Image de couverture de livre

The Devil Is in the Word Alignment Details: On Translation-Based Cross-Lingual Transfer for Token Classification Tasks

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ebing, Benedikt, Glavaš, Goran
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

To Translate or Not to Translate: A Systematic Investigation of Translation-Based Cross-Lingual Transfer to Low-Resource Languages
par: Ebing, Benedikt, et autres
Publié: (2023)

TransAlign: Machine Translation Encoders are Strong Word Aligners, Too
par: Ebing, Benedikt, et autres
Publié: (2025)

One Script Instead of Hundreds? On Pretraining Romanized Encoder Language Models
par: Ebing, Benedikt, et autres
Publié: (2026)

ANHALTEN: Cross-Lingual Transfer for German Token-Level Reference-Free Hallucination Detection
par: Herrlein, Janek, et autres
Publié: (2024)

Modular Sentence Encoders: Separating Language Specialization from Cross-Lingual Alignment
par: Huang, Yongxin, et autres
Publié: (2024)

Self-Distillation for Model Stacking Unlocks Cross-Lingual NLU in 200+ Languages
par: Schmidt, Fabian David, et autres
Publié: (2024)

SpeechTaxi: On Multilingual Semantic Speech Classification
par: Keller, Lennart, et autres
Publié: (2024)

Cross-Lingual Transfer Learning for Speech Translation
par: Ma, Rao, et autres
Publié: (2024)

Cross-Lingual Word Alignment for ASEAN Languages with Contrastive Learning
par: Zhang, Jingshen, et autres
Publié: (2024)

African or European Swallow? Benchmarking Large Vision-Language Models for Fine-Grained Object Classification
par: Geigle, Gregor, et autres
Publié: (2024)

Why Better Cross-Lingual Alignment Fails for Better Cross-Lingual Transfer: Case of Encoders
par: Veitsman, Yana, et autres
Publié: (2026)

Translate, then Detect: Leveraging Machine Translation for Cross-Lingual Toxicity Classification
par: Bell, Samuel J., et autres
Publié: (2025)

Parallel Tokenizers: Rethinking Vocabulary Design for Cross-Lingual Transfer
par: Kautsar, Muhammad Dehan Al, et autres
Publié: (2025)

The Curious Case of Factual (Mis)Alignment between LLMs' Short- and Long-Form Answers
par: Islam, Saad Obaid ul, et autres
Publié: (2025)

ReCoVeR the Target Language: Language Steering without Sacrificing Task Performance
par: Sterz, Hannah, et autres
Publié: (2025)

A Systematic Analysis of Subwords and Cross-Lingual Transfer in Multilingual Translation
par: Meyer, Francois, et autres
Publié: (2024)

Leveraging Open Information Extraction for More Robust Domain Transfer of Event Trigger Detection
par: Dukić, David, et autres
Publié: (2023)

MVL-SIB: A Massively Multilingual Vision-Language Benchmark for Cross-Modal Topical Matching
par: Schmidt, Fabian David, et autres
Publié: (2025)

Supervised In-Context Fine-Tuning for Generative Sequence Labeling
par: Dukić, David, et autres
Publié: (2025)

IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators
par: Paul, Indraneil, et autres
Publié: (2024)

mOthello: When Do Cross-Lingual Representation Alignment and Cross-Lingual Transfer Emerge in Multilingual Models?
par: Hua, Tianze, et autres
Publié: (2024)

Quantifying Cross-Lingual Transfer in Paralinguistic Speech Tasks
par: Buitrago, Pol, et autres
Publié: (2026)

Cross-Lingual Transfer for Natural Language Inference via Multilingual Prompt Translator
par: Qiu, Xiaoyu, et autres
Publié: (2024)

Compositional Steering of Large Language Models with Steering Tokens
par: Radevski, Gorjan, et autres
Publié: (2026)

POTSA: A Cross-Lingual Speech Alignment Framework for Speech-to-Text Translation
par: Li, Xuanchen, et autres
Publié: (2025)

PreAlign: Boosting Cross-Lingual Transfer by Early Establishment of Multilingual Alignment
par: Li, Jiahuan, et autres
Publié: (2024)

ToPro: Token-Level Prompt Decomposition for Cross-Lingual Sequence Labeling Tasks
par: Ma, Bolei, et autres
Publié: (2024)

Evaluating the Ability of LLMs to Solve Semantics-Aware Process Mining Tasks
par: Rebmann, Adrian, et autres
Publié: (2024)

Babel-ImageNet: Massively Multilingual Evaluation of Vision-and-Language Representations
par: Geigle, Gregor, et autres
Publié: (2023)

Does Object Grounding Really Reduce Hallucination of Large Vision-Language Models?
par: Geigle, Gregor, et autres
Publié: (2024)

Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment
par: Wu, Zhaofeng, et autres
Publié: (2024)

Lost in Translation? A Comparative Study on the Cross-Lingual Transfer of Composite Harms
par: Shukla, Vaibhav, et autres
Publié: (2026)

Middle-Layer Representation Alignment for Cross-Lingual Transfer in Fine-Tuned LLMs
par: Liu, Danni, et autres
Publié: (2025)

Understanding Cross-Lingual Alignment -- A Survey
par: Hämmerl, Katharina, et autres
Publié: (2024)

Analyzing the Effect of Linguistic Similarity on Cross-Lingual Transfer: Tasks and Experimental Setups Matter
par: Blaschke, Verena, et autres
Publié: (2025)

Is Cross-Lingual Transfer in Bilingual Models Human-Like? A Study with Overlapping Word Forms in Dutch and English
par: Škrjanec, Iza, et autres
Publié: (2026)

The Devil is in the EOS: Sequence Training for Detailed Image Captioning
par: Mohamed, Abdelrahman, et autres
Publié: (2025)

Improved Cross-Lingual Transfer Learning For Automatic Speech Translation
par: Khurana, Sameer, et autres
Publié: (2023)

SQATIN: Supervised Instruction Tuning Meets Question Answering for Improved Dialogue NLU
par: Razumovskaia, Evgeniia, et autres
Publié: (2023)

Self-Translate-Train: Enhancing Cross-Lingual Transfer of Large Language Models via Inherent Capability
par: Ri, Ryokan, et autres
Publié: (2024)