A Survey of Reinforcement Learning Informed by Natural Language

Luketina, Jelena; Nardelli, Nantas; Farquhar, Gregory; Foerster, Jakob; Andreas, Jacob; Grefenstette, Edward; Whiteson, Shimon; Rocktäschel, Tim

doi:10.24963/ijcai.2019/880

Cited by 123 publications

(103 citation statements)

References 6 publications

Supporting

Mentioning

100

Contrasting

Order By: Relevance

“…How does their performance without fine-tuning compare to symbolic knowledge bases automatically extracted from text? Beyond gathering a better general understanding of these models, we believe that answers to these questions can help us design better unsupervised knowledge representations that could transfer factual and commonsense knowledge reliably to downstream tasks such as commonsense (visual) question answering (Zellers et al, 2018;Talmor et al, 2019) or reinforcement learning (Branavan et al, 2011;Chevalier-Boisvert et al, 2018;Bahdanau et al, 2019;Luketina et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

Language Models as Knowledge Bases?

Petroni

Rocktäschel

Lewis

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

Self Cite

1,057

1,068

View full text Add to dashboard Cite

Recent progress in pretraining language models on large textual corpora led to a surge of improvements for downstream NLP tasks. Whilst learning linguistic knowledge, these models may also be storing relational knowledge present in the training data, and may be able to answer queries structured as "fillin-the-blank" cloze statements. Language models have many advantages over structured knowledge bases: they require no schema engineering, allow practitioners to query about an open class of relations, are easy to extend to more data, and require no human supervision to train. We present an in-depth analysis of the relational knowledge already present (without fine-tuning) in a wide range of state-of-theart pretrained language models. We find that (i) without fine-tuning, BERT contains relational knowledge competitive with traditional NLP methods that have some access to oracle knowledge, (ii) BERT also does remarkably well on open-domain question answering against a supervised baseline, and (iii) certain types of factual knowledge are learned much more readily than others by standard language model pretraining approaches. The surprisingly strong ability of these models to recall factual knowledge without any fine-tuning demonstrates their potential as unsupervised open-domain QA systems. The code to reproduce our analysis is available at https: //github.com/facebookresearch/LAMA.

show abstract

Section: Introductionmentioning

confidence: 99%

Language Models as Knowledge Bases?

Petroni

Rocktäschel

Lewis

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

Self Cite

1,057

1,068

View full text Add to dashboard Cite

show abstract

“…The literature related to applications of RL in NLP maybe divided into language-assisted RL and language conditional RL [248]. In the former case, the language is used to aid learning while the interaction with the specific language in later case, is initiated by the task formulation at hand itself.…”

Section: Natural Language Processingmentioning

confidence: 99%

A Gentle Introduction to Reinforcement Learning and its Application in Different Fields

Naeem

Rizvi

Coronato³

2020

IEEE Access

103

View full text Add to dashboard Cite

Due to the recent progress in Deep Neural Networks, Reinforcement Learning (RL) has become one of the most important and useful technology. It is a learning method where a software agent interacts with an unknown environment, selects actions, and progressively discovers the environment dynamics. RL has been effectively applied in many important areas of real life. This article intends to provide an in-depth introduction of the Markov Decision Process, RL and its algorithms. Moreover, we present a literature review of the application of RL to a variety of fields, including robotics and autonomous control, communication and networking, natural language processing, games and self-organized system, scheduling management and configuration of resources, and computer vision.

show abstract

“…This paper proposes a system architecture and a roadmap towards implementing the vision outlined here, suggesting preliminary directions for future work (learned world models, incorporating interaction into datasets). We believe that this framework will facilitate consolidation with multiple related lines of research across the different communities, particularly embodied AI and NLU (Luketina et al, 2019).…”

Section: C1 C2mentioning

confidence: 99%

Language (Re)modelling: Towards Embodied Language Understanding

Tamari

Shani

Hope

et al. 2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

While natural language understanding (NLU) is advancing rapidly, today's technology differs from human-like language understanding in fundamental ways, notably in its inferior efficiency, interpretability, and generalization. This work proposes an approach to representation and learning based on the tenets of embodied cognitive linguistics (ECL). According to ECL, natural language is inherently executable (like programming languages), driven by mental simulation and metaphoric mappings over hierarchical compositions of structures and schemata learned through embodied interaction. This position paper argues that the use of grounding by metaphoric inference and simulation will greatly benefit NLU systems, and proposes a system architecture along with a roadmap towards realizing this vision.

show abstract

A Survey of Reinforcement Learning Informed by Natural Language

Cited by 123 publications

References 6 publications

Language Models as Knowledge Bases?

Language Models as Knowledge Bases?

A Gentle Introduction to Reinforcement Learning and its Application in Different Fields

Language (Re)modelling: Towards Embodied Language Understanding

Contact Info

Product

Resources

About