VLSP 2025 Shared Task: A Seq2Seq Transformer Approach to Vietnamese Semantic Parsing

Improving Latvian Morphosyntactic Parsing with Pretrained Encoders and Analyzer-Constrained Decoding

SEAS: Sentence Extraction and Alignment from Subtitles

This submission includes a curated corpus of gold-standard alignments for English-Spanish and English-German subtitles, along with their corresponding subtitle files, a novel annotation tool, and the full code to reproduce the method.

RETUYT-InCo at MSLG-SPA 2026: Improving NLLB Fine-tuning with Synthetic Data for Mexican Sign Language Glosses

VietTayNMT: Directional LoRA for Low-Resource Vietnamese–Tay Neural Machine Translation

Low-resource machine translation for minority languages is hindered by limited parallel data, weak lexical coverage, and deployment constraints. This paper studies Vietnamese–Tay translation and introduces VietTayNMT, a lightweight bidirectional framework designed for both translation quality and edge-oriented efficien...

PlurVA-LLM-2026 Shared Task Track-1: Pluralistic Value Alignment in LLMs via Multilingual Fine-Tuning and Threshold Calibration

This approach combines option-permutation augmentation for Chinese data, annotator vote expansion for Indonesian data, and binary reformulation with SinhalaMMLU augmentation with SinhalaMMLU augmentation for Sri Lankan data to focus on pluralistic value alignment in the contexts of China, Indonesia, and Sri Lanka.

Improving Cross-Lingual Token Representations by Adding a Pinch of SALT

Cross-lingual sentence encoders enable scalable transfer across hundreds of languages, powering applications such as translation mining and zero-shot learning in low-resource settings. Although trained for sentence-level alignment, they are increasingly also applied to token-level tasks such as hallucination detection...