328 подписчиков
180 видео
PaVeDa - Pavia Verbs Database: Challenges and Perspectives #SIGTYP
Revisiting Dependency Length and Intervener Complexity Minimisation on a Parallel Corpus in 35 Langs
Adapting XLM-RoBERTa for Ancientand Historical Languages
Multilingual BERT has an Accent: Evaluating English Influences on Fluency in Multilingual Models
Allen Institute for AI:Shared Task on Word Embedding Evaluation for Ancient and Historical Languages
SIGTYP 2021: Claire Bowern (Keynote)
ParaNames: A Massively Multilingual Entity Name Corpus
You Can Have Your Data and Balance It Too: Towards Balanced and Efficient Multilingual Models
GUIDE: Creating Semantic Domain Dictionaries for Low-Resource Languages
The SIGTYP 2022 Shared Task on the Prediction of Cognate Reflexes (by Mattis List)
Compounds in Universal Dependencies: A Survey in Five European Languages
Sociolinguistically Informed Interpretability: A Case Study on Hinglish Emotion Classification
A Large-Scale Multilingual Study of Visual Constraints on Linguistic Selection of Descriptions
SIGTYP Lecture Series: Claire Bowern and Luke Lindemann. Part 1
Predicting Transfer for Improved Low-Resource Speech Recognition using Acoustic Pseudo-tokens
The Typology of Ellipsis: A Corpus for Linguistic Analysis and Machine Learning Applications
Are Sounds Sound for Phylogenetic Reconstruction?
ModeLing: A Novel Dataset for Testing Linguistic Reasoning in Language Models
Predicting Mandarin and Cantonese Adult Speakers’ Eye-Movement Patterns in Natural Reading
PaVeDa - Pavia Verbs Database: Challenges and Perspectives
Corpus-based Syntactic Typological Methods for Dependency Parsing Improvement
Computational Morphology and Lexicography Modeling of Modern StandardArabic Nominals
Isabel Papadimitriou: What Can We Learn about Language from Exploring Multilingual Language Models?
Gradual Language Model Adaptation Using Fine-Grained Typology
A New Dataset for Tonal and Segmental Dialectometry from the Yue- and Pinghua-Speaking Area
SIGTYP 2024 Shared Task on Word Embedding Evaluation for Ancient and Historical Languages
Language-Agnostic Measures Discriminate Inflection and Derivation
ÚFAL Submission for SIGTYP Supervised Cognate Detection Task
Does Transliteration Help Multilingual Language Modeling
Cross-lingual Transfer Learning with Persian
Enhancing Low-Resource Language Analysis With Character-Aware Hierarchical Transformers
