coreference Resolution
     Proceedings of EMNLP, 2017

[4] Kenton Lee Luheng He Luke Zettlemoyer
     Higher-order Coreference Resolution with Coarse-to-fine Inference
     Proceedings of NAACL, 2018

[5] Ilya Sutskever, Oriol Vinyals, Quoc V. Le
     Sequence to Sequence Learning with Neural Networks
     Proceedings of NIPS, 2014

[6] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion 
     Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin
     Attention Is All You Need
     Proceedings of NIPS, 2017

[7] Sameer Pradhan, Alessandro Moschitti, Nianwen Xue, Olga Uryupina, 
     Yuchen Zhang
     Conll-2012 shared task: Modeling multilingual unrestricted 
     coreference in ontonotes
     Proceedings of EMNLP and  CoNLL-Shared Task, 2012

[8] Zhang, Jiacheng, et al. "Improving the Transformer Translation Model 
     with Document-Level Context." EMNLP 2018.