Search Results for author:
Found 41 papers, 1 papers with code
AUGNLG: Few-shot Natural Language Generation using Self-trained Data Augmentation
Natural Language Generation (NLG) is a key component in a task-oriented dialogue system, which converts the structured meaning representation (MR) to the natural language.
Efficient Large-Scale Domain Classification with Personalized Attention
In this paper, we explore the task of mapping spoken language utterances to one of thousands of natural language understanding domains in intelligent personal digital assistants (IPDAs).
A Scalable Neural Shortlisting-Reranking Approach for Large-Scale Domain Classification in Natural Language Understanding
Intelligent personal digital assistants (IPDAs), a popular real-life application with spoken language understanding capabilities, can cover potentially thousands of overlapping domains for natural language understanding, and the task of finding the best domain to handle an utterance becomes a challenging problem on a large scale.
OneNet: Joint Domain, Intent, Slot Prediction for Spoken Language Understanding
In practice, most spoken language understanding systems process user input in a pipelined manner; first domain is predicted, then intent and semantic slots are inferred according to the semantic frames of the predicted domain.
Speaker-Sensitive Dual Memory Networks for Multi-Turn Slot Tagging
In multi-turn dialogs, natural language understanding models can introduce obvious errors by being blind to contextual information.
Character-Level Feature Extraction with Densely Connected Networks
Generating character-level features is an important step for achieving good results in various natural language processing tasks.
Rich Character-Level Information for Korean Morphological Analysis and Part-of-Speech Tagging
Due to the fact that Korean is a highly agglutinative, character-rich language, previous work on Korean morphological analysis typically employs the use of sub-character features known as graphemes or otherwise utilizes comprehensive prior linguistic knowledge (i. e., a dictionary of known morphological transformation forms, or actions).
Joint Learning of Domain Classification and Out-of-Domain Detection with Dynamic Class Weighting for Satisficing False Acceptance Rates
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 between users and the systems.
Coupled Representation Learning for Domains, Intents and Slots in Spoken Language Understanding
Our proposed model learns the vector representation of intents based on the slots tied to these intents by aggregating the representations of the slots.
Supervised Domain Enablement Attention for Personalized Domain Classification
The attention weights are explicitly encouraged to be similar to the corresponding elements of the ground-truth's one-hot vector by supervised attention, and the attention information of the other enabled domains is leveraged through self-distillation.
Efficient Large-Scale Neural Domain Classification with Personalized Attention
In this paper, we explore the task of mapping spoken language utterances to one of thousands of natural language understanding domains in intelligent personal digital assistants (IPDAs).
Domain Attention with an Ensemble of Experts
When given domain K + 1, our model uses a weighted combination of the K domain experts{'} feedback along with its own opinion to make predictions on the new domain.
Adversarial Adaptation of Synthetic or Stale Data
Both cause a distribution mismatch between training and evaluation, leading to a model that overfits the flawed training data and performs poorly on the test data.
Cross-Lingual Transfer Learning for POS Tagging without Cross-Lingual Resources
Evaluating on POS datasets from 14 languages in the Universal Dependencies corpus, we show that the proposed transfer learning model improves the POS tagging performance of the target languages without exploiting any linguistic knowledge between the source language and the target language.
Frustratingly Easy Neural Domain Adaptation
Popular techniques for domain adaptation such as the feature augmentation method of Daum{\'e} III (2009) have mostly been considered for sparse binary-valued features, but not for dense real-valued features such as those used in neural networks.
Domainless Adaptation by Constrained Decoding on a Schema Lattice
In many applications such as personal digital assistants, there is a constant need for new domains to increase the system{'}s coverage of user queries.
Locale-agnostic Universal Domain Classification Model in Spoken Language Understanding
In this paper, we introduce an approach for leveraging available data across multiple locales sharing the same language to 1) improve domain classification model accuracy in Spoken Language Understanding and user experience even if new locales do not have sufficient data and 2) reduce the cost of scaling the domain classifier to a large number of locales.
Continuous Learning for Large-scale Personalized Domain Classification
This is a major component in mainstream IPDAs in industry.
Pseudo Labeling and Negative Feedback Learning for Large-scale Multi-label Domain Classification
In large-scale domain classification, an utterance can be handled by multiple domains with overlapped capabilities.
Large-scale Hybrid Approach for Predicting User Satisfaction with Conversational Agents
An widely used approach to tackle this is to collect human annotation data and use them for evaluation or modeling.
Self-Supervised Contrastive Learning for Efficient User Satisfaction Prediction in Conversational Agents
Moreover, a powerful satisfaction model can be used as an objective function that a conversational agent continuously optimizes for.
A scalable framework for learning from implicit user feedback to improve natural language understanding in large-scale conversational AI systems
Natural Language Understanding (NLU) is an established component within a conversational AI or digital assistant system, and it is responsible for producing semantic understanding of a user request.
DEUS: A Data-driven Approach to Estimate User Satisfaction in Multi-turn Dialogues
Digital assistants are experiencing rapid growth due to their ability to assist users with day-to-day tasks where most dialogues are happening multi-turn.
Neural model robustness for skill routing in large-scale conversational AI systems: A design choice exploration
Ensuring model robustness or resilience in the skill routing component is an important problem since skills may dynamically change their subscription in the ontology after the skill routing model has been deployed to production.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Handling Long-Tail Queries with Slice-Aware Conversational Systems
We have been witnessing the usefulness of conversational AI systems such as Siri and Alexa, directly impacting our daily lives.
Learning Slice-Aware Representations with Mixture of Attentions
Real-world machine learning systems are achieving remarkable performance in terms of coarse-grained metrics like overall accuracy and F-1 score.
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.
