Search Results for author:
Found 5 papers, 2 papers with code
Leveraging Seq2seq Language Generation for Multi-level Product Issue Identification
To harness such information to better serve customers, in this paper, we created a machine learning approach to automatically identify product issues and uncover root causes from the customer feedback text.
Mind the Time: Temporally-Controlled Multi-Event Video Generation
Generating such sequences with precise temporal control is infeasible with existing video generators that rely on a single paragraph of text as input.
STRIVE: Scene Text Replacement In Videos
Finally, the new text is transferred from the reference to remaining frames using a novel learned image transformation network that captures lighting and blur effects in a temporally consistent manner.
PunKtuator: A Multilingual Punctuation Restoration System for Spoken and Written Text
Text transcripts without punctuation or sentence boundaries are hard to comprehend for both humans and machines.
Large Scale Multimodal Classification Using an Ensemble of Transformer Models and Co-Attention
Accurate and efficient product classification is significant for E-commerce applications, as it enables various downstream tasks such as recommendation, retrieval, and pricing.
