Opendata, web and dolomites


Induction of Broad-Coverage Semantic Parsers

Total Cost €


EC-Contrib. €






Project "BroadSem" data sheet

The following table provides information about the project.


Organization address
postcode: EH8 9YL

contact info
title: n.a.
name: n.a.
surname: n.a.
function: n.a.
email: n.a.
telephone: n.a.
fax: n.a.

 Coordinator Country United Kingdom [UK]
 Total cost 1˙457˙185 €
 EC max contribution 1˙457˙185 € (100%)
 Programme 1. H2020-EU.1.1. (EXCELLENT SCIENCE - European Research Council (ERC))
 Code Call ERC-2015-STG
 Funding Scheme ERC-STG
 Starting year 2016
 Duration (year-month-day) from 2016-05-01   to  2021-04-30


Take a look of project's partnership.

# participants  country  role  EC contrib. [€] 
1    THE UNIVERSITY OF EDINBURGH UK (EDINBURGH) coordinator 1˙238˙212.00


 Project objective

In the last one or two decades, language technology has achieved a number of important successes, for example, producing functional machine translation systems and beating humans in quiz games. The key bottleneck which prevents further progress in these and many other natural language processing (NLP) applications (e.g., text summarization, information retrieval, opinion mining, dialog and tutoring systems) is the lack of accurate methods for producing meaning representations of texts. Accurately predicting such meaning representations on an open domain with an automatic parser is a challenging and unsolved problem, primarily because of language variability and ambiguity. The reason for the unsatisfactory performance is reliance on supervised learning (learning from annotated resources), with the amounts of annotation required for accurate open-domain parsing exceeding what is practically feasible. Moreover, representations defined in these resources typically do not provide abstractions suitable for reasoning. In this project, we will induce semantic representations from large amounts of unannotated data (i.e. text which has not been labeled by humans) while guided by information contained in human-annotated data and other forms of linguistic knowledge. This will allow us to scale our approach to many domains and across languages. We will specialize meaning representations for reasoning by modeling relations (e.g., facts) appearing across sentences in texts (document-level modeling), across different texts, and across texts and knowledge bases. Learning to predict this linked data is closely related to learning to reason, including learning the notions of semantic equivalence and entailment. We will jointly induce semantic parsers (e.g., log-linear feature-rich models) and reasoning models (latent factor models) relying on this data, thus, ensuring that the semantic representations are informative for applications requiring reasoning.


year authors and title journal last update
List of publications.
2017 Phong Le, Ivan Titov
Optimizing Differentiable Relaxations of Coreference Evaluation Metrics
published pages: , ISSN: , DOI:
Proceeding of Conference on Natural Language Learning (CoNLL) 2019-07-08
2017 Diego Marcheggiani, Anton Frolov, Ivan Titov
A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labeling
published pages: , ISSN: , DOI:
Proceeding of the Conference on Natural Language Learning (CoNLL) 2019-07-08
2017 Ashutosh Modi, Ivan Titov, Vera Demberg, Asad Sayeed, Manfred Pinkal
Modelling Semantic Expectation: Using Script Knowledge for Referent Prediction
published pages: 31-44, ISSN: 2307-387X, DOI:
Transactions of the Association for Computational Linguistics 2019-07-08
2018 Le, Phong; Titov, Ivan
Improving Entity Linking by Modeling Latent Relations between Mentions
published pages: , ISSN: , DOI:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics 1 2019-05-27
2017 Havrylov, Serhii; Titov, Ivan
Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols
published pages: , ISSN: , DOI:
Advances in Neural Information Processing Systems (NIPS) 2019-05-27
2018 Voita, Elena; Serdyukov, Pavel; Sennrich, Rico; Titov, Ivan
Context-Aware Neural Machine Translation Learns Anaphora Resolution
published pages: 1264-1274, ISSN: , DOI:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics 2019-05-14
2018 Marcheggiani, Diego; Titov, Ivan
Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling
published pages: 1506–1515, ISSN: , DOI:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP) 2019-05-14
2018 Arthur Bražinskas; Serhii Havrylov; Ivan Titov
Embedding Words as Distributions with a Bayesian Skip-gram Model
published pages: 1775–1789, ISSN: , DOI:
Proceedings of the 27th International Conference on Computational Linguistics (COLING) 2019-05-14
2019 Caio Corro; Ivan Titov
Differentiable Perturb-and-Parse: Semi-Supervised Parsing with a Structured Variational Autoencoder
published pages: , ISSN: , DOI:
International Conference on Learning Representations (ICLR) 2019-02-22
2018 Lyu, Chunchuan; Titov, Ivan
AMR Parsing as Graph Prediction with Latent Alignment
published pages: 397--407, ISSN: , DOI:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics 2019-05-27
2018 Schlichtkrull, Michael; Kipf, Thomas N.; Bloem, Peter; Berg, Rianne van den; Titov, Ivan; Welling, Max
Modeling Relational Data with Graph Convolutional Networks
published pages: 593-607, ISSN: , DOI:
15th Extended Semantic Web Conference (ESWC) 2019-05-27
2018 Marcheggiani, Diego; Bastings, Joost; Titov, Ivan
Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networks
published pages: , ISSN: , DOI:
Proceedings of the Conference of the North American Chapter of the Association for Computation Linguistics (NAACL) 2019-05-27
2017 Joost Bastings, Ivan Titov, Wilker Aziz, Diego Marcheggiani, Khalil Simaan
Graph Convolutional Encoders for Syntax-aware Neural Machine Translation
published pages: 1957-1967, ISSN: , DOI: 10.18653/v1/D17-1209
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing 2019-05-27

Are you the coordinator (or a participant) of this project? Plaese send me more information about the "BROADSEM" project.

For instance: the website url (it has not provided by EU-opendata yet), the logo, a more detailed description of the project (in plain text as a rtf file or a word file), some pictures (as picture files, not embedded into any word file), twitter account, linkedin page, etc.

Send me an  email ( and I put them in your project's page as son as possible.

Thanks. And then put a link of this page into your project's website.

The information about "BROADSEM" are provided by the European Opendata Portal: CORDIS opendata.

More projects from the same programme (H2020-EU.1.1.)

LapIt (2019)

Making AML treatment a clinical reality: A novel anti-IL7 receptor antibody to deliver Lap to 5LO positive cells

Read More  

ModGravTrial (2019)

Modified Gravity on Trial

Read More  

MEMO (2020)

The Memory of Solitons

Read More