2 code implementations • 4 Jan 2024 • Songbo Hu, Xiaobin Wang, Zhangdie Yuan, Anna Korhonen, Ivan Vulić
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).
no code implementations • 19 Oct 2023 • Songbo Hu, Han Zhou, Moy Yuan, Milan Gritta, Guchun Zhang, Ignacio Iacobacci, Anna Korhonen, Ivan Vulić
Achieving robust language technologies that can perform well across the world's many languages is a central goal of multilingual NLP.
1 code implementation • 26 Jul 2023 • Songbo Hu, Han Zhou, Mete Hergul, Milan Gritta, Guchun Zhang, Ignacio Iacobacci, Ivan Vulić, Anna Korhonen
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.
1 code implementation • 7 Nov 2022 • Songbo Hu, Ivan Vulić, Fangyu Liu, Anna Korhonen
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.
1 code implementation • 12 Oct 2022 • Zhangdie Yuan, Songbo Hu, Ivan Vulić, Anna Korhonen, Zaiqiao Meng
Acquiring factual knowledge with Pretrained Language Models (PLMs) has attracted increasing attention, showing promising performance in many knowledge-intensive tasks.
no code implementations • 15 Sep 2021 • Christian Geishauser, Songbo Hu, Hsien-Chin Lin, Nurul Lubis, Michael Heck, Shutong Feng, Carel van Niekerk, Milica Gašić
The dialogue management component of a task-oriented dialogue system is typically optimised via reinforcement learning (RL).
no code implementations • SIGDIAL (ACL) 2021 • Hsien-Chin Lin, Nurul Lubis, Songbo Hu, Carel van Niekerk, Christian Geishauser, Michael Heck, Shutong Feng, Milica Gašić
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.