Papers by Jaejun Lee
Honkling: In-Browser Personalization for Ubiquitous Keyword Spotting (D19-3)
Copied to clipboard
| Challenge: | keyword spotting systems are used for simple commands recognition on devices . however, voice-enabled web applications are few and far between . a prominent drawback is that most of these systems perform speech recognition in the cloud . |
| Approach: | Honkling is a JavaScript-based keyword spotting system that can be deployed on user devices. |
| Outcome: | Honkling is a JavaScript-based keyword spotting system that can be deployed on user devices. |
Showing Your Work Doesn’t Always Work (2020.acl-main)
Copied to clipboard
| Challenge: | countless experimental papers lack empirical rigor, disregarding necessities such as statistical significance tests and computational environments. |
| Approach: | They propose to report the expected validation effectiveness of the best-tuned model with respect to the computational budget. |
| Outcome: | The proposed model favors negative errors and yields poor bootstrapped confidence intervals, the authors argue . they find that the proposed model is biased and uses error-prone assumptions . |
DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference (2020.acl-main)
Copied to clipboard
| Challenge: | Large-scale pre-trained language models such as BERT are notorious for being slow in both training and inference. |
| Approach: | They propose a method to accelerate BERT inference by inserting extra classification layers between each transformer layer of BERT. |
| Outcome: | The proposed method saves up to 40% inference time with minimal degradation in model quality. |
VISTA: Visual-Textual Knowledge Graph Representation Learning (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing knowledge graph embedding methods only consider the structure of a knowledge graph, but some recent proposed methods utilize images or text descriptions of entities in a VTKG. |
| Approach: | They propose a visual-textual knowledge graph (VTKG) where triplets can be explained using images and entities and relations can accompany text descriptions. |
| Outcome: | The proposed method outperforms state-of-the-art knowledge graph completion methods in real-world knowledge graphs. |