Results 11 to 20 of about 7,351 (251)

Collective Human Opinions in Semantic Textual Similarity

Transactions of the Association for Computational Linguistics, 2023
Abstract Despite the subjective nature of semantic textual similarity (STS) and pervasive disagreements in STS annotation, existing benchmarks have used averaged human ratings as gold standard. Averaging masks the true distribution of human opinions on examples of low agreement, and prevents models from capturing the semantic vagueness ...
Yuxia Wang, Shimin Tao, Ning Xie, Hao Yang, Timothy Baldwin, Karin Verspoor   +5 more
doaj   +3 more sources

Artificial intelligence-aided assignment of journal submissions to associate editors—a feasibility study on IEEE transactions on medical imaging [PDF]

Visual Computing for Industry, Biomedicine, and Art
Efficient and accurate assignment of journal submissions to suitable associate editors (AEs) is critical in maintaining review quality and timeliness, particularly in high-volume, rapidly evolving fields such as medical imaging.
Xuanang Xu, Joshua Yan, Gloria Nwachukwu, Hongming Shan, Uwe Kruger, Ge Wang   +5 more
doaj   +2 more sources

UQeResearch: Semantic Textual Similarity Quantification [PDF]

Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015), 2015
This paper presents an approach for estimating the Semantic Textual Similarity of full English sentences as specified in Shared Task 2 of SemEval-2015. The semantic similarity of sentence pairs is quantified from three perspectives - structural, syntactical, and semantic. The numerical representations of the derived similarity measures are then applied
Hamed Hassanzadeh, Tudor Groza, Anthony N. Nguyen, Jane Hunter 0001   +3 more
openaire   +2 more sources

C-STS: Conditional Semantic Textual Similarity

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023
Published in EMNLP ...
Ameet Deshpande, Carlos E. Jimenez, Howard Chen 0003, Vishvak Murahari, Victoria Graf, Tanmay Rajpurohit, Ashwin Kalyan, Danqi Chen 0001, Karthik Narasimhan   +8 more
openaire   +2 more sources

Czech News Dataset for Semantic Textual Similarity

Language Resources and Evaluation, 2022
Abstract This paper describes a novel dataset consisting of sentences with two different semantic similarity annotations; with and without surrounding context. The data originate from the journalistic domain in the Czech language. The final dataset contains 138,556 human annotations divided into train and test sets.
Jakub Sido, Michal Seják, Ondrej Prazák, Miloslav Konopík, Václav Moravec   +4 more
openaire   +2 more sources

Semantic Textual Similarity of Sentences with Emojis

Companion Proceedings of the Web Conference 2020, 2020
In this paper, we extend the task of semantic textual similarity to include sentences which contain emojis. Emojis are ubiquitous on social media today, but are often removed in the pre-processing stage of curating datasets for NLP tasks. In this paper, we qualitatively ascertain the amount of semantic information lost by discounting emojis, as well as
Alok Debnath, Nikhil Pinnaparaju, Manish Shrivastava 0001, Vasudeva Varma, Isabelle Augenstein   +4 more
openaire   +3 more sources

Crosslinguistic Semantic Textual Similarity of Buddhist Chinese and Classical Tibetan

Journal of Open Humanities Data, 2022
In this paper we present the first-ever procedure for identifying highly similar sequences of text in Chinese and Tibetan translations of Buddhist 'sūtra' literature.
Rafal Felbur, Marieke Meelen, Paul Vierthaler   +2 more
doaj   +1 more source

Correlation Coefficients and Semantic Textual Similarity [PDF]

Proceedings of the 2019 Conference of the North, 2019
A large body of research into semantic textual similarity has focused on constructing state-of-the-art embeddings using sophisticated modelling, careful choice of learning signals and many clever tricks. By contrast, little attention has been devoted to similarity measures between these embeddings, with cosine similarity being used unquestionably in ...
Vitalii Zhelezniak, Aleksandar Savkov, April Shen, Nils Y. Hammerla   +3 more
openaire   +2 more sources

Attention-Based Overall Enhance Network for Chinese Semantic Textual Similarity Measure

Journal of Applied Science and Engineering, 2021
Semantic text similarity(STS) measure plays an important role in the practical application of natural language processing. However, due to the complexity of Chinese semantic comprehension and the lack of currently available Chinese text similarity ...
Hao Zhang, HuaXiong Zhang, XingYu Lu, Qiang Gao   +3 more
doaj   +1 more source

Similarity Search on Semantic Trajectories Using Text Processing

ISPRS International Journal of Geo-Information, 2022
The use of location-based sensors has increased exponentially. Tracking moving objects has become increasingly common, consolidating a new field of research that focuses on trajectory data management.
Damião Ribeiro de Almeida, Cláudio de Souza Baptista, Fabio Gomes de Andrade   +2 more
doaj   +1 more source