CORDIS
EU research results

CORDIS

English EN

Form-Independent Semantics for Natural Language Understanding

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.
Leaflet | Map data © OpenStreetMap contributors, Credit: EC-GISCO, © EuroGeographics for the administrative boundaries

Host institution

THE UNIVERSITY OF EDINBURGH

Address

Old College, South Bridge
Eh8 9yl Edinburgh

United Kingdom

Activity type

Higher or Secondary Education Establishments

EU Contribution

€ 1 996 792

Beneficiaries (1)

Sort alphabetically

Sort by EU Contribution

Expand all

THE UNIVERSITY OF EDINBURGH

United Kingdom

EU Contribution

€ 1 996 792

Project information

Grant agreement ID: 742137

Status

Ongoing project

  • Start date

    1 August 2017

  • End date

    31 July 2022

Funded under:

H2020-EU.1.1.

  • Overall budget:

    € 1 996 792

  • EU contribution

    € 1 996 792

Hosted by:

THE UNIVERSITY OF EDINBURGH

United Kingdom