paper-with-me

Papers

Target Conditioned Sampling: Optimizing Data Selection for Multilingual Neural Machine Translation

2019-05-20 · ACL 2019 7 · Xinyi Wang, Graham Neubig

To improve low-resource Neural Machine Translation (NMT) with multilingual corpora, training on the most related high-resource language only is often more effective than using all data available (Neubig and Hu, 2018). However, it is possible that an intelligent data selection strategy can further improve low-resource NMT with data from other auxiliary languages. In this paper, we seek to construct a sampling distribution over all multilingual data, so that it minimizes the training loss of the low-resource language. Based on this formulation, we propose an efficient algorithm, Target Conditioned Sampling (TCS), which first samples a target sentence, and then conditionally samples its source sentence. Experiments show that TCS brings significant gains of up to 2 BLEU on three of four languages we test, with minimal training overhead.

📄 PDF Abstract BibTeX arXiv:1905.08212

Code (0)

등록된 구현이 없습니다.

Tasks

Low Resource Neural Machine TranslationLow-Resource Neural Machine TranslationLow Resource NMTMachine TranslationNMTSentenceTranslation

Similar Papers 제목 키워드 기반

Optimize Your Sampling: Tuned Diffusion Sampling with Bayesian Optimization

2026-08-18 · Travis Zhang, Christian Belardi, Justin Lovelace, Jin Peng Zhou 외 arxiv

Sampling from a diffusion model typically requires many forward passes through a large neural network, making generation computationally expensive. While much work has focused on efficient solvers and samplers, comparati…

Text-to-Image Generation

Online Learning-based Waveform Selection for Improved Vehicle Recognition in Automotive Radar

2022-12-01 · Charles E. Thornton, William W. Howard, R. Michael Buehrer

This paper describes important considerations and challenges associated with online reinforcement-learning based waveform selection for target identification in frequency modulated continuous wave (FMCW) automotive radar…

reinforcement-learningReinforcement Learning (RL)Thompson Sampling

Meta-Aligner: Bidirectional Preference-Policy Optimization for Multi-Objective LLMs Alignment

2026-04-27 · Wenzhe Xu, Biao Liu, Yiyang Sun, Xin Geng 외 arxiv

Multi-Objective Alignment aims to align Large Language Models (LLMs) with diverse and often conflicting human values by optimizing multiple objectives simultaneously. Existing methods predominantly rely on static prefere…

Response Generation

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding

2026-08-06 · Bo Zhang, Wenxin Wang, Feng Chen, Zhihao Zhang 외 arxiv

Recent advancements in MLLM-based long-form video understanding have mitigated inference-time computational cost and limited context lengths by selecting query-relevant frames. However, existing approaches predominantly …

Global Resolution: Optimal Multi-Draft Speculative Sampling via Convex Minimization

2025-11-19 · Rahul Krishna Thomas, Arka Pal arxiv

Speculative sampling reduces the latency of autoregressive decoding for target model LLMs without sacrificing inference quality, by using a cheap draft model to suggest a candidate token and a verification criterion to a…