Is Reinforcement Learning (Not) for Natural Language Processing?: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization [PDF]
arXiv.org, 2022 We tackle the problem of aligning pre-trained large language models (LMs) with human preferences. If we view text generation as a sequential decision-making problem, reinforcement learning (RL) appears to be a natural conceptual framework. However, using
Rajkumar Ramamurthy +7 more
semanticscholar +1 more source
A Scoping Literature Review of Natural Language Processing Application to Safety Occurrence Reports
Safety, 2023 Safety occurrence reports can contain valuable information on how incidents occur, revealing knowledge that can assist safety practitioners. This paper presents and discusses a literature review exploring how Natural Language Processing (NLP) has been ...
John W. Ricketts +3 more
semanticscholar +1 more source
Integrating Manual and Automatic Annotation for the Creation of Discourse Network Data Sets
Politics and Governance, 2020 This article investigates the integration of machine learning in the political claim annotation workflow with the goal to partially automate the annotation and analysis of large text corpora.
Sebastian Haunss +6 more
doaj +1 more source
Enhancing Semantic Code Search With Deep Graph Matching
IEEE Access, 2023 The job of discovering appropriate code snippets against a natural language query is an important task for software developers. Appropriate code retrieval increases software productivity and quality as well.
Nazia Bibi +5 more
doaj +1 more source
Exploiting Cloze-Questions for Few-Shot Text Classification and Natural Language Inference [PDF]
Conference of the European Chapter of the Association for Computational Linguistics, 2020 Some NLP tasks can be solved in a fully unsupervised fashion by providing a pretrained language model with “task descriptions” in natural language (e.g., Radford et al., 2019). While this approach underperforms its supervised counterpart, we show in this
Timo Schick, Hinrich Schütze
semanticscholar +1 more source
Making Sense of Language Signals for Monitoring Radicalization
Applied Sciences, 2022 Understanding radicalization pathways, drivers, and factors is essential for the effective design of prevention and counter-radicalization programs. Traditionally, the primary methods used by social scientists to detect these drivers and factors include ...
Óscar Araque +7 more
doaj +1 more source
ID2SBVR: A Method for Extracting Business Vocabulary and Rules from an Informal Document
Big Data and Cognitive Computing, 2022 Semantics of Business Vocabulary and Rules (SBVR) is a standard that is applied in describing business knowledge in the form of controlled natural language.
Irene Tangkawarow +2 more
doaj +1 more source
Cross-Task Generalization via Natural Language Crowdsourcing Instructions [PDF]
Annual Meeting of the Association for Computational Linguistics, 2021 Humans (e.g., crowdworkers) have a remarkable ability in solving different tasks, by simply reading textual instructions that define them and looking at a few examples.
Swaroop Mishra +3 more
semanticscholar +1 more source
Research on Technology of Generating Multi-table SQL Query Statement by Natural Language
Jisuanji kexue yu tansuo, 2020 SQL (structured query language) query generation from natural language is not only one of the most important parts of constructing intelligent database query system, but also one of the difficulties in the individualized operation and maintenance of ...
CAO Jinchao, HUANG Tao, CHEN Gang, WU Xiaofan, CHEN Ke
doaj +1 more source
Recent Advances in Natural Language Processing via Large Pre-trained Language Models: A Survey [PDF]
ACM Computing Surveys, 2021 Large, pre-trained language models (PLMs) such as BERT and GPT have drastically changed the Natural Language Processing (NLP) field. For numerous NLP tasks, approaches leveraging PLMs have achieved state-of-the-art performance. The key idea is to learn a
Bonan Min +8 more
semanticscholar +1 more source