Learning Open Domain Multi-hop Search Using Reinforcement Learning
- URL: http://arxiv.org/abs/2205.15281v1
- Date: Mon, 30 May 2022 17:44:19 GMT
- Title: Learning Open Domain Multi-hop Search Using Reinforcement Learning
- Authors: Enrique Noriega-Atala, Mihai Surdeanu, Clayton T. Morrison
- Abstract summary: We teach an automated agent to learn how to search for multi-hop paths of relations between entities in an open domain.
We implement the method in an actor-critic reinforcement learning algorithm and evaluate it on a dataset of search problems derived from a subset of English Wikipedia.
- Score: 20.078330789576256
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We propose a method to teach an automated agent to learn how to search for
multi-hop paths of relations between entities in an open domain. The method
learns a policy for directing existing information retrieval and machine
reading resources to focus on relevant regions of a corpus. The approach
formulates the learning problem as a Markov decision process with a state
representation that encodes the dynamics of the search process and a reward
structure that minimizes the number of documents that must be processed while
still finding multi-hop paths. We implement the method in an actor-critic
reinforcement learning algorithm and evaluate it on a dataset of search
problems derived from a subset of English Wikipedia. The algorithm finds a
family of policies that succeeds in extracting the desired information while
processing fewer documents compared to several baseline heuristic algorithms.
Related papers
- Query-oriented Data Augmentation for Session Search [71.84678750612754]
We propose query-oriented data augmentation to enrich search logs and empower the modeling.
We generate supplemental training pairs by altering the most important part of a search context.
We develop several strategies to alter the current query, resulting in new training data with varying degrees of difficulty.
arXiv Detail & Related papers (2024-07-04T08:08:33Z) - Relation-aware Ensemble Learning for Knowledge Graph Embedding [68.94900786314666]
We propose to learn an ensemble by leveraging existing methods in a relation-aware manner.
exploring these semantics using relation-aware ensemble leads to a much larger search space than general ensemble methods.
We propose a divide-search-combine algorithm RelEns-DSC that searches the relation-wise ensemble weights independently.
arXiv Detail & Related papers (2023-10-13T07:40:12Z) - Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models [17.059322033670124]
We propose a novel strategy that propels Large Language Models through algorithmic reasoning pathways.
Our results suggest that instructing an LLM using an algorithm can lead to performance surpassing that of the algorithm itself.
arXiv Detail & Related papers (2023-08-20T22:36:23Z) - Unified Functional Hashing in Automatic Machine Learning [58.77232199682271]
We show that large efficiency gains can be obtained by employing a fast unified functional hash.
Our hash is "functional" in that it identifies equivalent candidates even if they were represented or coded differently.
We show dramatic improvements on multiple AutoML domains, including neural architecture search and algorithm discovery.
arXiv Detail & Related papers (2023-02-10T18:50:37Z) - Fast Line Search for Multi-Task Learning [0.0]
We propose a novel idea for line search algorithms in multi-task learning.
The idea is to use latent representation space instead of parameter space for finding step size.
We compare this idea with classical backtracking and gradient methods with a constant learning rate on MNIST, CIFAR-10, Cityscapes tasks.
arXiv Detail & Related papers (2021-10-02T21:02:29Z) - Meta Navigator: Search for a Good Adaptation Policy for Few-shot
Learning [113.05118113697111]
Few-shot learning aims to adapt knowledge learned from previous tasks to novel tasks with only a limited amount of labeled data.
Research literature on few-shot learning exhibits great diversity, while different algorithms often excel at different few-shot learning scenarios.
We present Meta Navigator, a framework that attempts to solve the limitation in few-shot learning by seeking a higher-level strategy.
arXiv Detail & Related papers (2021-09-13T07:20:01Z) - Memory Augmented Sequential Paragraph Retrieval for Multi-hop Question
Answering [32.69969157825044]
We propose a new architecture that models paragraphs as sequential data and considers multi-hop information retrieval as a kind of sequence labeling task.
We evaluate our method on both full wiki and distractor subtask of HotpotQA, a public textual multi-hop QA dataset.
arXiv Detail & Related papers (2021-02-07T08:15:51Z) - Information Theoretic Meta Learning with Gaussian Processes [74.54485310507336]
We formulate meta learning using information theoretic concepts; namely, mutual information and the information bottleneck.
By making use of variational approximations to the mutual information, we derive a general and tractable framework for meta learning.
arXiv Detail & Related papers (2020-09-07T16:47:30Z) - Discovering Reinforcement Learning Algorithms [53.72358280495428]
Reinforcement learning algorithms update an agent's parameters according to one of several possible rules.
This paper introduces a new meta-learning approach that discovers an entire update rule.
It includes both 'what to predict' (e.g. value functions) and 'how to learn from it' by interacting with a set of environments.
arXiv Detail & Related papers (2020-07-17T07:38:39Z) - Text Detection on Roughly Placed Books by Leveraging a Learning-based
Model Trained with Another Domain Data [0.30458514384586394]
In this paper, we focus on how to generate bounding boxes that are appropriate to grasp text areas on books.
We develop algorithms that construct the bounding boxes by improving and leveraging the results of a learning-based method.
Our algorithms can utilize different learning-based approaches to detect scene texts.
arXiv Detail & Related papers (2020-06-26T05:53:23Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.