Search Results for author:
Found 11 papers, 0 papers with code
TrICy: Trigger-guided Data-to-text Generation with Intent aware Attention-Copy
Data-to-text (D2T) generation is a crucial task in many natural language understanding (NLU) applications and forms the foundation of task-oriented dialog systems.
Ranked #3 on
Data-to-Text Generation
on E2E NLG Challenge
What's in the Flow? Exploiting Temporal Motion Cues for Unsupervised Generic Event Boundary Detection
This inquiry drives us to algorithmically harness motion cues for identifying generic event boundaries in videos.
Ranked #1 on
Generic Event Boundary Detection
on Kinetics-GEBD
An Edge Assisted Robust Smart Traffic Management and Signalling System for Guiding Emergency Vehicles During Peak Hours
In this paper, we have proposed a three-phase system that can guide emergency vehicles and manage traffic based on the degree of congestion.
LIP: Lightweight Intelligent Preprocessor for meaningful text-to-speech
In this work, we aim to introduce a lightweight intelligent preprocessor (LIP) that can enhance the readability of a message before being passed downstream to existing TTS systems.
PrivPAS: A real time Privacy-Preserving AI System and applied ethics
This motivates us to work towards a solution to generate privacy-conscious cues for raising awareness in smartphone users of any sensitivity in their viewfinder content.
LIDSNet: A Lightweight on-device Intent Detection model using Deep Siamese Network
To build high-quality real-world conversational solutions for edge devices, there is a need for deploying intent detection model on device.
Ranked #1 on
Intent Detection
on SNIPS
(model size metric)
Language Detection Engine for Multilingual Texting on Mobile Devices
This model outperforms fastText by 60. 39% and ML-Kit by 23. 67% in F1 score for European languages.
Real-Time Optimized N-gram For Mobile Devices
The LM loading time on mobile is linear with respect to model size.
edATLAS: An Efficient Disambiguation Algorithm for Texting in Languages with Abugida Scripts
To this end, we propose a disambiguation algorithm and showcase its usefulness in two novel mutually non-exclusive input methods for languages natively using the abugida writing system: (a) disambiguation of ambiguous input for abugida scripts, and (b) disambiguation of word variants in romanized scripts.
EmpLite: A Lightweight Sequence Labeling Model for Emphasis Selection of Short Texts
To the best of our knowledge, this work presents the first lightweight deep learning approach for smartphone deployment of emphasis selection.
LiteMuL: A Lightweight On-Device Sequence Tagger using Multi-task Learning
The proposed LiteMuL not only outperforms the current state of the art results but also surpasses the results of our proposed on-device task-specific models, with accuracy gains of up to 11% and model-size reduction by 50%-56%.
