Opendata, web and dolomites


Fast Natural Language Parsing for Large-Scale NLP

Total Cost €


EC-Contrib. €






 FASTPARSE project word cloud

Explore the words cloud of the FASTPARSE project. It provides you a very rough idea of what is the project "FASTPARSE" about.

patterns    circulating    avoiding    machine    vast    model    public    parsers    hundred    faster    convenient    explicit    nlp    compress    fronts    rely    joint    ed    mining    engines    web    data    unfortunately    written    opinion    translation    constitutes    reuse    communicate    acceptable    syntactic    calculation    kinds    barriers    forms    granted    prohibitive    eliminate    redundant    analyze    hardware    intermediate    parsing    fundamental    extract    unstructured    answering    societies    individuals    unprecedented    recode    break    language    bottleneck    digest    cognitively    technologies    question    calculations    summarization    context    discover    accurate    suitable    natural    form    inspired    amounts    search    standard    roadblock    extraction    computational    documents    generate    techniques    small    power    algorithms    fastparse    modern    fast    monitor    linguistic    regularities    internet    popularization    leveraging    people    human    sentences    speed    asset   

Project "FASTPARSE" data sheet

The following table provides information about the project.


Organization address
postcode: 15001

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 Spain [ES]
 Project website
 Total cost 1˙481˙747 €
 EC max contribution 1˙481˙747 € (100%)
 Programme 1. H2020-EU.1.1. (EXCELLENT SCIENCE - European Research Council (ERC))
 Code Call ERC-2016-STG
 Funding Scheme ERC-STG
 Starting year 2017
 Duration (year-month-day) from 2017-02-01   to  2022-01-31


Take a look of project's partnership.

# participants  country  role  EC contrib. [€] 
1    UNIVERSIDADE DA CORUNA ES (LA CORUNA) coordinator 1˙481˙747.00


 Project objective

The popularization of information technology and the Internet has resulted in an unprecedented growth in the scale at which individuals and institutions generate, communicate and access information. In this context, the effective leveraging of the vast amounts of available data to discover and address people's needs is a fundamental problem of modern societies.

Since most of this circulating information is in the form of written or spoken human language, natural language processing (NLP) technologies are a key asset for this crucial goal. NLP can be used to break language barriers (machine translation), find required information (search engines, question answering), monitor public opinion (opinion mining), or digest large amounts of unstructured text into more convenient forms (information extraction, summarization), among other applications.

These and other NLP technologies rely on accurate syntactic parsing to extract or analyze the meaning of sentences. Unfortunately, current state-of-the-art parsing algorithms have high computational costs, processing less than a hundred sentences per second on standard hardware. While this is acceptable for working on small sets of documents, it is clearly prohibitive for large-scale processing, and thus constitutes a major roadblock for the widespread application of NLP.

The goal of this project is to eliminate this bottleneck by developing fast parsers that are suitable for web-scale processing. To do so, FASTPARSE will improve the speed of parsers on several fronts: by avoiding redundant calculations through the reuse of intermediate results from previous sentences; by applying a cognitively-inspired model to compress and recode linguistic information; and by exploiting regularities in human language to find patterns that the parsers can take for granted, avoiding their explicit calculation. The joint application of these techniques will result in much faster parsers that can power all kinds of web-scale NLP applications.


year authors and title journal last update
List of publications.
2020 Daniel Fernández-González, Carlos Gómez-Rodríguez
Discontinuous Constituent Parsing with Pointer Networks
published pages: In press, ISSN: , DOI:
Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20) 2020-03-11
2020 David Vilares, Michalina Strzyz, Anders Søgaard, Carlos Gómez-Rodríguez
Parsing as Pretraining
published pages: In press, ISSN: , DOI:
Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20) 2020-03-11
2020 Carlos Gómez-Rodríguez, Morten H. Christiansen, Ramon Ferrer-i-Cancho
Cognitive Constraints Built into Formal Grammars: Implications for Language Evolution
published pages: , ISSN: , DOI: 10.17617/2.3190925
The Evolution of Language: Proceedings of the 13th International Conference (EvoLang13) 2020-03-11
2019 Michalina Strzyz, David Vilares, Carlos Gómez-Rodríguez
Sequence Tagging for Fast Dependency Parsing
published pages: 49, ISSN: 2504-3900, DOI: 10.3390/proceedings2019021049
Proceedings 21/1 2020-03-11
2018 Mark Dáibhidh Anderson, David Vilares
Increasing NLP Parsing Efficiency with Chunking
published pages: 1160, ISSN: 2504-3900, DOI: 10.3390/proceedings2181160
Proceedings 2/18 2019-08-29
2019 Daniel Fernández-González, Carlos Gómez-Rodríguez
Faster shift-reduce constituent parsing with a non-binary, bottom-up strategy
published pages: 559-574, ISSN: 0004-3702, DOI: 10.1016/j.artint.2019.07.006
Artificial Intelligence 275 2019-08-29
2019 Michalina Strzyz, Carlos Gómez-Rodríguez
Speeding Up Natural Language Parsing by Reusing Partial Results
published pages: , ISSN: , DOI:
Proceedings of the 20th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing 2019) 2019-08-29
2019 Yerai Doval, Carlos Gómez-Rodríguez
Comparing neural- and N-gram-based language models for word segmentation
published pages: 187-197, ISSN: 1532-2882, DOI: 10.1002/asi.24082
Journal of the Association for Information Science and Technology 70/2 2019-08-29
2017 Gómez Rodríguez, Carlos
Towards fast natural language parsing: FASTPARSE ERC Starting Grant
published pages: 121-124, ISSN: 1135-5948, DOI:
Procesamiento del Lenguaje Natural 59 2019-06-13
2019 Carlos Gómez-Rodríguez, Iago Alonso-Alonso, David Vilares
How important is syntactic parsing accuracy? An empirical evaluation on rule-based sentiment analysis
published pages: , ISSN: 0269-2821, DOI: 10.1007/s10462-017-9584-0
Artificial Intelligence Review 2019-06-13
2018 R. Ferrer-i-Cancho, C. Gómez-Rodríguez, J.L. Esteban
Are crossing dependencies really scarce?
published pages: 311-329, ISSN: 0378-4371, DOI: 10.1016/j.physa.2017.10.048
Physica A: Statistical Mechanics and its Applications 493 2019-06-13
2017 David Vilares, Miguel A. Alonso, Carlos Gómez-Rodríguez
Tratamiento sintáctico de la negación en análisis del sentimiento monolingüe y multilingüe
published pages: 39-46, ISSN: , DOI:
Proc. of Taller de NEGación en ESpañol (NEGES 2017) 2019-06-13
New treebank or repurposed? On the feasibility of cross-lingual parsing of Romance languages with Universal Dependencies
published pages: 91-122, ISSN: 1351-3249, DOI: 10.1017/S1351324917000377
Natural Language Engineering 24/01 2019-06-13
2017 Carlos Gómez-Rodríguez, Ramon Ferrer-i-Cancho
Scarcity of crossing dependencies: A direct outcome of a specific constraint?
published pages: 62304, ISSN: 2470-0045, DOI: 10.1103/PhysRevE.96.062304
Physical Review E 96/6 2019-06-13
2018 Chen, Xinying; Gómez Rodríguez, Carlos; Ferrer Cancho, Ramon
A dependency look at the reality of constituency
published pages: 104-106, ISSN: 1617-8351, DOI:
Glottometrics 40 2019-06-13
2017 Carlos Gómez-Rodríguez
On the relation between dependency distance, crossing dependencies, and parsing
published pages: 200-203, ISSN: 1571-0645, DOI: 10.1016/j.plrev.2017.05.007
Physics of Life Reviews 21 2019-06-13
2018 Carlos Gómez-Rodríguez
Natural Language Parsing: Progress and Challenges
published pages: 159-175, ISSN: 1889-3805, DOI:
Boletín de Estadística e Investigación Operativa 34(2) 2019-06-13
2018 Yerai Doval, David Vilares
On the Processing and Analysis of Microtexts: From Normalization to Semantics
published pages: 1170, ISSN: 2504-3900, DOI: 10.3390/proceedings2181170
Proceedings 2/18 2019-08-29
2019 Ramon Ferrer-i-Cancho, Carlos Gómez-Rodríguez
Anti dependency distance minimization in short sequences. A graph theoretic approach
published pages: In press, ISSN: 0929-6174, DOI:
Journal of Quantitative Linguistics 2019-08-29
2019 Mark Anderson, David Vilares, Carlos Gómez-Rodríguez
Artificially Evolved Chunks for Morphosyntactic Analysis
published pages: To appear, ISSN: , DOI:
Proceedings of the 18th International Workshop on Treebanks and Linguistic Theories 2019-08-29

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

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


The Mass Politics of Disintegration

Read More  


Economic Fluctuations, Productivity Growth and Stabilization Policies: A Keynesian Growth Perspective

Read More  

Photopharm (2020)

Photopharmacology: From Academia toward the Clinic.

Read More