Results 71 to 80 of about 2,197,203 (280)

Organic Materials of Tomorrow: Horizons of Artificial Intelligence

Advanced Materials, EarlyView.
This review examines machine learning techniques accelerating the discovery of organic semiconductors by linking molecular structure to properties. Key methods include graph neural networks, generative models, and active learning. Applications to organic photovoltaics demonstrate practical impact.
Harold Mena, J. Terence Blaskovits, Kun‐Han Lin, Denis Andrienko   +3 more
wiley   +1 more source

GPT-3.5 for Grammatical Error Correction

Proceedings of the Language Resources and Evaluation Conference
This paper investigates the application of GPT-3.5 for Grammatical Error Correction (GEC) in multiple languages in several settings: zero-shot GEC, fine-tuning for GEC, and using GPT-3.5 to re-rank correction hypotheses generated by other GEC models. In the zero-shot setting, we conduct automatic evaluations of the corrections proposed by GPT-3.5 using
Katinskaia Anisia, Yangarber Roman
openaire   +5 more sources

Neural Quality Estimation of Grammatical Error Correction [PDF]

Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 2018
Grammatical error correction (GEC) systems deployed in language learning environments are expected to accurately correct errors in learners’ writing. However, in practice, they often produce spurious corrections and fail to correct many errors, thereby misleading learners.
Shamil Chollampatt, Hwee Tou Ng
openaire   +1 more source

Spatial‐Compatibility‐Assisted Molecular Intercalation in MXenes

Advanced Materials, EarlyView.
This work demonstrates a solvent–free NH4F–mediated route for simultaneous Al removal and molecular intercalation in MXenes. Intercalants are selected by comparing their crystallographic X, Y, and Z dimensions with the MXene interlayer spacing, establishing a spatial‐compatibility criterion that rationalizes guest–host matching and enables predictive ...
Minhao Sheng, Xiaoqing Bin, Xiangyang Liu, Yingji Zhao, Wenxiu Que, Yusuke Asakura, Yusuke Yamauchi   +6 more
wiley   +1 more source

Single‐Particle FRET Probes Heterogeneity in the Ligand Shell of Colloidal Perovskite Quantum Dots

Advanced Materials, EarlyView.
Single‐particle, single‐molecule Förster resonance energy transfer turns dye‐tagged ligands into nanorulers for the otherwise elusive organic shell of CsPbBr3 quantum dots. Distance variations within individual particles reveal pronounced local heterogeneity, while changes in the surrounding ligand chemistry shift the average dye–surface separation ...
Leon G. Feld, Oleksandr Kolomiiets, Noah A. Shahin, Sebastian Sabisch, Amrutha Rajan, Gabriele Rainò, Maksym V. Kovalenko   +6 more
wiley   +1 more source

Grammatical Error Correction with Neural Reinforcement Learning

CoRR, 2017
We propose a neural encoder-decoder model with reinforcement learning (NRL) for grammatical error correction (GEC). Unlike conventional maximum likelihood estimation (MLE), the model directly optimizes towards an objective that considers a sentence-level, task-specific evaluation metric, avoiding the exposure bias issue in MLE.
Keisuke Sakaguchi, Matt Post, Benjamin Van Durme   +2 more
openaire   +4 more sources

Multimodal Engagement Assessment in Children During Invented Story Paradigm With a Social Robot

Advanced Robotics Research, EarlyView.
A multimodal framework is proposed to assess children's engagement during storytelling interactions with a social robot. Gaze, physiological, and behavioral data are combined and validated against observer ratings. An automated gaze‐labeling strategy is introduced, and supervised classifiers achieve high accuracy. The study supports scalable engagement
Laura Fiorini, Elena Adelucci, Stefano Scatigna, Lorenzo Pugi, Alice Bruni, Benedetta Carotenuto, Chiara Pecini, Filippo Cavallo   +7 more
wiley   +1 more source

Deep Learning-Based Context-Sensitive Spelling Typing Error Correction

IEEE Access, 2020
This study aims to solve the context-sensitive spelling error problem for English documents. There are two types of spelling errors in English: non-word spelling errors and context-sensitive spelling errors. Non-word spelling errors are simple to correct
Jung-Hun Lee, Minho Kim, Hyuk-Chul Kwon
doaj   +1 more source

A multi-task learning framework for efficient grammatical error correction of textual messages in mobile communications

EURASIP Journal on Wireless Communications and Networking, 2022
In mobile communications, plenty of textual messages need to be transmitted and processed rapidly. However, messages usually contain noise, which will affect the performance of related applications. Thus, we investigate grammatical error correction (GEC)
Fayu Pan, Bin Cao, Jing Fan
doaj   +1 more source

LLM‐Integrated Human–Robot Interaction System for Microrobots

Advanced Robotics Research, EarlyView.
This paper proposes an LLM‐based control framework for guiding microrobots using human natural language. This framework can convert the natural human speech into safe and executable command sets for reliable navigation in complex environments. The experimental results show high accuracy and robustness in task performance, demonstrating the potential of
Bairong Zhu, Amar Salehi, Tingting Yu
wiley   +1 more source