Active learning for ontological event extraction incorporating named entity recognition and unknown word handling by Han, Xu, Kim, Jung-jae, Kwoh, Chee Keong

“…We then develop a statistical method to rank the potential false negatives of unlabeled documents 1) by using a language model that measures the probabilities of the expression of multiple events in documents and 2) by using a named entity recognition system that locates the named entities that can be event arguments (e.g. proteins). …”
Get full text
Get full text

Power system modeling and simulation by Luo, Yishi

“…Correspondingly, the demand for higher functional software with better modeling environment is acquired. In this dissertation, PSS/E and MATLAB/Simulink environment are appliedintegratedly, the dissertation is mainly focusing on a test system called Nordic-74 which is a variant of Nordic-32 published by IEEE Power & Energy Society in 2015. …”
Get full text

Contextual object detection with multimodal large language models by Zang, Yuhang, Li, Wei, Han, Jun, Zhou, Kaiyang, Loy, Chen Change

“…Moreover, we present ContextDET, a unified multimodal model that is capable of end-to-end differentiable modeling of visual-language contexts, so as to locate, identify, and associate visual objects with language inputs for human-AI interaction. …”
Get full text

Scene classification using a hybrid generative/discriminative approach by Bosch, A, Zisserman, A, Muñoz, X

“…We achieve superior classification performance to recent publications that have used a bag of visual word representation, in all cases, using the authors’ own data sets and testing protocols. …”

Learning object categories from Google’s image search by Fergus, R, Fei-Fei, L, Perona, P, Zisserman, A

“…We develop a new model, TSI-pLSA, which extends pLSA (as applied to visual words) to include spatial information in a translation and scale invariant manner. …”

Cats and dogs by Parkhi, OM, Vedaldi, A, Zisserman, A, lawahar, CV

“…To this end we introduce a new annotated dataset of pets covering 37 different breeds of cats and dogs. …”

Machine translation of software-specific documentations by Tee, Li Yin

“…Lastly, we evaluate our test sets with BLEU (bilingual evaluation understudy) and WER (word error rate) to get the translation quality and find out how this model and what is the problem and what can be improved.…”
Get full text

Diagrammatic Representation and Inference : 12th International Conference, Diagrams 2021, Virtual, September 28-30, 2021, Proceedings / by Diagrams (Conference) (12th : 2021 : Online) 643173, Basu, Amrita, 1953-, editor 643175, Stapleton, Gem, editor 643176, Linker, Sven, editor 643177, Legg, Catherine, editor 643178, Manalo, Emmanuel, editor 643179, Viana, Petrucio, editor 643180

Adversarial Prompt Transformation for Systematic Jailbreaks of LLMs by Awoufack, Kevin E.

“…This was implemented using Proximal Policy Optimization (PPO) and tested with both a classifier and judge reward model, attaining at best a 16% attach success rate on a target model. …”
Get full text