Mova0.5 pre-release⌕
☰
home / docs / papers / authors / Amir Pouran Ben Veyseh

Amir Pouran Ben Veyseh

2 paper cards in Mova's library · 2019–2021

Amir Pouran Ben Veyseh wrote 2 of the papers Mova reads, in 2019–2021, most of them on Treebanks; often with Thien Huu Nguyen, Dejing Dou, Minh Van Nguyen.

OpenAlex · ORCID · h-index 17 · 2380 citations · 45 works — openalex, 2026-10-18

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology · ORCID

Topics: Treebanks 1

Papers

  1. Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing (2021)
    Trankit is a toolkit for many languages built on one shared XLM-RoBERTa encoder, with small language-specific adapters plugged into each layer, so that each language or task changes only its adapter and its output layers.
  2. Graph based Neural Networks for Event Factuality Prediction using Syntactic and Semantic Structures (2019)
    Event factuality prediction gives a real score in [−3, +3] for an event mention. Cue words that set the factuality can be far from the event word in the sentence, and a dependency tree can reach them while a sequential model can weigh them by meaning. The model has three parts: BERT and two BiLSTM layers for the…

Co-authors (4)

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/authors/amir-pouran-ben-veyseh/