Shashi Narayan

Research Associate
Informatics Forum 338
School of Informatics
The University of Edinburgh
10 Crichton Street
Edinburgh EH8 9AB, UK
Phone: +44 (0)131 650 4418
email: Shashi.Narayan(at){,}

My research focuses on natural language understanding and generation. I aim to develop general frameworks for generation from underlying meaning representations or for text rewriting such as summarization, text simplification, question answering and paraphrase generation. The aim is to develop a general framework that is not specific to an application and which incorporates task-specific syntactic and semantic information. I mostly rely on deep learning and spectral methods to develop such framework. I also have experience with parsing and other structured prediction problems.

Currently, I am working with Shay Cohen on the H2020 SUMMA project. I closely collaborate with Mirella Lapata and Claire Gardent. I am part of the cohort and EdinburghNLP groups.

Previously, I was a doctoral student at Université de Lorraine, Nancy, working at Loria INRIA under the supervision of Claire Gardent. I was awarded an Erasmus Mundus Masters scholarship in Language and Communication Technology (EM-LCT). I did my major (Bachelor of Technology, Honors) in Computer Science and Engineering from Indian Institute of Technology (IIT), Kharagpur India.

Recent News

Feb, 2018
Our long paper "Ranking Sentences for Extractive Summarization with Reinforcement Learning" with Shay B. Cohen and Mirella Lapata will appear at NAACL 2018.
Our tutorial proposal called "Deep Learning Approaches for Text Production" with Claire Gardent got accepted for NAACL 2018.

Dec, 2017
Area chair for Generation, NAACL HLT 2018.

Sep 21, 2017
The automatic evaluation results from the WebNLG challenge are now publically available here. Thanks for participating!

Sep 18, 2017
We are pleased to announce our Rainbow Parser from Narayan and Cohen (EMNLP'15 and ACL'16). This includes code for training and decoding with latent-variable probabilistic context-free grammars (L-PCFGs).

mailto googlescholar github