Optimizing Machine Translation for Virtual Assistants: Multi-Variant Generation with VerbNet and Conditional Beam Search

M Sowański, A Janicki - 2023 18th Conference on Computer …, 2023 - ieeexplore.ieee.org
In this paper, we introduce a domain-adapted machine translation (MT) model for intelligent
virtual assistants (IVA) designed to translate natural language understanding (NLU) training …

[PDF][PDF] Analysis of Dataset Limitations in Semantic Knowledge-Driven Multi-Variant Machine Translation

M Sowański, J Hosciłowicz, A Janicki - Journal of Automation, Mobile …, 2024 - sciendo.com
In this study, we explore the implicafions of dataset limitafions in semanfic knowledge‐driven
machine trans‐lafion (MT) for intelligent virtual assistants (IVA). Our approach diverges from …

CL-QR: Cross-lingual enhanced query reformulation for multi-lingual conversational AI agents

Z Sun, Z Zhao, S Lu, C Ma, X Liu, X Fan… - Proceedings of the …, 2023 - aclanthology.org
The growing popularity of conversational AI agents such as Alexa, Google Assistant, and Siri
rely on accurate spoken language comprehension. The query reformulation (QR) method …

Novel feature discovery for task-oriented dialog systems

VT Ho, M Soliman, A Abujabal - Findings of the Association for …, 2023 - aclanthology.org
A novel feature represents a cluster of semantically equivalent novel user requests eg,
requests to play a song on a service or read user's messages. Detecting and supporting …