State-of-the-Art Semantic Resources Development in Multi-language NLP

cpa where do we go from here research institute n.w
1 / 7
Embed
Share

Explore a collaborative project focusing on developing semantic resources for English, Spanish, Italian, and Czech using Collaborative Parsing Architecture (CPA). The project aims to enhance NLP semantic and syntactic parsers, utilizing innovative models and tasks such as phrase sense disambiguation, metonymy resolution, and more.

  • NLP
  • Semantic Resources
  • Multi-language
  • Collaboration
  • Syntax

Uploaded on | 0 Views


Download Presentation

Please find below an Image/Link to download the presentation.

The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.

You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.

The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.

E N D

Presentation Transcript


  1. CPA: Where do we go from here? Research Institute for Information and Language Processing, University of Wolverhampton; UPF Barcelona; University of Pavia, Dept of Humanities; Masaryk University, Faculty of Informatics, Brno; 1

  2. Context |European Collaboration/Partnership 2

  3. Aims Develop state-of-the-art semantic resources using CPA for English, Spanish, Italian, Czech Contribute to the improvement of NLP semantic and syntactic parsers Trade on the interaction between syntax and semantics Possible model: Czech Verbalex 3

  4. Tasks Phrase sense disambiguation Phrase sense discrimination Metonymy resolution (including coercion) Figurative language (metaphor) resolution Ontology-driven textual inference - RTE (Recognising Textual Entailment) 4

  5. Resource Compilation Annotated diverse corpora - inter-annotator agreement Populated corpus-driven cross-linguistic ontology Inter-connected pattern dictionaries for all participant languages 5

  6. Target Applications (1) Applications in computational linguistics Machine translation Idiomatic language generation Information extraction Textual entailment Semi-automatic taxonomy induction Contribution to text simplification 6

  7. Target Applications (2) Language teaching Natural phraseology Error correction Prioritization and choices for syllabus development Pedagogical Dictionaries 7

More Related Content