Viktor Hangya
  • Bio
  • Publications
  • Projects
  • Experience
  • Recent & Upcoming Talks
    • Example Talk
  • Projects
    • Anchor Embeddings
    • MultiHS
    • TextLSP
    • UnsupPSE
  • Publications
    • A Study of the Class Imbalance Problem in Abusive Language Detection
    • How to Solve Few-Shot Abusive Content Detection Using the Data We Actually Have
    • Extending Multilingual Machine Translation through Imitation Learning
    • Label modification and bootstrapping for zero-shot cross-lingual hate speech detection
    • LMU at HaSpeeDe3: Multi-Dataset Training for Cross-Domain Hate Speech Detection
    • Multilingual Word Embeddings for Low-Resource Languages using Anchors and a Chain of Related Languages
    • Comparative Analysis of Cross-lingual Contextualized Word Embeddings
    • Don't Forget Cheap Training Signals Before Building Unsupervised Bilingual Word Embeddings
    • Improving Low-Resource Languages in Pre-Trained Multilingual Language Models
    • Adapting Entities across Languages and Cultures
    • Anchor-based Bilingual Word Embeddings for Low-Resource Languages
    • Cross-Lingual Transfer Learning for Hate Speech Detection
    • Do not neglect related languages: The case of low-resource Occitan cross-lingual word embeddings
    • Improving Machine Translation of Rare and Unseen Word Senses
    • Combining Word Embeddings with Bilingual Orthography Embeddings for Bilingual Dictionary Induction
    • Exploring Bilingual Word Embeddings for Hiligaynon, a Low-Resource Language
    • LMU Bilingual Dictionary Induction System with Word Surface Similarity Scores for BUCC 2020
    • Target-Level Sentiment Analysis on Various Genres
    • The LMU Munich System for the WMT20 Very Low Resource Supervised MT Task
    • Towards Handling Compositionality in Low-Resource Bilingual Word Induction
    • Better OOV Translation with Bilingual Terminology Mining
    • The LMU Munich Unsupervised Machine Translation System for WMT19
    • Unsupervised Parallel Sentence Extraction with Parallel Segment Detection Helps Machine Translation
    • An Unsupervised System for Parallel Corpus Filtering
    • Evaluating bilingual word embeddings on the long tail
    • LMU Munich's Neural Machine Translation Systems at WMT 2018
    • The LMU Munich Unsupervised Machine Translation Systems
    • Two Methods for Domain Adaptation of Bilingual Tasks: Delightfully Simple and Broadly Applicable
    • A comparative empirical study on social media sentiment analysis over various genres and languages
    • Latent Syntactic Structure-Based Sentiment Analysis
    • A Hungarian sentiment corpus manually annotated at aspect level
    • Automatic Construction of Domain Specific Sentiment Lexicons for Hungarian
    • SZTE-NLP: Aspect level opinion mining exploiting syntactic cues
    • Filtering and Polarity Detection for Reputation Management on Tweets
    • SZTE-NLP: Sentiment Detection on Twitter Messages
    • Target-oriented opinion mining from tweets
  • Projects
  • Blog
    • 👩🏼‍🏫 Teach academic courses
  • Experience
  • Teaching
    • Learn JavaScript
    • Learn Python

Improving Low-Resource Languages in Pre-Trained Multilingual Language Models

Jan 1, 2022·
Viktor Hangya
,
Hossain Shaikh Saadi
,
Alexander Fraser
· 0 min read
Cite URL
Type
Conference paper
Publication
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Last updated on Jan 1, 2022
← Don't Forget Cheap Training Signals Before Building Unsupervised Bilingual Word Embeddings Jan 1, 2022
Adapting Entities across Languages and Cultures Jan 1, 2021 →

© 2024 Me. This work is licensed under CC BY NC ND 4.0

Published with Hugo Blox Builder — the free, open source website builder that empowers creators.