Search Results for author:
Found 7 papers, 4 papers with code
DIALIGHT: Lightweight Multilingual Development and Evaluation of Task-Oriented Dialogue Systems with Large Language Models
We present DIALIGHT, a toolkit for developing and evaluating multilingual Task-Oriented Dialogue (ToD) systems which facilitates systematic evaluations and comparisons between ToD systems using fine-tuning of Pretrained Language Models (PLMs) and those utilising the zero-shot and in-context learning capabilities of Large Language Models (LLMs).
A Systematic Study of Performance Disparities in Multilingual Task-Oriented Dialogue Systems
Achieving robust language technologies that can perform well across the world's many languages is a central goal of multilingual NLP.
Multi3WOZ: A Multilingual, Multi-Domain, Multi-Parallel Dataset for Training and Evaluating Culturally Adapted Task-Oriented Dialog Systems
Creating high-quality annotated data for task-oriented dialog (ToD) is known to be notoriously difficult, and the challenges are amplified when the goal is to create equitable, culturally adapted, and large-scale ToD datasets for multiple languages.
Reranking Overgenerated Responses for End-to-End Task-Oriented Dialogue Systems
At training, the high-scoring partition comprises all generated responses whose similarity to the gold response is higher than the similarity of the greedy response to the gold response.
Can Pretrained Language Models (Yet) Reason Deductively?
Acquiring factual knowledge with Pretrained Language Models (PLMs) has attracted increasing attention, showing promising performance in many knowledge-intensive tasks.
What Does The User Want? Information Gain for Hierarchical Dialogue Policy Optimisation
The dialogue management component of a task-oriented dialogue system is typically optimised via reinforcement learning (RL).
Domain-independent User Simulation with Transformers for Task-oriented Dialogue Systems
TUS can compete with rule-based user simulators on pre-defined domains and is able to generalise to unseen domains in a zero-shot fashion.
