English
Related papers

Related papers: Training with Exploration Improves a Greedy Stack-…

200 papers

This paper introduces a greedy parser based on neural networks, which leverages a new compositional sub-tree representation. The greedy parser and the compositional procedure are jointly trained, and tightly depends on each-other. The…

Machine Learning · Computer Science 2015-04-14 Joël Legrand , Ronan Collobert

Greedy algorithms for NLP such as transition based parsing are prone to error propagation. One way to overcome this problem is to allow the algorithm to backtrack and explore an alternative solution in cases where new evidence contradicts…

Computation and Language · Computer Science 2022-06-29 Franck Dary , Maxime Petit , Alexis Nasr

Exploration is a difficult challenge in reinforcement learning and even recent state-of-the art curiosity-based methods rely on the simple epsilon-greedy strategy to generate novelty. We argue that pure random walks do not succeed to…

Machine Learning · Computer Science 2018-07-06 Fabio Pardo , Vitaly Levdik , Petar Kormushev

Online learning algorithms, widely used to power search and content optimization on the web, must balance exploration and exploitation, potentially sacrificing the experience of current users in order to gain information that will lead to…

Machine Learning · Computer Science 2021-12-28 Manish Raghavan , Aleksandrs Slivkins , Jennifer Wortman Vaughan , Zhiwei Steven Wu

Applying the theory of compressive sensing in practice always takes different kinds of perturbations into consideration. In this paper, the recovery performance of greedy pursuits with replacement for sparse recovery is analyzed when both…

Information Theory · Computer Science 2015-06-04 Laming Chen , Yuantao Gu

Prior work has shown that structural supervision helps English language models learn generalizations about syntactic phenomena such as subject-verb agreement. However, it remains unclear if such an inductive bias would also improve language…

Computation and Language · Computer Science 2021-09-24 Yiwen Wang , Jennifer Hu , Roger Levy , Peng Qian

The question of how to explore, i.e., take actions with uncertain outcomes to learn about possible future rewards, is a key question in reinforcement learning (RL). Here, we show a surprising result: We show that Q-learning with nonlinear…

Machine Learning · Computer Science 2018-05-31 Justas Dauparas , Ryota Tomioka , Katja Hofmann

Recent methods based on pre-trained language models have exhibited superior performance over tabular tasks (e.g., tabular NLI), despite showing inherent problems such as not using the right evidence and inconsistent predictions across…

Computation and Language · Computer Science 2022-10-25 Abhilash Reddy Shankarampeta , Vivek Gupta , Shuo Zhang

Recent advances in conditional recurrent language modelling have mainly focused on network architectures (e.g., attention mechanism), learning algorithms (e.g., scheduled sampling and sequence-level training) and novel applications (e.g.,…

Computation and Language · Computer Science 2016-05-13 Kyunghyun Cho

Recent advancements in agentic test-time scaling allow models to gather environmental feedback before committing to final actions. A key limitation of existing methods is that they typically employ undifferentiated exploration strategies,…

Artificial Intelligence · Computer Science 2026-05-13 Xingyuan Hua , Sheng Yue , Ju Ren

The Exploration-Exploitation tradeoff arises in Reinforcement Learning when one cannot tell if a policy is optimal. Then, there is a constant need to explore new actions instead of exploiting past experience. In practice, it is common to…

Machine Learning · Computer Science 2019-09-10 Lior Shani , Yonathan Efroni , Shie Mannor

Test-time data augmentation$-$averaging the predictions of a machine learning model across multiple augmented samples of data$-$is a widely used technique that improves the predictive performance. While many advanced learnable data…

Machine Learning · Statistics 2020-06-23 Dmitry Molchanov , Alexander Lyzhov , Yuliya Molchanova , Arsenii Ashukha , Dmitry Vetrov

Fine-tuned language models use greedy decoding to answer reading comprehension questions with relative success. However, this approach does not ensure that the answer is a span in the given passage, nor does it guarantee that it is the most…

Computation and Language · Computer Science 2022-11-09 Or Castel , Ori Ram , Avia Efrat , Omer Levy

We present evidence of substantial benefit from efficient exploration in gathering human feedback to improve large language models. In our experiments, an agent sequentially generates queries while fitting a reward model to the feedback…

Machine Learning · Computer Science 2024-06-06 Vikranth Dwaracherla , Seyed Mohammad Asghari , Botao Hao , Benjamin Van Roy

In this work we propose a new deep learning tool called deep dictionary learning. Multi-level dictionaries are learnt in a greedy fashion, one layer at a time. This requires solving a simple (shallow) dictionary learning problem, the…

Machine Learning · Computer Science 2016-02-02 Snigdha Tariyal , Angshul Majumdar , Richa Singh , Mayank Vatsa

Recent advancements have shown that reinforcement learning (RL) can substantially improve the reasoning abilities of large language models (LLMs). The effectiveness of such RL training, however, depends critically on the exploration space…

Computation and Language · Computer Science 2026-03-17 Haoyuan Wu , Hai Wang , Jiajia Wu , Jinxiang Ou , Keyao Wang , Weile Chen , Zihao Zheng , Bei Yu

Efficient exploration remains a challenging research problem in reinforcement learning, especially when an environment contains large state spaces, deceptive local optima, or sparse rewards. To tackle this problem, we present a…

Artificial Intelligence · Computer Science 2018-10-30 Zhang-Wei Hong , Tzu-Yun Shann , Shih-Yang Su , Yi-Hsiang Chang , Chun-Yi Lee

A wide variety of neural-network architectures have been proposed for the task of Chinese word segmentation. Surprisingly, we find that a bidirectional LSTM model, when combined with standard deep learning techniques and best practices, can…

Computation and Language · Computer Science 2018-08-27 Ji Ma , Kuzman Ganchev , David Weiss

We present a simple and effective scheme for dependency parsing which is based on bidirectional-LSTMs (BiLSTMs). Each sentence token is associated with a BiLSTM vector representing the token in its sentential context, and feature vectors…

Computation and Language · Computer Science 2016-07-21 Eliyahu Kiperwasser , Yoav Goldberg

Many tasks within NLP can be framed as sequential decision problems, ranging from sequence tagging to text generation. However, for many tasks, the standard training methods, including maximum likelihood (teacher forcing) and scheduled…

Computation and Language · Computer Science 2024-06-14 Jianing Yang , Harshine Visvanathan , Yilin Wang , Xinyi Hu , Matthew Gormley