All the WebNLG papers are now online on our website:
https://t.co/oLmTzdB4e5,
including the WebNLG+ challenge report!
Looking forward to seeing you on 18 December at #INLG2020!
WebNLG workshop at #INLG2020 will feature 6 regular papers, the WebNLG+ challenge overview, and 15 system descriptions!
Preliminary program 👇👇👇
https://t.co/sSqc8XyPQQ
"A Case Study of NLG from Multimedia Data Sources: Generating Architectural Landmark Descriptions", using #Wikipedia article text, Wikimedia #Commons images, and #DBpedia triples.
(Mille et al, 2020)
https://t.co/EeQ6BWibhk
17 teams (1/3 of them was from industry) from 13 countries participated in WebNLG this year! They submitted 48 systems in total; the majority of them (33 systems) to RDF-to-text (English).
Automatic eval results are out: https://t.co/iBnJ8h4HgQ
Human eval is under way!
WebNLG 2020: the workshop on Natural Language Generation from the Semantic Web will happen virtually in December at #INLG2020
The workshop has two goals:
- To promote discussion on NLG and the Semantic Web
- To present the results of the WebNLG challenge
https://t.co/jqg1863Afl
In addition to the main conference, this year’s INLG will also host five wonderful workshops. You can find more information about the workshops on the conference website:
https://t.co/WFMCQHuKn9
#INLG2020#NLProc
The list of accepted workshops for #INLG2020 is now available on the conference website.
We will host five workshops:
- Discourse Theories for Text Planning
- NL4XAI
- NLG4HRI
- Evaluating NLG Evaluation
- WebNLG
https://t.co/1WLChCIEiX
The second WebNLG challenge (WebNLG+) is currently running!
57 people from 20 countries have already downloaded our train&dev data! 🌎🌍🌏
Please come and join us (you have time until mid-September):
https://t.co/NpizxVEBJQ
It is our pleasure to announce that three years after the first edition, the second WebNLG challenge will take place in 2020!
TL;DR: WebNLG goes bi-lingual (English, Russian) and bi-directional (generation and parsing)! 🎉
More info: https://t.co/NpizxVWcBo
Adjusted challenge dates are out!
30 April 2020: Release of some preliminary evaluation scripts
30 May 2020: Release of the final evaluation scripts
13 September 2020: Release of test data
27 September 2020: Entry submission
15-18 December 2020: Results presented at #INLG2020
New version 2.1 of WebNLG was released last November🥳 We cleaned 5.6K texts from misspellings and added missing semantic content. Check it out at https://t.co/6OnpDdYcX1 to see how WebNLG maps triples from @dbpedia to short texts.
Dear researchers in #NLG, we just released the new version of the enriched @WebNLG corpus, now with the test part of the data annotated. This is a valuable benchmark to test not only your end-to-end approaches, but also your pipeline ones. Check it out on https://t.co/y8Y6yVsQ1Z