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”

Constructing Code-mixed Universal Dependency Forest for Unbiased Cross-lingual Relation Extraction

The result's identifiers

  • Result code in IS VaVaI

    <a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A4ZR6BPLD" target="_blank" >RIV/00216208:11320/23:4ZR6BPLD - isvavai.cz</a>

  • Result on the web

    <a href="http://arxiv.org/abs/2305.12258" target="_blank" >http://arxiv.org/abs/2305.12258</a>

  • DOI - Digital Object Identifier

    <a href="http://dx.doi.org/10.48550/arXiv.2305.12258" target="_blank" >10.48550/arXiv.2305.12258</a>

Alternative languages

  • Result language

    angličtina

  • Original language name

    Constructing Code-mixed Universal Dependency Forest for Unbiased Cross-lingual Relation Extraction

  • Original language description

    "Latest efforts on cross-lingual relation extraction (XRE) aggressively leverage the language-consistent structural features from the universal dependency (UD) resource, while they may largely suffer from biased transfer (e.g., either target-biased or source-biased) due to the inevitable linguistic disparity between languages. In this work, we investigate an unbiased UD-based XRE transfer by constructing a type of code-mixed UD forest. We first translate the sentence of the source language to the parallel target-side language, for both of which we parse the UD tree respectively. Then, we merge the source-/target-side UD structures as a unified code-mixed UD forest. With such forest features, the gaps of UD-based XRE between the training and predicting phases can be effectively closed. We conduct experiments on the ACE XRE benchmark datasets, where the results demonstrate that the proposed code-mixed UD forests help unbiased UD-based XRE transfer, with which we achieve significant XRE performance gains."

  • 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