Opendata, web and dolomites

SEMANTAX SIGNED

Form-Independent Semantics for Natural Language Understanding

Total Cost €

0

EC-Contrib. €

0

Partnership

0

Views

0

Project "SEMANTAX" data sheet

The following table provides information about the project.

Coordinator
THE UNIVERSITY OF EDINBURGH 

Organization address
address: OLD COLLEGE, SOUTH BRIDGE
city: EDINBURGH
postcode: EH8 9YL
website: www.ed.ac.uk

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˙996˙792 €
 EC max contribution 1˙996˙792 € (100%)
 Programme 1. H2020-EU.1.1. (EXCELLENT SCIENCE - European Research Council (ERC))
 Code Call ERC-2016-ADG
 Funding Scheme ERC-ADG
 Starting year 2017
 Duration (year-month-day) from 2017-08-01   to  2022-07-31

 Partnership

Take a look of project's partnership.

# participants  country  role  EC contrib. [€] 
1    THE UNIVERSITY OF EDINBURGH UK (EDINBURGH) coordinator 1˙996˙792.00

Map

 Project objective

The project addresses the most important open problem in NLP, to develop a robust semantics that is invariant across different linguistic forms within a language and across languages, and embodies aspects of common-sense knowledge. It will be derived by machine-learning from machine-reading of vast amounts of text, using an existing state-of-the-art wide-coverage CCG semantic parser developed under previous ERC funding to the PI, initially to build traditional semantic analyses of sentences relating named entities.

Patterns of entailment across semantic expressions relating the same named entities will be then detected across other entities of the same types, to construct directed entailment graphs. Cliques within the graphs constitute paraphrases, and can be collapsed to a single cluster identifier. The paraphrase-clustered entailment graph can then be used to redefine the semantics delivered by the parser as conjunctions of entailed paraphrase clusters, to make it invariant under paraphrase and common-sense entailment, yet compatible with a traditional logical operator semantics. The semantics will be extended to a wide range of logical operators, including tense, modality, aspect, and voice, and to implicative and evidential verbs, light verbs, multi-word expressions, and idioms. The method will be applied to semantic parsing, machine translation, knowledge-graph query, and the construction of large knowledge graphs or semantic nets from text, using spreading activation to limit growth in costs of updating and querying the knowledge graph.

In the later stages of the project, the paraphrase-clustered entailment semantics will form the bassi for an incremental semantic parser, using a novel shift-reduce architecture proposed for CCG by the PI in 2000, guided by a modern neural network parsing model acting as a categorial 'supertagger' and parser action model, for application to language modeling for the machine translation component.

 Publications

year authors and title journal last update
List of publications.
2019 Tim Hunter, Miloš Stanojević, Edward Stabler
The Active-Filler Strategy in a Move-Eager Left-Corner Minimalist Grammar Parser
published pages: 1-10, ISSN: , DOI: 10.18653/v1/w19-2901
Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics 2019 2020-04-01
2019 Sabine Weber, Mark Steedman
Construction and Alignment of Multilingual Entailment Graphs for Semantic Inference
published pages: 77-79, ISSN: , DOI:
Proceedings of the 2019 Workshop on Widening NLP 2019 2020-04-01
2018 Andrew McLeod, Mark Steedman
Meter Detection and Alignment of MIDI Performance
published pages: 113-119, ISSN: , DOI:
Proceedings of the International Society for Music Information Retrieval (ISMIR) 2019 2020-04-01
2019 Ida Szubert, Mark Steedman
Node Embeddings for Graph Merging: Case of Knowledge Graph Construction
published pages: 172-176, ISSN: , DOI: 10.18653/v1/d19-5321
Proceedings of the Thirteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-13) 2019 2020-04-01
2019 John Torr, Milos Stanojevic, Mark Steedman, Shay B. Cohen
Wide-Coverage Neural A* Parsing for Minimalist Grammars
published pages: 2486-2505, ISSN: , DOI: 10.18653/v1/p19-1238
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics 2019 2020-04-01
2019 Miloš Stanojević, Mark Steedman
CCG Parsing Algorithm with Incremental Tree Rotation
published pages: 228-239, ISSN: , DOI: 10.18653/v1/n19-1020
Proceedings of the 2019 Conference of the North 2019 2020-04-01
2017 Mark Steedman
The emergence of language
published pages: 579-590, ISSN: 0268-1064, DOI: 10.1111/mila.12160
Mind & Language 32/5 2019-04-18
2018 Mohammad Javad Hosseini, Nathanael Chambers, Siva Reddy, Xavier R. Holt Shay B. Cohen, Mark Johnson, Mark Steedman
Learning Typed Entailment Graphs with Global Soft Constraints
published pages: 703–718, ISSN: , DOI:
Transactions of the Association for Computational Linguistics 2018 2019-04-18
2018 Andrew McLeod, Mark Steedman
Evaluating Automatic Polyphonic Music Transcription
published pages: 42-49, ISSN: , DOI:
Proceedings of the 19th International Society for Music Information Retrieval Conference 19 2019-04-18
2019 Mark Steedman
Combinatory Categorial Grammar
published pages: , ISSN: , DOI:
Current Approaches to Syntax - A Comparative Handbook 2019 2019-04-18
2019 Thomas Kober, Sander Bijl de Vroe, Mark Steedman
Temporal and Aspectual Entailment
published pages: to appear, ISSN: , DOI:
Proceedings of the Conference on Computational Semantics 19 2019-04-18
2018 Andrew McLeod, Mark Steedman
Multi-pitch Detection and Voice Assignment for a cappella Recordings of Multiple Singers
published pages: 113-119, ISSN: , DOI:
Proceedings of the International Society for Music Information Retrieval Conference 19 2019-04-18
2017 Andrew McLeod, Rodrigo Schramm, Mark Steedman, Emmanouil Benetos
Automatic Transcription of Polyphonic Vocal Music
published pages: 1285, ISSN: 2076-3417, DOI: 10.3390/app7121285
Applied Sciences 7/12 2019-04-18
2018 Gozde Gul Sahin, Mark Steedman
Data Augmentation via Dependency Tree Morphing for Low-Resource Language
published pages: 5004-5009, ISSN: , DOI:
Proceedings of the Conference on Empirical Methods in Natural Language Processing Yearly 2019-04-18
2019 Mark Steedman
Form-Independent Meaning Representation for Eventualities
published pages: 605-623, ISSN: , DOI:
The Oxford Handbook of Event Structure (R. Truswell, ed.) 2019 2019-04-18
2019 Milos Stanojevic, Mark Steedman
CCG Parsing Algorithm with Incremental Tree Rotation
published pages: to appear, ISSN: , DOI:
Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics Yearly 2019-04-18
2018 Milos Stanojevic, Edward Stabler
A Sound and Complete Left-Corner Parsing for Minimalist Grammars
published pages: 65-74, ISSN: , DOI:
Proceedings of the Workshop on Cognitive Aspects of Computational Language Learning and Processing 8 2019-04-18
2018 Gozde Gul Sahin, Mark Steedman
Character-Level Models versus Morphology in Semantic Role Labeling
published pages: 386-396, ISSN: , DOI:
Proceedings of the Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) 56 2019-04-18
2018 Mark Steedman
The Lost Combinator
published pages: 613-629, ISSN: 0891-2017, DOI: 10.1162/coli_a_00328
Computational Linguistics 44/4 2019-04-18
2018 Liane Guillou, Christian Hardmeier
Automatic Reference-Based Evaluation of Pronoun Translation Misses the Point
published pages: 4797-4802, ISSN: , DOI:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing Yearly 2019-04-18

Are you the coordinator (or a participant) of this project? Plaese send me more information about the "SEMANTAX" 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 (fabio@fabiodisconzi.com) 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 "SEMANTAX" are provided by the European Opendata Portal: CORDIS opendata.

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

TORYD (2020)

TOpological many-body states with ultracold RYDberg atoms

Read More  

DOUBLE-TROUBLE (2020)

Replaying the ‘genome duplication’ tape of life: the importance of polyploidy for adaptation in a changing environment

Read More  

inhibiTOR (2020)

Novel selective mTORC1 inhibitors

Read More