Privacy norms for smart home personal assistants

N Abdi, X Zhan, KM Ramokapane, J Such - Proceedings of the 2021 CHI …, 2021 - dl.acm.org
Smart Home Personal Assistants (SPA) have a complex ecosystem that enables them to
carry out various tasks on behalf of the user with just voice commands. SPA capabilities are …

SkillVet: automated traceability analysis of Amazon Alexa skills

JS Edu, X Ferrer-Aran, J Such… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Skills, are essential components in Smart Personal Assistants (SPA). The number of skills
has grown rapidly, dominated by a changing environment that has no clear business model …

Joint learning of domain classification and out-of-domain detection with dynamic class weighting for satisficing false acceptance rates

JK Kim, YB Kim - arXiv preprint arXiv:1807.00072, 2018 - arxiv.org
In domain classification for spoken dialog systems, correct detection of out-of-domain (OOD)
utterances is crucial because it reduces confusion and unnecessary interaction costs …

A re-ranker scheme for integrating large scale nlu models

C Su, R Gupta, S Ananthakrishnan… - 2018 IEEE Spoken …, 2018 - ieeexplore.ieee.org
Large scale Natural Language Understanding (NLU) systems are typically trained on large
quantities of data, requiring a fast and scalable training strategy. A typical design for NLU …

Large-scale hybrid approach for predicting user satisfaction with conversational agents

D Park, H Yuan, D Kim, Y Zhang, M Spyros… - arXiv preprint arXiv …, 2020 - arxiv.org
Measuring user satisfaction level is a challenging task, and a critical component in
developing large-scale conversational agent systems serving the needs of real users. An …

Learning context-dependent label permutations for multi-label classification

J Nam, YB Kim, EL Mencia, S Park… - International …, 2019 - proceedings.mlr.press
A key problem in multi-label classification is to utilize dependencies among the labels.
Chaining classifiers are a simple technique for addressing this problem but current …

Deciding whether to ask clarifying questions in large-scale spoken language understanding

JK Kim, G Wang, S Lee, YB Kim - 2021 IEEE Automatic Speech …, 2021 - ieeexplore.ieee.org
A large-scale conversational agent can suffer from understanding user utterances with
various ambiguities such as ASR ambiguity, intent ambiguity, and hypothesis ambiguity …

A bandit approach to posterior dialog orchestration under a budget

S Upadhyay, M Agarwal, D Bounneffouf… - arXiv preprint arXiv …, 2019 - arxiv.org
Building multi-domain AI agents is a challenging task and an open problem in the area of AI.
Within the domain of dialog, the ability to orchestrate multiple independently trained dialog …

Pseudo labeling and negative feedback learning for large-scale multi-label domain classification

JK Kim, YB Kim - … 2020-2020 IEEE International Conference on …, 2020 - ieeexplore.ieee.org
In large-scale domain classification, an utterance can be handled by multiple domains with
overlapped capabilities. However, only a limited number of ground-truth domains are …

Tadse: Template-aware dialogue sentence embeddings

M Oh, J Li, G Wang - arXiv preprint arXiv:2305.14299, 2023 - arxiv.org
Learning high quality sentence embeddings from dialogues has drawn increasing attentions
as it is essential to solve a variety of dialogue-oriented tasks with low annotation cost …