paper-with-me

Papers

Differentiable Scheduled Sampling for Credit Assignment

2017-04-23 · ACL 2017 7 · Kartik Goyal, Chris Dyer, Taylor Berg-Kirkpatrick

We demonstrate that a continuous relaxation of the argmax operation can be used to create a differentiable approximation to greedy decoding for sequence-to-sequence (seq2seq) models. By incorporating this approximation into the scheduled sampling training procedure (Bengio et al., 2015)--a well-known technique for correcting exposure bias--we introduce a new training objective that is continuous and differentiable everywhere and that can provide informative gradients near points where previous decoding decisions change their value. In addition, by using a related approximation, we demonstrate a similar approach to sampled-based training. Finally, we show that our approach outperforms cross-entropy training and scheduled sampling procedures in two sequence prediction tasks: named entity recognition and machine translation.

📄 PDF Abstract BibTeX arXiv:1704.06970

Code (0)

등록된 구현이 없습니다.

Tasks

Machine Translationnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)Translation

Similar Papers 제목 키워드 기반

Differentiable Sampling with Flexible Reference Word Order for Neural Machine Translation

2019-04-04 · NAACL 2019 6 · Weijia Xu, Xing Niu, Marine Carpuat

Despite some empirical success at correcting exposure bias in machine translation, scheduled sampling algorithms suffer from a major drawback: they incorrectly assume that words in the reference translations and in sampl…

Machine TranslationTranslation

A Review of Neuroscience-Inspired Machine Learning

2024-02-16 · Alexander Ororbia, Ankur Mali, Adam Kohan, Beren Millidge 외

One major criticism of deep learning centers around the biological implausibility of the credit assignment schema used for learning -- backpropagation of errors. This implausibility translates into practical limitations,…

Credit Assignment with Resets in Language Model Reasoning

2026-05-25 · Ankur Samanta, Akshayaa Magesh, Ayush Jain, Youliang Yu 외 arxiv

Contemporary reinforcement learning with verifiable reward methods post-train language models on multi-step reasoning by assigning a single outcome reward uniformly across all tokens in a trajectory. Such uniform assignm…

Reinforcement Learning

Dueling Posterior Sampling for Preference-Based Reinforcement Learning

2019-08-04 · Ellen R. Novoseller, Yibing Wei, Yanan Sui, Yisong Yue 외

In preference-based reinforcement learning (RL), an agent interacts with the environment while receiving preferences instead of absolute feedback. While there is increasing research activity in preference-based RL, the d…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Shapley Counterfactual Credits for Multi-Agent Reinforcement Learning

2021-06-01 · Jiahui Li, Kun Kuang, Baoxiang Wang, Furui Liu 외

Centralized Training with Decentralized Execution (CTDE) has been a popular paradigm in cooperative Multi-Agent Reinforcement Learning (MARL) settings and is widely used in many real applications. One of the major challe…

counterfactualMulti-agent Reinforcement Learningreinforcement-learningReinforcement Learning+3