Yannis Konstas

Yannis Konstas

Assistant Professor (Lecturer)

Office: EM 1.46

Email: i.konstas@hw.ac.uk

Mailing Address:
School of Mathematical and
Computer Sciences,
Heriot Watt University,
Edinburgh, Scotland, UK EH14 4AS.

Research

I am an assistant professor (lectuter according to the UK system) at Heriot-Watt University

My main research interests focus on the area of Natural Language Processing (NLP) and Natural Language Generation (NLG) with an emphasis on data-driven machine learning methods.

In particular, I am investigating generating text from meaning representations, programming language code, as well as generating stories from sequences of generic events, or other educational domains such as Math word problems. I am also interested in multi-disciplinary applications of NLP in the context of Dialogue Systems and Conversational Agents embedded in autonomous robots.
If you are interested in doing a PhD have a look here.
I continuously enjoy investigating new research fi elds, hence I have also acquired skills in Psycholinguistically-Motivated Parsing and Semantics, as well as Information Retrieval from my past employments.
I was a postdoctoral researcher in the department of Computer Science & Engineering, at the University of Washington, working with Luke Zettlemoyer, and Yejin Choi, between 2015 ans 2017.
I have also worked as a research associate (post-doc) at the University of Edinburgh, with Frank Keller and Mirella Lapata, on the SynSem EPSRC project, aiming to integrate semantics into a full syntactic parser. 
I completed my PhD in 2013, 'Joint Models for Concept-to-text Generation', at the University of Edinburgh, supervised by Mirella Lapata.


Publications

2017

Ioannis Konstas, Srinivasan Iyer, Mark Yatskar, Yejin Choi, Luke Zettlemoyer. 2017. Neural AMR: Sequence-to-Sequence Models for Parsing and Generation. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, Vancouver, Canada. [pdf] [code]

Srinivasan Iyer, Ioannis Konstas, Alvin Cheung, Jayant Krishnamurthy, Luke Zettlemoyer. 2017. Learning a Neural Semantic Parser from User Feedback. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, Vancouver, Canada. [pdf]

Roy Schwartz, Maarten Sap, Ioannis Konstas, Leila Zilles, Yejin Choi and Noah A. Smith. 2017. The Effect of Different Writing Tasks on Linguistic Style: A Case Study of the ROC Story Cloze Task. In Proceedings of the 21st SIGNLL Conference on Computational Natural Language Learning, Vancouver, Canada. [pdf]

Roy Schwartz, Maarten Sap, Ioannis Konstas, Leila Zilles, Yejin Choi and Noah A. Smith. 2017. Story Cloze Task: UW NLP System LSDSem 2017 shared task. (Best performing system) [pdf]

2016

Rik Koncel-Kedziorski, Ioannis Konstas, Luke Zettlemoyer and Hannaneh Hajishirzi. 2016. A Theme-Rewriting Approach for Generating Algebra Word Problems. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, Austin, USA. [pdf] [bib]

Srinivasan Iyer, Yannis Konstas, Alvin Cheung, Luke Zettlemoyer. 2016. Summarizing Source Code using a Neural Attention Model. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, Berlin, Germany. [pdf] [bib]

2015

Ioannis Konstas and Frank Keller. 2015. Semantic Role Labeling improves incremental parsing. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics. Beijing, China. [pdf] [bib]

2014

Ioannis Konstas, Frank Keller, Vera Demberg and Mirella Lapata. 2014. Incremental Semantic Role Labeling with Tree Adjoining Grammar. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Doha, Qatar. [pdf] [bib] [slides] [video]

Ioannis Konstas. 2014. Joint Models for Concept-to-Text Generation, PhD Thesis, University of Edinburgh. [pdf]

2013

Ioannis Konstas and Mirella Lapata. 2013. A Global Model for Concept-to-Text Generation, Journal of Artificial Intelligence Research, Volume 48, pages 305-346. [pdf]

Ioannis Konstas and Mirella Lapata. 2013. Inducing Document Plans for Concept-to-Text Generation. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 1503-1514, Seattle, Washington, USA. [pdf] [bib] [slides]

Silvia Pareti, Tim O'Keefe, Ioannis Konstas, James R. Curran, and Irena Koprinska. Automatically Detecting and Attributing Indirect Quotations. 2013. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 989-999, Seattle, Washington, USA. [pdf]

2012

Ioannis Konstas and Mirella Lapata. 2012. Concept-to-text generation via discriminative reranking. In Proceedings of the 50th Annual Meeting of the Association for  Computational Linguistics (Volume 1: Long Papers), pages 369-378, Jeju Island, Korea. [pdf] [bib] [slides]

Ioannis Konstas and Mirella Lapata. 2012. Unsupervised concept-to-text generation with hypergraphs. In Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 752-761, Montreal, Canada. [pdf] [bib] [slides]

2011

Iván Cantador, Ioannis Konstas, Joemon M. Jose. Categorising Social Tags to Improve Folksonomy-based Recommendations. 2011. Web Semantics: Science, Services and Agents on the World Wide Web, 9(1):1 – 15.

2009

Ioannis Arapakis, Ioannis Konstas, Joemon M. Jose. 2009. Using facial expressions and peripheral physiological signals as implicit indicators of topical relevance. In ACM Multimedia, pages 461-470, Singapore. [pdf]

Ioannis Konstas, Vassilios Stathopoulos, Joemon M. Jose. 2009. On social networks and collaborative recommendation. In SIGIR, pages 195-202, Boston, MA, USA. [pdf]

Ioannis Arapakis, Ioannis Konstas, Joemon M. Jose, Ioannis Kompatsiaris. 2009. Modeling facial expressions and peripheral physiological signals to predict topical relevance. In SIGIR, pages 728-729, Boston, MA, USA. [pdf]

Oliver Lemon, Ioannis Konstas. 2009. User Simulations for Context-Sensitive Speech Recognition in Spoken Dialogue Systems. In EACL, pages 505-513, Athens, Greece. [pdf] [bib]


Invited Talks

  • Building adaptable and scalable Natural Language Generation Systems, AUEB / ISI / Sheffield / HWU / UIC, Spring - Summer 2017. [slides]
  • Early Goals that Remain Uphill Battles, Uphill Battles in Language Processing Workshop, Austin, EMNLP 2016. [slides]
  • NeuGen: Text Generation from Meaning Representations, Microsoft Research, Redmond, May 2016. [slides]
  • Learning to generate: Concept-to-text generation using machine learning, Invited Speaker - NLG Summer School, Aberdeen, July 2015. [slides]
  • Incremental Semantic Role Labeling with Tree Adjoining Grammar, University of Edinburgh, October 2014. [slides]
  • Joint models for Concept-to-Text Generation, University of Washington, October 2013 - University of Potsdam / Saarland, January 2014. [slides]