paper-with-me

홈 › Papers

Simulated Multiple Reference Training Improves Low-Resource Machine Translation

2020-04-30 · EMNLP 2020 11 · Huda Khayrallah, Brian Thompson, Matt Post, Philipp Koehn

Many valid translations exist for a given sentence, yet machine translation (MT) is trained with a single reference translation, exacerbating data sparsity in low-resource settings. We introduce Simulated Multiple Reference Training (SMRT), a novel MT training method that approximates the full space of possible translations by sampling a paraphrase of the reference sentence from a paraphraser and training the MT model to predict the paraphraser's distribution over possible tokens. We demonstrate the effectiveness of SMRT in low-resource settings when translating to English, with improvements of 1.2 to 7.0 BLEU. We also find SMRT is complementary to back-translation.

📄 PDF Abstract BibTeX arXiv:2004.14524

Code (1)

thompsonb/fairseq-smrt pytorch

Tasks

Machine TranslationSentenceTranslationvalid

Similar Papers 제목 키워드 기반

SMRT Chatbots: Improving Non-Task-Oriented Dialog with Simulated Multiple Reference Training

2020-11-01 · Findings of the Association for Computational Linguistics 2020 · Huda Khayrallah, João Sedoc

Non-task-oriented dialog models suffer from poor quality and non-diverse responses. To overcome limited conversational data, we apply Simulated Multiple Reference Training (SMRT; Khayrallah et al., 2020), and use a parap…

Diversity

Preference Packing: Efficient Preference Optimization for Large Language Models

2026-02-27 · Jaekyung Cho arxiv

Resource-efficient training optimization techniques are becoming increasingly important as the size of large language models (LLMs) continues to grow. In particular, batch packing is commonly used in pre-training and sup…

Improving Low-resource RRG Parsing with Cross-lingual Self-training

2022-10-01 · COLING 2022 10 · Kilian Evang, Laura Kallmeyer, Jakub Waszczuk, Kilu von Prince 외

This paper considers the task of parsing low-resource languages in a scenario where parallel English data and also a limited seed of annotated sentences in the target language are available, as for example in bootstrappi…

Constituency Parsing

Freeform Preference Learning for Robotic Manipulation

2026-06-30 · Marcel Torne, Anubha Mahajan, Abhijnya Bhat, Chelsea Finn arxiv

Reward design remains a central bottleneck for autonomous robot policy improvement, especially in long-horizon manipulation tasks where sparse success labels provide too little signal and binary preferences collapse many…

Causal-Aware Foundation-Model for Bilevel Optimization in Discrete Choice Settings

2026-05-07 · Shivaram Subramanian, Zhengliang Xue, Markus Ettl, Yingdong Lu 외 arxiv

We introduce a causal aware foundation-model framework for real time optimal decision making in discrete choice environments. We propose a constrained triple-head price optimization (C3PO) network to solve a bilevel deci…

Bilevel OptimizationMulti-Task LearningDecision Making