no code implementations • WS 2019 • Chris van der Lee, Albert Gatt, Emiel van Miltenburg, S Wubben, er, Emiel Krahmer
Currently, there is little agreement as to how Natural Language Generation (NLG) systems should be evaluated.
1 code implementation • WS 2018 • Thiago Castro Ferreira, Diego Moussallem, Emiel Krahmer, S Wubben, er
This paper describes the enrichment of WebNLG corpus (Gardent et al., 2017a, b), with the aim to further extend its usefulness as a resource for evaluating common NLG tasks, including Discourse Ordering, Lexicalization and Referring Expression Generation.
1 code implementation • WS 2018 • Chris van der Lee, Emiel Krahmer, S Wubben, er
The current study investigated novel techniques and methods for trainable approaches to data-to-text generation.
no code implementations • COLING 2018 • Chris van der Lee, Bart Verduijn, Emiel Krahmer, S Wubben, er
We present an evaluation of PASS, a data-to-text system that generates Dutch soccer reports from match statistics which are automatically tailored towards fans of one club or the other.
1 code implementation • COLING 2018 • Florian Kunneman, S Wubben, er, Antal Van den Bosch, Emiel Krahmer
In the second evaluation, the gold-standard pros and cons were assessed along with the system output.
1 code implementation • WS 2018 • Thiago Castro Ferreira, S Wubben, er, Emiel Krahmer
This study describes the approach developed by the Tilburg University team to the shallow task of the Multilingual Surface Realization Shared Task 2018 (SR18).
no code implementations • WS 2017 • Chris van der Lee, Emiel Krahmer, S Wubben, er
We present PASS, a data-to-text system that generates Dutch soccer reports from match statistics.
no code implementations • WS 2017 • Thiago Castro Ferreira, Iacer Calixto, S Wubben, er, Emiel Krahmer
In this paper, we study AMR-to-text generation, framing it as a translation task and comparing two different MT approaches (Phrase-based and Neural MT).
no code implementations • EACL 2017 • Thiago Castro Ferreira, Emiel Krahmer, S Wubben, er
The model relies on the REGnames corpus, a dataset with 53, 102 proper name references to 1, 000 people in different discourse contexts.
no code implementations • WS 2016 • Thiago Castro Ferreira, S Wubben, er, Emiel Krahmer
no code implementations • NAACL 2016 • Thiago Castro Ferreira, Emiel Krahmer, S Wubben, er
1 code implementation • LREC 2016 • Alice Frain, S Wubben, er
We test the viability of our data on the task of classification of satire.
no code implementations • ACL 2012 • S Wubben, er, Antal van den Bosch, Emiel Krahmer
Ranked #3 on Text Simplification on ASSET