Results 41 to 50 of about 561,016 (281)
News Topic Detection Based on Capsule Semantic Graph
Big Data Mining and Analytics, 2022 Most news topic detection methods use word-based methods, which easily ignore the relationship among words and have semantic sparsity, resulting in low topic detection accuracy.
Shuang Yang, Yan Tang
doaj +1 more source
IEEE Access, 2021 Battery ensures power solutions for many necessary portable devices such as electric vehicles, mobiles, and laptops. Owing to the rapid growth of Li-ion battery users, unwanted incidents involving Li-ion batteries have also increased to some extent.
Shahid A. Hasib +11 more
semanticscholar +1 more source
OCTIS: Comparing and Optimizing Topic models is Simple!
Conference of the European Chapter of the Association for Computational Linguistics, 2021 In this paper, we present OCTIS, a framework for training, analyzing, and comparing Topic Models, whose optimal hyper-parameters are estimated using a Bayesian Optimization approach.
Silvia Terragni +4 more
semanticscholar +1 more source
Improving Unsupervised Dialogue Topic Segmentation with Utterance-Pair Coherence Scoring [PDF]
SIGDIAL Conferences, 2021 Dialogue topic segmentation is critical in several dialogue modeling problems. However, popular unsupervised approaches only exploit surface features in assessing topical coherence among utterances.
Linzi Xing, G. Carenini
semanticscholar +1 more source
A Novel Hierarchical Topic Model for Horizontal Topic Expansion With Observed Label Information
IEEE Access, 2019 Hierarchical topic models, such as hierarchical Latent Dirichlet Allocation (hLDA)and its variations, can organize topics into a hierarchy automatically.
Xi Zou +4 more
doaj +1 more source
A latent topic‐aware network for dense video captioning
IET Computer Vision, 2023 Multiple events in a long untrimmed video possess the characteristics of similarity and continuity. These characteristics can be considered as a kind of topic semantic information, which probably behaves as same sports, similar scenes, same objects etc ...
Tao Xu +3 more
doaj +1 more source
NaturalConv: A Chinese Dialogue Dataset Towards Multi-turn Topic-driven Conversation [PDF]
AAAI Conference on Artificial Intelligence, 2021 In this paper, we propose a Chinese multi-turn topic-driven conversation dataset, NaturalConv, which allows the participants to chat anything they want as long as any element from the topic is mentioned and the topic shift is smooth.
Xiaoyang Wang +3 more
semanticscholar +1 more source
Exploiting Long-Term Dependency for Topic Sentiment Analysis
IEEE Access, 2020 Most existing unsupervised approaches to detect topic sentiment in social texts consider only the text sequences in corpus and put aside social dynamics, as leads to algorithm’s disability to discover true sentiment of social users. To address the
Faliang Huang +3 more
doaj +1 more source
Graph-Sparse LDA: A Topic Model with Structured Sparsity [PDF]
, 2014 Originally designed to model text, topic modeling has become a powerful tool for uncovering latent structure in domains including medicine, finance, and vision.
Adams, Ryan +2 more
core +1 more source
Topic modeling revisited: New evidence on algorithm performance and quality metrics
PLoS ONE, 2022 Topic modeling is a popular technique for exploring large document collections. It has proven useful for this task, but its application poses a number of challenges. First, the comparison of available algorithms is anything but simple, as researchers use
M. Rüdiger +3 more
semanticscholar +1 more source