All

What are you looking for?

All
Projects
Results
Organizations

Quick search

  • Projects supported by TA ČR
  • Excellent projects
  • Projects with the highest public support
  • Current projects

Smart search

  • That is how I find a specific +word
  • That is how I leave the -word out of the results
  • “That is how I can find the whole phrase”

Pre-Trained Language-Meaning Models for Multilingual Parsing and Generation

The result's identifiers

  • Result code in IS VaVaI

    <a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A3MSI6EE4" target="_blank" >RIV/00216208:11320/23:3MSI6EE4 - isvavai.cz</a>

  • Result on the web

    <a href="http://arxiv.org/abs/2306.00124" target="_blank" >http://arxiv.org/abs/2306.00124</a>

  • DOI - Digital Object Identifier

    <a href="http://dx.doi.org/10.48550/arXiv.2306.00124" target="_blank" >10.48550/arXiv.2306.00124</a>

Alternative languages

  • Result language

    angličtina

  • Original language name

    Pre-Trained Language-Meaning Models for Multilingual Parsing and Generation

  • Original language description

    "Pre-trained language models (PLMs) have achieved great success in NLP and have recently been used for tasks in computational semantics. However, these tasks do not fully benefit from PLMs since meaning representations are not explicitly included in the pre-training stage. We introduce multilingual pre-trained language-meaning models based on Discourse Representation Structures (DRSs), including meaning representations besides natural language texts in the same model, and design a new strategy to reduce the gap between the pre-training and fine-tuning objectives. Since DRSs are language neutral, cross-lingual transfer learning is adopted to further improve the performance of non-English tasks. Automatic evaluation results show that our approach achieves the best performance on both the multilingual DRS parsing and DRS-to-text generation tasks. Correlation analysis between automatic metrics and human judgements on the generation task further validates the effectiveness of our model. Human inspection reveals that out-of-vocabulary tokens are the main cause of erroneous results."

  • Czech name

  • Czech description

Classification

  • Type

    O - Miscellaneous

  • CEP classification

  • OECD FORD branch

    10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Result continuities

  • Project

  • Continuities

Others

  • Publication year

    2023

  • Confidentiality

    S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů