Social event and conference dinner

Upon popular request, information has been added about the social event and the conference dinner. To be found in the Programme section, but also here (social event) and here (conference dinner). So, it is not a secret (anymore).

Welcome to INLG 2018

In just a few days, INLG 2018 will welcome a record number of participants, to both the main conference and the workshops. We are very much looking forward to meeting all of you. To help you on your way, the location page has been updated with information about the workshop venues. The campus is easy to reach by train and the buildings are a 5 minute walk from Tilburg University train station.

The address details of the Willem II stadium are: Goirlese Weg 34, 5026 PC Tilburg, and it can be easily reached from Tilburg Central train station by bus (line 1, 8, 132, 601).

Have a good trip, and see you at INLG!

Poster presentations

Several of you have asked about the dimensions and orientation of the poster boards for the poster presentation. To wit: the poster boards can hold posters of (at least) size A0 and are portrait oriented.

In addition, there is the possibility to have your poster printed in Tilburg, some options below:


Be aware that most printing companies need at least a few hours to print a poster and that prices vary from 10 to about 50 euro, depending on quality and company.

Registration is open!

It is now possible to register for INLG 2018! Please use the link under “registration” to do so at your earliest convenience.

Early bird registration starts now and ends Saturday, October 27. Late registration ends on Monday, November 5. On-site registration will remain possible during the whole conference.

If you experience any difficulty, please let us know.

Accepted papers for INLG 2018

We are pleased to announce that the following papers have been accepted for INLG 2018. A more detailed program will be announced shortly.

Long papers

  • A Master-Apprentice Approach to Automatic Creation of Cultural Satire — Khalid Alnajjar and Mika Hämäläinen
  • Designing and testing the messages produced by a virtual dietitian — Luca Anselma and Alessandro Mazzei
  • Evaluation methodologies in Automatic Question Generation 2013-2018 — Jacopo Amidei, Paul Piwek and Alistair Willis
  • SimpleNLG-ZH: a Linguistic Realisation Engine for Mandarin — Guanyi Chen, Kees van Deemter and Chenghua Lin
  • Learning to Flip the Bias of News Headlines — Wei-Fan Chen, Henning Wachsmuth, Khalid Al Khatib and Benno Stein
  • Syntactic Manipulation for Generating more Diverse and Interesting Texts — Jan Milan Deriu and Mark Cieliebak
  • Stylistically User-Specific Generation — Abdurrisyad Fikri, Hiroya Takamura and Manabu Okumura
  • LSTM Hypertagging — Reid Fu and Michael White
  • Specificity measures and reference — Albert Gatt, Nicolás Marín, Gustavo Rivas-Gervilla and Daniél Sánchez
  • Explainable Autonomy: A Study of Explanation Styles for Building Clear Mental Models through a Multimodal Interface — Francisco Garcia, David A Robb, Pedro Patron, Atanas Ivaylov Laskov and Helen Hastie
  • End-to-End Content and Plan Selection for Data-to-Text Generation — Sebastian Gehrmann, Falcon Dai, Henry Elder and Alexander Rush
  • Treat the system like a human student: Automatic naturalness evaluation of generated text without reference texts — Isabel Groves, Ye Tian and Ioannis Douratsos
  • Neural Generation of Diverse Questions using Answer Focus, Contextual and Linguistic Features — Vrindavan Harrison and Marilyn Walker
  • Sequence-to-Sequence Models for Data-to-Text Natural Language Generation: Word- vs. Character-based Processing and Output Diversity — Glorianna Jagfeld, Sabrina Beer and Ngoc Thang Vu
  • Characterizing Variation in Crowd-Sourced Data for Training Neural Language Generators to Produce Stylistically Varied Outputs — Juraj Juraska and Marilyn Walker
  • Automated learning of templates for data-to-text generation: comparing rule-based, statistical and neural methods — Chris van der Lee, Emiel Krahmer and Sander Wubben
  • Statistical NLG for Generating the Content and Form of Referring Expressions — Xiao Li, Kees van Deemter and Chenghua Lin
  • Content Aware Source Code Change Description Generation — Pablo Loyola, Edison Marrese-Taylor, Jorge Balazs, Yutaka Matsuo and Fumiko Satoh
  • Adapting Descriptions of People to the Point of View of a Moving Observer — Gonzalo Méndez, Raquel Hervas, Pablo Gervás, Ricardo de la Rosa and Daniel Ruiz
  • Underspecified Universal Dependency Structures as Inputs for Multilingual Surface Realisation — Simon Mille, Anja Belz and Leo Wanner
  • BENGAL: An Automatic Benchmark Generator for Entity Recognition and Linking — Axel Ngonga, Michael Röder, Diego Moussallem, Ricardo Usbeck and René Speck
  • Automatically Generating Questions about Novel Metaphors in Literature — Natalie Parde and Rodney Nielsen
  • Generation of Company descriptions using concept-to-text and text-to-text deep models: dataset collection and systems evaluation — Raheel Qader, Khoder Jneid, François Portet and Cyril Labbe
  • Can Neural Generators for Dialogue Learn Sentence Planning and Discourse Structuring? — Lena Reed, Shereen Oraby and Marilyn Walke
  • Sentence Packaging in Text Generation from Semantic Graphs as a Community Detection Problem — Alexander Shvets, Simon Mille and Leo Wanner
  • Handling Rare Items in Data-to-Text Generation — Anastasia Shimorina and Claire Gardent
  • Neural Transition-based Syntactic Linearization — Linfeng Song, Yue Zhang and Daniel Gildea
  • Generating E-Commerce Product Titles and Predicting their Quality — José G. C. de Souza, Michael Kozielski, Prashant Mathur, Ernie Chang, Marco Guerini, Matteo Negri, Marco Turchi and Evgeny Matusov
  • Comprehension Driven Document Planning in Natural Language Generation Systems — Craig Thomson, Ehud Reiter and Somayajulu Sripada
  • Narrating a Knowledge Base — Qingyun Wang, Xiaoman Pan, Lifu Huang, Boliang Zhang, Zhiying Jiang, Heng Ji and Kevin Knight
  • Decoding Strategies for Neural Referring Expression Generation — Sina Zarrieß and David Schlangen
  • Adapting Neural Single-Document Summarization Model for Abstractive Multi-Document Summarization: A Pilot Study — Jianmin Zhang, Jiwei Tan and Xiaojun Wan


Short papers

  • Char2char Generation with Reranking for the E2E NLG Challenge — Shubham Agarwal, Marc Dymetman and Eric Gaussier
  • Improving Context Modelling in Multimodal Dialogue Generation — Shubham Agarwal, Ondřej Dušek, Ioannis Konstas and Verena Rieser
  • Generating Market Comments Referring to External Resources — Tatsuya Aoki, Akira Miyazawa, Kasumi Aoki, Keiichi Goshima, Tatsuya Ishigaki, Ichiro Kobayashi, Hiroya Takamura and Yusuke Miyao
  • SpatialVOC2K: A Multilingual Dataset of Images with Annotations and Features for Spatial Relations between Objects — Anja Belz and Adrian Muscat
  • Adding the Third Dimension to Spatial Relation Detection in 2D Images — Brandon Birmingham, Adrian Muscat and Anja Belz
  • Automatic Opinion Question Generation — Yllias Chali and Tina Baghaee
  • Modelling Pro-drop with the Rational Speech Acts Model — Guanyi Chen, Kees van Deemter and Chenghua Lin
  • Self-Learning Architecture for Natural Language Generation — Hyungtak Choi, Siddarth KM, Haehun Yang, Heesik Jeon, Inchul Hwang and Jihie Kim
  • Final Report of the E2E NLG Challenge — Ondřej Dušek, Jekaterina Novikova and Verena Rieser
  • E2E NLG Challenge Submission: Towards Controllable Generation of Diverse Natural Language — Henry Elder, Sebastian Gehrmann, Alexander O’Connor and Qun Liu
  • Enriching the WebNLG corpus — Thiago Castro Ferreira, Diego Moussallem, Emiel Krahmer and Sander Wubben
  • Towards making NLG a voice for interpretable Machine Learning — James Forrest, Somayajulu Sripada, Wei Pang and George Coghill
  • Adapting SimpleNLG to Galician language — Andrea Cascallar Fuentes, Alejandro Ramos Soto and Alberto Bugarín Diz
  • Template-based multilingual football reports generation using Wikidata as a knowledge base — Lorenzo Gatti, Chris van der Lee and Mariët Theune
  • Toward Bayesian Synchronous Tree Substitution Grammars for Sentence Planning — David M. Howcroft, Dietrich Klakow and Vera Demberg
  • The Task Matters: Comparing Image Captioning and Task-Based Dialogical Image Description — Nikolai Ilinykh, Sina Zarrieß and David Schlangen
  • Going Dutch: Creating SimpleNLG-NL — Ruud de Jong and Mariët Theune
  • Generating Summaries of Sets of Consumer Products: Learning from Experiments — Kittipitch Kuptavanich, Ehud Reiter, Kees van Deemter and Advaith Siddharthan
  • Neural sentence generation from formal semantics — Kana Manome, Masashi Yoshikawa, Hitomi Yanaka, Pascual Martínez-Gómez, Koji Mineshima and Daisuke Bekki
  • Deep Graph Convolutional Encoders for Structured Data to Text Generation — Diego Marcheggiani and Laura Perez-Beltrachini
  • Talking about other people: an endless range of possibilities — Emiel van Miltenburg, Desmond Elliott and Piek Vossen
  • E2E NLG Challenge: Neural Models vs. Templates — Yevgeniy Puzikov and Iryna Gurevych
  • The E2E NLG Challenge: A Tale of Two Systems — Frank Schilder, Charese Smiley, Elnaz Davoodi and Dezhao Song
  • Meteorologists and Students: A resource for language grounding of geographical descriptors — Alejandro Ramos Soto, Ehud Reiter, Kees van Deemter, Jose Alonso and Albert Gatt
  • Cyclegen: Cyclic consistency based product review generator from attributes — Vasu Sharma, Harsh Sharma, Ankita Bishnu and Labhesh Patel
  • Automatic Evaluation of Neural Personality-based Chatbots — Yujie Xing and Raquel Fernández


Demo presentations

  • Interactive health insight miner: an adaptive, semantic-based approach —Isabel Funke, Rim Helaoui and Aki Harma
  • Poem Machine – a Co-creative NLG Web Application for Poem Writing — Mika Hämäläinen
  • Japanese Advertising Slogan Generator using Case Frame and Word Vector — Kango Iwama and Yoshinobu Kano
  • Multi-Language Surface Realisation as REST API based NLG Microservice — Andreas Madsack, Johanna Heininger, Nyamsuren Davaasambuu, Vitaliia Voronik, Michael Käufl and Robert Weißgraeber

Deadline extenstion, location and workshops

(1) Upon multiple requests, we have decided to **extend** the deadline for submissions with one week. The new deadline is July 16, 2018.

(2) The location of the main INLG conference is known and exciting: it will be organized in the conference center of the Koning Willem II Stadion, the home of the Tilburg soccer team. The conference will start on Monday afternoon (November 5), with the invited tutorial of Yoav Goldberg.

(3) The main conference will be preceded on Monday morning (November 5) by three workshops, and followed by two more workshop as well as a full day hackathon on Thursday (November 8), all organized at Tilburg University.  The list of workshops is:

Monday-morning, November 5, 2018 (Tilburg University)

  • 3rd Workshop on Computational Creativity in Language Generation (CC-NLG 2018)
  • Workshop on Intelligent Interactive Systems and Language Generation (2IS&NLG)
  • Workshop on Adaptive NLG

Thursday (all day), November 8, 2018 (Tilburg University)

  • Workshop on Natural Language Generation for Human–Robot Interaction
  • Workshop on Text adaptation

More information on the workshops will follow soon.

Invited speakers announce and online submission system up and running

(1) We are proud to announce the invited speakers for INLG 2018:

  • Yoav Goldberg (Bar Ilan University, Israel, who will give an invited tutorial on Neural NLG),
  • Lillian Lee (Cornell University, Ithaca, USA), and
  • Verena Rieser (Heriot-Watt University, Edinburgh, UK).

(2) Please also note that the online submission system is up and running here.

Call for papers

We invite the submission of long and short papers, as well as system demonstrations, related to all aspects of Natural Language Generation (NLG), including data-to-text, concept-to-text, text-to-text and vision-to-text approaches. Accepted papers will be presented as oral talks or posters. Read on