We describe a joint model for intent detection and slot filling based on convolutional neural
networks (CNN). The proposed architecture can be perceived as a neural network (NN) …

While reinforcement learning (RL) has demonstrated remarkable success in enhancing
large language models (LLMs), it has primarily focused on single-turn tasks such as solving …

We highlight a practical yet rarely discussed problem in dialogue state tracking (DST),
namely handling unknown slot values. Previous approaches generally assume predefined …

In a multi-domain, multi-turn spoken language understanding session, information from the
history often greatly reduces the ambiguity of the current turn. In this paper, we apply the …

We introduce the Piecewise-Constant Conditional Intensity Model, a model for learning
temporal dependencies in event streams. We describe a closed-form Bayesian approach to …

Recent advancements in integrating external tools with Large Language Models (LLMs) have
opened new frontiers, with applications in mathematical reasoning, code generators, and …

Multi-intent natural language sentence classification aims at identifying multiple user goals
in a single natural language sentence (eg,“find Beyonce’s movie and music”→ find movie, …

Unsupervised sentence representation learning has progressed through contrastive learning
and data augmentation methods such as dropout masking. Despite this progress, sentence …

Background House dust mite (HDM) is the most common airborne source causing complex
allergy symptoms. There are geographic differences in the allergen molecule sensitization …

We describe a unified multi-turn multi-task spoken language understanding (SLU) solution
capable of handling multiple context sensitive classification (intent determination) and …