Privacy norms for smart home personal assistants
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 …
carry out various tasks on behalf of the user with just voice commands. SPA capabilities are …
SkillVet: automated traceability analysis of Amazon Alexa skills
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 …
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 …
utterances is crucial because it reduces confusion and unnecessary interaction costs …
A re-ranker scheme for integrating large scale nlu models
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 …
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 …
developing large-scale conversational agent systems serving the needs of real users. An …
Learning context-dependent label permutations for multi-label classification
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 …
Chaining classifiers are a simple technique for addressing this problem but current …
Deciding whether to ask clarifying questions in large-scale spoken language understanding
A large-scale conversational agent can suffer from understanding user utterances with
various ambiguities such as ASR ambiguity, intent ambiguity, and hypothesis ambiguity …
various ambiguities such as ASR ambiguity, intent ambiguity, and hypothesis ambiguity …
A bandit approach to posterior dialog orchestration under a budget
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 …
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 …
overlapped capabilities. However, only a limited number of ground-truth domains are …
Tadse: Template-aware dialogue sentence embeddings
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 …
as it is essential to solve a variety of dialogue-oriented tasks with low annotation cost …