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”

Dependency Parsing is More Parameter-Efficient with Normalization

The result's identifiers

  • Result code in IS VaVaI

    <a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F26%3AIUSTYWZM" target="_blank" >RIV/00216208:11320/26:IUSTYWZM - isvavai.cz</a>

  • Result on the web

    <a href="http://arxiv.org/abs/2505.20215" target="_blank" >http://arxiv.org/abs/2505.20215</a>

  • DOI - Digital Object Identifier

    <a href="http://dx.doi.org/10.48550/arXiv.2505.20215" target="_blank" >10.48550/arXiv.2505.20215</a>

Alternative languages

  • Result language

    angličtina

  • Original language name

    Dependency Parsing is More Parameter-Efficient with Normalization

  • Original language description

    Dependency parsing is the task of inferring natural language structure, often approached by modeling word interactions via attention through biaffine scoring. This mechanism works like self-attention in Transformers, where scores are calculated for every pair of words in a sentence. However, unlike Transformer attention, biaffine scoring does not use normalization prior to taking the softmax of the scores. In this paper, we provide theoretical evidence and empirical results revealing that a lack of normalization necessarily results in overparameterized parser models, where the extra parameters compensate for the sharp softmax outputs produced by high variance inputs to the biaffine scoring function. We argue that biaffine scoring can be made substantially more efficient by performing score normalization. We conduct experiments on semantic and syntactic dependency parsing in multiple languages, along with latent graph inference on non-linguistic data, using various settings of a $k$-hop parser. We train $N$-layer stacked BiLSTMs and evaluate the parser's performance with and without normalizing biaffine scores. Normalizing allows us to achieve state-of-the-art performance with fewer samples and trainable parameters. Code: https://github.com/paolo-gajo/EfficientSDP

  • 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

    2025

  • Confidentiality

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