2022

• A Well-Composed Text is Half Done! Composition Sampling for Diverse Conditional Generation, Shashi Narayan, Gonçalo Simões, Yao Zhao, Joshua Maynez, Dipanjan Das, Michael Collins, Mirella Lapata. To appear at ACL. [pdf, data]

2021

• FROST: Planning with Learned Entity Prompts for Abstractive Summarization, Shashi Narayan, Yao Zhao, Joshua Maynez, Gonçalo Simões, Vitaly Nikolaev, Ryan McDonald, Transactions of the Association for Computational Linguistics (TACL), Volume 9. [pdf, data]

• A Thorough Evaluation of Task-Specific Pretraining for Summarization, Sascha Rothe, Joshua Maynez and Shashi Narayan, Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP). [pdf]

• MIRANEWS: Dataset and Benchmarks for Multi-Resource-Assisted News Summarization, Xinnuo Xu, Ondřej Dušek, Shashi Narayan, Verena Rieser and Ioannis Konstas, Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP) Findings. [pdf]

• Focus Attention: Promoting Faithfulness and Diversity in Summarization, Rahul Aralikatte, Shashi Narayan, Joshua Maynez, Sascha Rothe and Ryan McDonald, Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNL) [pdf, bib]

• The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics, Sebastian Gehrmann et. al. [arXiv, GEM]

2020

• Stepwise Extractive Summarization and Planning with Structured Transformers, Shashi Narayan, Joshua Maynez, Jakub Adamek, Daniele Pighin, Blaz Bratanic and Ryan McDonald, Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). [arXiv, pdf, bib]

• On Faithfulness and Factuality in Abstractive Summarization, Joshua Maynez, Shashi Narayan, Bernd Bohnet and Ryan McDonald, Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL). [pdf, bib, data]

• Book: Deep Learning Approaches to Text Production, Shashi Narayan and Claire Gardent, Synthesis Lectures on Human Language Technologies, March 2020, Vol. 13, No. 1 , Pages 1-199, edited by Graeme Hirst. [link]

• Leveraging pre-trained checkpoints for sequence generation tasks, Sascha Rothe, Shashi Narayan and Aliaksei Severyn, Transactions of the Association for Computational Linguistics, Vol. 8, 264-280. [arXiv, pdf, bib, data]

• QURIOUS: Question Generation Pretraining for Text Generation, Shashi Narayan, Gonçalo Simoes, Ji Ma, Hannah Craighead, Ryan Mcdonald, arXiv preprint. [pdf]

2019

• Sticking to the Facts: Confident Decoding for Faithful Data-to-Text Generation, Ran Tian, Shashi Narayan, Thibault Sellam and Ankur P. Parikh, arXiv preprint. [pdf]

• What is this Article about? Extreme Summarization with Topic-aware Convolutional Neural Networks, Shashi Narayan, Shay B. Cohen and Mirella Lapata, Journal of Artificial Intelligence Research 66, 243-278. [pdf, bib]

• HighRES: Highlight-based Reference-less Evaluation of Summarization, Hardy Hardy, Shashi Narayan and Andreas Vlachos, Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL). [pdf, bib]

• Jointly Extracting and Compressing Documents with Summary State Representations, Afonso Mendes, Shashi Narayan, Sebastião Miranda, Zita Marinho, André F. T. Martins and Shay B. Cohen, Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL). [pdf, bib]

2018

• Don’t Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization, Shashi Narayan, Shay B. Cohen and Mirella Lapata, Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP). [pdf, bib, data]

• Ranking Sentences for Extractive Summarization with Reinforcement Learning, Shashi Narayan, Shay B. Cohen and Mirella Lapata, Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL). [pdf, bib, data]

• Privacy-preserving Neural Representations of Text, Maximin Coavoux, Shashi Narayan and Shay B. Cohen, Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP). [pdf, bib]

• Deep Learning Approaches to Text Production, Claire Gardent and Shashi Narayan, Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Tutorial Abstracts (NAACL). [pdf, bib]

• Local String Transduction as Sequence Labeling, Joana Ribeiro, Shashi Narayan, Shay B. Cohen and Xavier Carreras, Proceedings of the 27th International Conference on Computational Linguistics (COLING). [pdf, bib]

• Document Modeling with External Attention for Sentence Extraction, Shashi Narayan, Ronald Cardenas, Nikos Papasarantopoulos, Shay B. Cohen, Mirella Lapata, Jiangsheng Yu and Yi Chang, Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL). [pdf, bib]

2017

• Neural Extractive Summarization with Side Information, Shashi Narayan, Nikos Papasarantopoulos, Shay B. Cohen and Mirella Lapata, In arXiv:1704.04530 (preprint). [data and code, demo]

• Split and Rephrase, Shashi Narayan, Claire Gardent, Shay B. Cohen and Anastasia Shimorina, In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP), Copenhagen, Denmark. [pdf, bib, data]

• Creating Training Corpora for NLG Micro-Planning, Claire Gardent, Anastasia Shimorina, Shashi Narayan and Laura Perez-Beltrachini, In Proceedings of the 55th Annual meeting of the Association for Computational Linguistics (ACL), Vancouver. [pdf, bib, data]

• The WebNLG Challenge: Generating Text from RDF Data, Claire Gardent, Anastasia Shimorina, Shashi Narayan and Laura Perez-Beltrachini, In Proceedings of the 10th International Natural Language Generation conference (INLG), Compostela, Spain. [pdf, bib]

• The SUMMA Platform Prototype, Liepins et. al., In Proceedings of the Demonstrations at the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL), Valencia, Spain. [pdf, bib]

2016

• Optimizing Spectral Learning for Parsing, Shashi Narayan and Shay B. Cohen, In Proceedings of the 54th Annual meeting of the Association for Computational Linguistics (ACL), Berlin 2016. [pdf, bib, data, code, slides]

• Encoding Prior Knowledge with Eigenword Embeddings, Dominique Osborne, Shashi Narayan and Shay B. Cohen, In Transactions of the Association for Computational Linguistics (TACL), 2016. [pdf, bib]

• Paraphrase Generation from Latent-Variable PCFGs for Semantic Parsing, Shashi Narayan, Siva Reddy and Shay B. Cohen, In Proceedings of the 9th International Natural Language Generation conference (INLG), Edinburgh. [pdf, bib, slides]

• Unsupervised Sentence Simplification Using Deep Semantics, Shashi Narayan and Claire Gardent, In Proceedings of the 9th International Natural Language Generation conference (INLG), Edinburgh. [pdf, bib, data, slides] (Runner-up, Best paper award)

• The WebNLG Challenge: Generating Text from DBPedia Data, Emilie Colin, Claire Gardent, Yassine Mrabet, Shashi Narayan and Laura Perez-Beltrachini, In Proceedings of the 9th International Natural Language Generation conference (INLG), Edinburgh. [pdf, bib]

2015

• Diversity in Spectral Learning for Natural Language Parsing, Shashi Narayan and Shay B. Cohen, In Proceedings of the 2015 Conference on Empirical Methods on Natural Language Processing (EMNLP), Lisbon, Portugal. [pdf, bib, poster, code]

• Multiple Adjunction in Feature-based Tree-Adjoining Grammar, Claire Gardent and Shashi Narayan, In Computational Linguistics. [pdf]

• A Generation Framework for Grammar Development, Shashi Narayan and Claire Gardent, In the first International Workshop on Data-to-Text Generation (D2T), Edinburgh UK. [pdf]

2014

• PhD Thesis: Generating and Simplifying Sentences, Université de Lorraine. Advisor: Claire Gardent. [thesis]

• Hybrid Simplification using Deep Semantics and Machine Translation, Shashi Narayan and Claire Gardent, In Proceedings of the 52nd Annual meeting of the Association for Computational Linguistics (ACL), Baltimore. [pdf, bib, notes, dataset, code]

2013

• Generating Elliptic Coordination, Claire Gardent and Shashi Narayan, In Proceedings of the 14th European Workshop on Natural Language Generation (ENLG), ACL, Sofia Bulgaria. [pdf, bib, Elliptic Sentences]

2012

• Error Mining with Suspicion Trees: Seeing the Forest for the Trees, Shashi Narayan and Claire Gardent, In Proceedings of the 24th International Conference on Computational Linguistics (COLING), Mumbai, India. [pdf, bib]

• Structure-Driven Lexicalist Generation, Shashi Narayan and Claire Gardent, In Proceedings of the 24th International Conference on Computational Linguistics (COLING), Mumbai, India. [pdf, bib]

• Error Mining on Dependency Trees, Claire Gardent and Shashi Narayan, In Proceedings of the 50th Annual meeting of the Association for Computational Linguistics (ACL), Jeju Island, Korea. [pdf, bib]

2011

• Masters Thesis: RTG Based Surface Realization from Dependency Representation, Erasmus Mundus Masters in Language and Communication Technology (EM-LCT), Advisors: Claire Gardent and Mike Rosner. [thesis, em-url]

2010

• Population and Enrichment of Event Ontology Using Twitter, Shashi Narayan, Srdjan Prodanovic, Zoe Bogart and Mohammad Fazleh Elahi, In Proceedings of the workshop on Semantic Personalized Information Management (SPIM) in conjunction with the 7th international conference on Language Resources and Evaluation (LREC), Malta. [pdf]

• A Composite Kernel for Named Entity Recognition, Sujan Kumar Saha, Shashi Narayan, Sudeshna Sarkar and Pabitra Mitra, In Pattern Recognition Letters. [pdf]

2009

• Bachelor Thesis: Support Vector Machine for Hindi Parts of Speech Tagging and Named Entity Recognition Tasks, Computer Science and Engineering, IIT Kharagpur, Advisor: Sudeshna Sarkar. [thesis]