Filters








75,966 Hits in 11.2 sec

Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation [article]

Albert Gatt, Emiel Krahmer
2018 arXiv   pre-print
This paper surveys the current state of the art in Natural Language Generation (NLG), defined as the task of generating text or speech from non-linguistic input.  ...  This survey therefore aims to (a) give an up-to-date synthesis of research on the core tasks in NLG and the architectures adopted in which such tasks are organised; (b) highlight a number of relatively  ...  Acknowledgements We thank the four reviewers for their detailed and constructive comments.  ... 
arXiv:1703.09902v4 fatcat:owx2fgo2bjej3b27ve2f3ledoe

Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation

Albert Gatt, Emiel Krahmer
2018 The Journal of Artificial Intelligence Research  
This paper surveys the current state of the art in Natural Language Generation (NLG), defined as the task of generating text or speech from non-linguistic input.  ...  This survey therefore aims to (a) give an up-to-date synthesis of research on the core tasks in NLG and the architectures adopted in which such tasks are organised; (b) highlight a number of recent research  ...  Acknowledgments We thank the four reviewers for their detailed and constructive comments.  ... 
doi:10.1613/jair.5477 fatcat:ycuteghjzncn7nx6pzkhzd6mn4

BACON: Deep-Learning Powered AI for Poetry Generation with Author Linguistic Style Transfer [article]

Alejandro Rodriguez Pascual
2021 arXiv   pre-print
Extrinsic evaluation of the output generated by BACON shows that participants were unable to tell the difference between human and AI-generated poems in any statistically significant way.  ...  It combines concepts and techniques from finite state machinery, probabilistic models, artificial neural networks and deep learning, to write original poetry with rich aesthetic-qualities in the style  ...  and the WFST used in the APG module.  ... 
arXiv:2112.11483v1 fatcat:d3veffh2dffw5c5uida4jfhqtu

Pretrained Language Models for Text Generation: A Survey [article]

Junyi Li, Tianyi Tang, Wayne Xin Zhao, Jian-Yun Nie, Ji-Rong Wen
2022 arXiv   pre-print
This comprehensive survey is intended to help researchers interested in text generation problems to learn the core concepts, the main techniques and the latest developments in this area based on PLMs.  ...  Text generation based on PLMs is viewed as a promising approach in both academia and industry. In this paper, we provide a survey on the utilization of PLMs in text generation.  ...  In conclusion, text generation based on PLMs has greatly contributed to the advance of the state of the art in this field.  ... 
arXiv:2201.05273v4 fatcat:pnffabspsnbhvo44gbaorhxc3a

Positioning yourself in the maze of Neural Text Generation: A Task-Agnostic Survey [article]

Khyathi Raghavi Chandu, Alan W Black
2021 arXiv   pre-print
Neural text generation metamorphosed into several critical natural language applications ranging from text completion to free form narrative generation.  ...  Specifically, this paper surveys the fundamental components of modeling approaches relaying task agnostic impacts across various generation tasks such as storytelling, summarization, translation etc.,  ...  Albert Gatt and Emiel Krahmer. 2018. Survey of the state of the art in natural language generation: Core tasks, applications and evaluation. J. Artif. Intell. Res., 61:65-170.  ... 
arXiv:2010.07279v2 fatcat:jp76n5vk7zbvnhfexhwa3rludu

Smart Contract Generation Assisted by AI-Based Word Segmentation

Yu Tong, Weiming Tan, Jingzhi Guo, Bingqing Shen, Peng Qin, Shuaihe Zhuo
2022 Applied Sciences  
In the robustness evaluation, SpIn achieves state-of-the-art F1 scores and Recall of Out-of-Vocabulary (R_OOV) words on multiple word segmentation tasks.  ...  SpIn serves as the core component in AIASCG that accurately recommends the intermediate MNL outputs from a natural language sentence, tremendously reducing the manual effort in contract generation.  ...  Informed Consent Statement: Not applicable. Data Availability Statement: Not applicable. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/app12094773 fatcat:binsuxkssnazdhmbzbdtgkbo6m

Investigating Pretrained Language Models for Graph-to-Text Generation [article]

Leonardo F. R. Ribeiro, Martin Schmitt, Hinrich Schütze, Iryna Gurevych
2021 arXiv   pre-print
In this paper, we investigate two recently proposed pretrained language models (PLMs) and analyze the impact of different task-adaptive pretraining strategies for PLMs in graph-to-text generation.  ...  We show that the PLMs BART and T5 achieve new state-of-the-art results and that task-adaptive pretraining strategies improve their performance even further.  ...  Ribeiro is supported by the German Research Foundation (DFG) as part of the Research Training Group "Adaptive Preparation of Information form Heterogeneous Sources" (AIPHES, GRK 1994/1) and as part of  ... 
arXiv:2007.08426v3 fatcat:zwirbzu5gnatth5qzxeyodmlyu

Message from the general chair

Benjamin C. Lee
2015 2015 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)  
To inject knowledge, we use a state-of-the-art system which cross-links (or "grounds") expressions in free text to Wikipedia.  ...  We explore ways of using the resulting grounding to boost the performance of a state-of-the-art co-reference resolution system.  ...  in natural language generation.  ... 
doi:10.1109/ispass.2015.7095776 dblp:conf/ispass/Lee15 fatcat:ehbed6nl6barfgs6pzwcvwxria

Societal Biases in Language Generation: Progress and Challenges [article]

Emily Sheng, Kai-Wei Chang, Premkumar Natarajan, Nanyun Peng
2021 arXiv   pre-print
Technology for language generation has advanced rapidly, spurred by advancements in pre-training large models on massive amounts of data and the need for intelligent agents to communicate in a natural  ...  Language generation presents unique challenges for biases in terms of direct user interaction and the structure of decoding techniques.  ...  Acknowledgments We would like to thank Seraphina Goldfarb-Tarrant, Sunipa Dev, Jason Teoh, members of the Plus Lab, and our anonymous reviewers for the many helpful suggestions that went into this paper  ... 
arXiv:2105.04054v3 fatcat:dhwma4hvfbf7jke3lt227qb73i

Few-Shot Table-to-Text Generation with Prototype Memory [article]

Yixuan Su, Zaiqiao Meng, Simon Baker, Nigel Collier
2021 arXiv   pre-print
However, due to the data-hungry nature of neural models, their performances strongly rely on large-scale training examples, limiting their applicability in real-world applications.  ...  Experimental results on three benchmark datasets with three state-of-the-art models demonstrate that the proposed framework significantly improves the model performance across various evaluation metrics  ...  Acknowledgments The authors wish to thank our anonymous reviewers for their insightful suggestions and comments.  ... 
arXiv:2108.12516v2 fatcat:xadgdq6xyfgajc23q26rtlkx44

Dynamic deadlock verification for general barrier synchronisation

Tiago Cogumbreiro, Raymond Hu, Francisco Martins, Nobuko Yoshida
2015 Proceedings of the 20th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming - PPoPP 2015  
We prove that finding a deadlock in either representation is equivalent, and that the verification algorithm is sound and complete with respect to the notion of deadlock in our core language.  ...  Our tool verifies more barrier synchronisation patterns than current state-of-the-art.  ...  The work is partially supported by EPSRC KTS with Cognizant, EP/K034413/1, EP/K011715/1 and EP/L00058X/1, EU project FP7-612985 Up-Scale and ICT COST Action 1201 BETTY.  ... 
doi:10.1145/2688500.2688519 dblp:conf/ppopp/CogumbreiroHMY15 fatcat:zpos24esf5hgnjhvhiyvfbfk7y

Dynamic deadlock verification for general barrier synchronisation

Tiago Cogumbreiro, Raymond Hu, Francisco Martins, Nobuko Yoshida
2015 SIGPLAN notices  
We prove that finding a deadlock in either representation is equivalent, and that the verification algorithm is sound and complete with respect to the notion of deadlock in our core language.  ...  Our tool verifies more barrier synchronisation patterns than current state-of-the-art.  ...  The work is partially supported by EPSRC KTS with Cognizant, EP/K034413/1, EP/K011715/1 and EP/L00058X/1, EU project FP7-612985 Up-Scale and ICT COST Action 1201 BETTY.  ... 
doi:10.1145/2858788.2688519 fatcat:tn3tnmgbhba4dpojydqrpxeiam

The ECHORD Project: A General Perspective [chapter]

Sascha Griffiths, Ciro Natale, Ricardo Araújo, Germano Veiga, Pasquale Chiacchio, Florian Röhrbein, Stefano Chiaverini, Reinhard Lafrenz
2014 Springer Tracts in Advanced Robotics  
There has been a long history of outstanding research and development in both robot manufacturers and research institutes.  ...  However, finding common ground between manufacturers and the research community, especially when it comes to defining the future direction of robotics research, has proven difficult in the past.  ...  The core idea of the experiment was the application of state-ofthe-art industrial robots together with fixable, passive kinematic arms, which have a large number of degrees of freedom, but without their  ... 
doi:10.1007/978-3-319-03838-4_1 fatcat:6vwxybovv5ev3g5mw4xre4tmmm

Computational generation of slogans

Khalid Alnajjar, Hannu Toivonen
2020 Natural Language Engineering  
We evaluate the metaphor and slogan generation methods by running crowdsourced surveys.  ...  In advertising, slogans are used to enhance the recall of the advertised product by consumers and to distinguish it from others in the market.  ...  This work has been supported by the Academy of Finland under grant 276897 (CLiC) and by the European Union's Horizon 2020 programme under grant 825153 (Embeddia).  ... 
doi:10.1017/s1351324920000236 fatcat:nglnm2oar5etpk74asov5uujnu

A review of the generation of requirements specification in natural language using objects UML models and domain ontology

Alaa Abdalazeim, Farid Meziane
2021 Procedia Computer Science  
This paper presents a survey of some works undertaken in the field of generation natural language specifications from object UML model using the support of an ontology. and analyzing the robustness and  ...  This paper presents a survey of some works undertaken in the field of generation natural language specifications from object UML model using the support of an ontology. and analyzing the robustness and  ...  Generating natural language specifications from software models: state of the art In this section, we will review two types of works.  ... 
doi:10.1016/j.procs.2021.05.102 fatcat:ehjiod3kdvectoibcc2q5kpjny
« Previous Showing results 1 — 15 out of 75,966 results