1 code implementation • EANCS 2021 • Alexandru Coca, Bo-Hsiang Tseng, Bill Byrne
The evaluation of dialogue systems in interaction with simulated users has been proposed to improve turn-level, corpus-based metrics which can only evaluate test cases encountered in a corpus and cannot measure system’s ability to sustain multi-turn interactions.
no code implementations • 3 Feb 2024 • Atharva Kulkarni, Bo-Hsiang Tseng, Joel Ruben Antony Moniz, Dhivya Piraviperumal, Hong Yu, Shruti Bhargava
Remarkably, our few-shot learning approach recovers nearly $98%$ of the performance compared to the few-shot setup using human-annotated training data.
no code implementations • 1 Feb 2024 • YIlun Zhu, Joel Ruben Antony Moniz, Shruti Bhargava, Jiarui Lu, Dhivya Piraviperumal, Site Li, Yuan Zhang, Hong Yu, Bo-Hsiang Tseng
Understanding context is key to understanding human language, an ability which Large Language Models (LLMs) have been increasingly seen to demonstrate to an impressive extent.
no code implementations • 3 Nov 2023 • Halim Cagri Ates, Shruti Bhargava, Site Li, Jiarui Lu, Siddhardha Maddula, Joel Ruben Antony Moniz, Anil Kumar Nalamalapu, Roman Hoang Nguyen, Melis Ozyildirim, Alkesh Patel, Dhivya Piraviperumal, Vincent Renkens, Ankit Samal, Thy Tran, Bo-Hsiang Tseng, Hong Yu, Yuan Zhang, Rong Zou
Successfully handling context is essential for any dialog understanding task.
no code implementations • 23 Sep 2023 • Alexandru Coca, Bo-Hsiang Tseng, Jinghong Chen, Weizhe Lin, Weixuan Zhang, Tisha Anders, Bill Byrne
Schema-guided dialogue state trackers can generalise to new domains without further training, yet they are sensitive to the writing style of the schemata.
no code implementations • 2 Jun 2023 • Jiarui Lu, Bo-Hsiang Tseng, Joel Ruben Antony Moniz, Site Li, Xueyun Zhu, Hong Yu, Murat Akbacak
Providing voice assistants the ability to navigate multi-turn conversations is a challenging problem.
1 code implementation • ACL 2021 • Bo-Hsiang Tseng, Yinpei Dai, Florian Kreyssig, Bill Byrne
Our goal is to develop a modelling framework that can incorporate new dialogue scenarios through self-play between the two agents.
1 code implementation • NAACL 2021 • Bo-Hsiang Tseng, Shruti Bhargava, Jiarui Lu, Joel Ruben Antony Moniz, Dhivya Piraviperumal, Lin Li, Hong Yu
In this work, we propose a novel joint learning framework of modeling coreference resolution and query rewriting for complex, multi-turn dialogue understanding.
1 code implementation • EMNLP 2021 • Weizhe Lin, Bo-Hsiang Tseng, Bill Byrne
Dialogue State Tracking is central to multi-domain task-oriented dialogue systems, responsible for extracting information from user utterances.
Ranked #1 on
Multi-domain Dialogue State Tracking
on MULTIWOZ 2.0
no code implementations • Findings of the Association for Computational Linguistics 2020 • Yen-chen Wu, Bo-Hsiang Tseng, Milica Gasic
In order to improve the sample-efficiency of deep reinforcement learning (DRL), we implemented imagination augmented agent (I2A) in spoken dialogue systems (SDS).
1 code implementation • ACL 2020 • Bo-Hsiang Tseng, Jianpeng Cheng, Yimai Fang, David Vandyke
This approach allows us to explore both spaces of natural language and formal representations, and facilitates information sharing through the latent space to eventually benefit NLU and NLG.
Natural Language Understanding
Task-Oriented Dialogue Systems
+1
no code implementations • 26 Nov 2019 • Bo-Hsiang Tseng, Marek Rei, Paweł Budzianowski, Richard E. Turner, Bill Byrne, Anna Korhonen
Dialogue systems benefit greatly from optimizing on detailed annotations, such as transcribed utterances, internal dialogue state representations and dialogue act labels.
no code implementations • IJCNLP 2019 • Bo-Hsiang Tseng, Marek Rei, Pawe{\l} Budzianowski, Richard Turner, Bill Byrne, Anna Korhonen
Dialogue systems benefit greatly from optimizing on detailed annotations, such as transcribed utterances, internal dialogue state representations and dialogue act labels.
no code implementations • WS 2019 • Bo-Hsiang Tseng, Paweł Budzianowski, Yen-chen Wu, Milica Gašić
Domain adaptation in natural language generation (NLG) remains challenging because of the high complexity of input semantics across domains and limited data of a target domain.
no code implementations • WS 2018 • Stefan Ultes, Paweł\ Budzianowski, Iñigo Casanueva, Lina Rojas-Barahona, Bo-Hsiang Tseng, Yen-chen Wu, Steve Young, Milica Gašić
Statistical spoken dialogue systems usually rely on a single- or multi-domain dialogue model that is restricted in its capabilities of modelling complex dialogue structures, e. g., relations.
1 code implementation • WS 2018 • Bo-Hsiang Tseng, Florian Kreyssig, Pawel Budzianowski, Inigo Casanueva, Yen-chen Wu, Stefan Ultes, Milica Gasic
Cross-domain natural language generation (NLG) is still a difficult task within spoken dialogue modelling.
1 code implementation • EMNLP 2018 • Pawe{\l} Budzianowski, Tsung-Hsien Wen, Bo-Hsiang Tseng, I{\~n}igo Casanueva, Stefan Ultes, Osman Ramadan, Milica Ga{\v{s}}i{\'c}
Even though machine learning has become the major scene in dialogue research community, the real breakthrough has been blocked by the scale of data available. To address this fundamental obstacle, we introduce the Multi-Domain Wizard-of-Oz dataset (MultiWOZ), a fully-labeled collection of human-human written conversations spanning over multiple domains and topics. At a size of 10k dialogues, it is at least one order of magnitude larger than all previous annotated task-oriented corpora. The contribution of this work apart from the open-sourced dataset is two-fold:firstly, a detailed description of the data collection procedure along with a summary of data structure and analysis is provided.
5 code implementations • EMNLP 2018 • Paweł Budzianowski, Tsung-Hsien Wen, Bo-Hsiang Tseng, Iñigo Casanueva, Stefan Ultes, Osman Ramadan, Milica Gašić
Even though machine learning has become the major scene in dialogue research community, the real breakthrough has been blocked by the scale of data available.
1 code implementation • WS 2018 • Lina Rojas-Barahona, Bo-Hsiang Tseng, Yinpei Dai, Clare Mansfield, Osman Ramadan, Stefan Ultes, Michael Crawford, Milica Gasic
In recent years, we have seen deep learning and distributed representations of words and sentences make impact on a number of natural language processing tasks, such as similarity, entailment and sentiment analysis.
no code implementations • WS 2018 • I{\~n}igo Casanueva, Pawe{\l} Budzianowski, Stefan Ultes, Florian Kreyssig, Bo-Hsiang Tseng, Yen-chen Wu, Milica Ga{\v{s}}i{\'c}
Reinforcement learning (RL) is a promising dialogue policy optimisation approach, but traditional RL algorithms fail to scale to large domains.
no code implementations • 14 Jun 2018 • Lina M. Rojas-Barahona, Stefan Ultes, Pawel Budzianowski, Iñigo Casanueva, Milica Gasic, Bo-Hsiang Tseng, Steve Young
This paper presents two ways of dealing with scarce data in semantic decoding using N-Best speech recognition hypotheses.
no code implementations • NAACL 2018 • Iñigo Casanueva, Paweł Budzianowski, Pei-Hao Su, Stefan Ultes, Lina Rojas-Barahona, Bo-Hsiang Tseng, Milica Gašić
Reinforcement learning (RL) is a promising approach to solve dialogue policy optimisation.
no code implementations • 23 Aug 2016 • Bo-Hsiang Tseng, Sheng-syun Shen, Hung-Yi Lee, Lin-shan Lee
Multimedia or spoken content presents more attractive information than plain text content, but it's more difficult to display on a screen and be selected by a user.
no code implementations • 3 Jun 2015 • Bo-Hsiang Tseng, Hung-Yi Lee, Lin-shan Lee
With the popularity of mobile devices, personalized speech recognizer becomes more realizable today and highly attractive.