Copertina

TransAlign: Machine Translation Encoders are Strong Word Aligners, Too

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ebing, Benedikt, Goldschmied, Christian, Glavaš, Goran
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

The Devil Is in the Word Alignment Details: On Translation-Based Cross-Lingual Transfer for Token Classification Tasks
di: Ebing, Benedikt, et al.
Pubblicazione: (2025)

To Translate or Not to Translate: A Systematic Investigation of Translation-Based Cross-Lingual Transfer to Low-Resource Languages
di: Ebing, Benedikt, et al.
Pubblicazione: (2023)

One Script Instead of Hundreds? On Pretraining Romanized Encoder Language Models
di: Ebing, Benedikt, et al.
Pubblicazione: (2026)

Modular Sentence Encoders: Separating Language Specialization from Cross-Lingual Alignment
di: Huang, Yongxin, et al.
Pubblicazione: (2024)

SpeechTaxi: On Multilingual Semantic Speech Classification
di: Keller, Lennart, et al.
Pubblicazione: (2024)

OTTAWA: Optimal TransporT Adaptive Word Aligner for Hallucination and Omission Translation Errors Detection
di: Huang, Chenyang, et al.
Pubblicazione: (2024)

Supervised In-Context Fine-Tuning for Generative Sequence Labeling
di: Dukić, David, et al.
Pubblicazione: (2025)

IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators
di: Paul, Indraneil, et al.
Pubblicazione: (2024)

Babel-ImageNet: Massively Multilingual Evaluation of Vision-and-Language Representations
di: Geigle, Gregor, et al.
Pubblicazione: (2023)

Does Object Grounding Really Reduce Hallucination of Large Vision-Language Models?
di: Geigle, Gregor, et al.
Pubblicazione: (2024)

African or European Swallow? Benchmarking Large Vision-Language Models for Fine-Grained Object Classification
di: Geigle, Gregor, et al.
Pubblicazione: (2024)

ANHALTEN: Cross-Lingual Transfer for German Token-Level Reference-Free Hallucination Detection
di: Herrlein, Janek, et al.
Pubblicazione: (2024)

Whisper Has an Internal Word Aligner
di: Yeh, Sung-Lin, et al.
Pubblicazione: (2025)

SQATIN: Supervised Instruction Tuning Meets Question Answering for Improved Dialogue NLU
di: Razumovskaia, Evgeniia, et al.
Pubblicazione: (2023)

Paraphrase-Aligned Machine Translation
di: Chang, Ke-Ching, et al.
Pubblicazione: (2024)

MVL-SIB: A Massively Multilingual Vision-Language Benchmark for Cross-Modal Topical Matching
di: Schmidt, Fabian David, et al.
Pubblicazione: (2025)

ReCoVeR the Target Language: Language Steering without Sacrificing Task Performance
di: Sterz, Hannah, et al.
Pubblicazione: (2025)

Self-Distillation for Model Stacking Unlocks Cross-Lingual NLU in 200+ Languages
di: Schmidt, Fabian David, et al.
Pubblicazione: (2024)

mBLIP: Efficient Bootstrapping of Multilingual Vision-LLMs
di: Geigle, Gregor, et al.
Pubblicazione: (2023)

The Curious Case of Factual (Mis)Alignment between LLMs' Short- and Long-Form Answers
di: Islam, Saad Obaid ul, et al.
Pubblicazione: (2025)

How Much Do LLMs Hallucinate across Languages? On Realistic Multilingual Estimation of LLM Hallucination
di: Islam, Saad Obaid ul, et al.
Pubblicazione: (2025)

Leveraging Open Information Extraction for More Robust Domain Transfer of Event Trigger Detection
di: Dukić, David, et al.
Pubblicazione: (2023)

Don't Stop the Multi-Party! On Generating Synthetic Written Multi-Party Conversations with Constraints
di: Penzo, Nicolò, et al.
Pubblicazione: (2025)

Heterogeneous Encoders Scaling In The Transformer For Neural Machine Translation
di: Hu, Jia Cheng, et al.
Pubblicazione: (2023)

Word Alignment as Preference for Machine Translation
di: Wu, Qiyu, et al.
Pubblicazione: (2024)

Reward-Shifted Speculative Sampling Is An Efficient Test-Time Weak-to-Strong Aligner
di: Li, Bolian, et al.
Pubblicazione: (2025)

Evaluating the Ability of LLMs to Solve Semantics-Aware Process Mining Tasks
di: Rebmann, Adrian, et al.
Pubblicazione: (2024)

Geographic Adaptation of Pretrained Language Models
di: Hofmann, Valentin, et al.
Pubblicazione: (2022)

Transformer-Encoder Trees for Efficient Multilingual Machine Translation and Speech Translation
di: Guan, Yiwen, et al.
Pubblicazione: (2025)

Fleurs-SLU: A Massively Multilingual Benchmark for Spoken Language Understanding
di: Schmidt, Fabian David, et al.
Pubblicazione: (2025)

TransBench: Benchmarking Machine Translation for Industrial-Scale Applications
di: Li, Haijun, et al.
Pubblicazione: (2025)

Knowledge Distillation vs. Pretraining from Scratch under a Fixed (Computation) Budget
di: Bui, Minh Duc, et al.
Pubblicazione: (2024)

ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding
di: Paul, Indraneil, et al.
Pubblicazione: (2025)

Compositional Steering of Large Language Models with Steering Tokens
di: Radevski, Gorjan, et al.
Pubblicazione: (2026)

Large Language Models are Miscalibrated In-Context Learners
di: Li, Chengzu, et al.
Pubblicazione: (2023)

Quantity vs. Quality of Monolingual Source Data in Automatic Text Translation: Can It Be Too Little If It Is Too Good?
di: Abdulmumin, Idris, et al.
Pubblicazione: (2024)

CANTONMT: Investigating Back-Translation and Model-Switch Mechanisms for Cantonese-English Neural Machine Translation
di: Hong, Kung Yin, et al.
Pubblicazione: (2024)

NiuTrans.LMT: Toward Inclusive and Scalable Multilingual Machine Translation with LLMs
di: Luo, Yingfeng, et al.
Pubblicazione: (2025)

ArcAligner: Adaptive Recursive Aligner for Compressed Context Embeddings in RAG
di: Li, Jianbo, et al.
Pubblicazione: (2026)

Beyond Decoder-only: Large Language Models Can be Good Encoders for Machine Translation
di: Luo, Yingfeng, et al.
Pubblicazione: (2025)