Pei-Hao Su

Publication Activity (10 Years)

Years Active: 2015-2021
Publications (10 Years): 41

Top Topics

Language Generation

Reinforcement Learning

Dialogue System

Top Venues

SIGDIAL Conference

Publications

Ivan Vulic, Pei-Hao Su, Sam Coope, Daniela Gerz, Pawel Budzianowski, Iñigo Casanueva, Nikola Mrksic, Tsung-Hsien Wen
ConvFiT: Conversational Fine-Tuning of Pretrained Language Models. CoRR (2021)
Daniela Gerz, Pei-Hao Su, Razvan Kusztos, Avishek Mondal, Michal Lis, Eshan Singhal, Nikola Mrksic, Tsung-Hsien Wen, Ivan Vulic
Multilingual and Cross-Lingual Intent Detection from Spoken Data. EMNLP (1) (2021)
Daniela Gerz, Pei-Hao Su, Razvan Kusztos, Avishek Mondal, Michal Lis, Eshan Singhal, Nikola Mrksic, Tsung-Hsien Wen, Ivan Vulic
Multilingual and Cross-Lingual Intent Detection from Spoken Data. CoRR (2021)
Ivan Vulic, Pei-Hao Su, Samuel Coope, Daniela Gerz, Pawel Budzianowski, Iñigo Casanueva, Nikola Mrksic, Tsung-Hsien Wen
ConvFiT: Conversational Fine-Tuning of Pretrained Language Models. EMNLP (1) (2021)
Matthew Henderson, Iñigo Casanueva, Nikola Mrksic, Pei-Hao Su, Tsung-Hsien Wen, Ivan Vulic
ConveRT: Efficient and Accurate Conversational Representations from Transformers. EMNLP (Findings) (2020)
Matthew Henderson, Pawel Budzianowski, Iñigo Casanueva, Sam Coope, Daniela Gerz, Girish Kumar, Nikola Mrksic, Georgios Spithourakis, Pei-Hao Su, Ivan Vulic, Tsung-Hsien Wen
A Repository of Conversational Datasets. CoRR (2019)
Matthew Henderson, Ivan Vulic, Iñigo Casanueva, Pawel Budzianowski, Daniela Gerz, Sam Coope, Georgios Spithourakis, Tsung-Hsien Wen, Nikola Mrksic, Pei-Hao Su
PolyResponse: A Rank-based Approach to Task-Oriented Dialogue with Application in Restaurant Search and Booking. CoRR (2019)
Matthew Henderson, Ivan Vulic, Daniela Gerz, Iñigo Casanueva, Pawel Budzianowski, Sam Coope, Georgios Spithourakis, Tsung-Hsien Wen, Nikola Mrksic, Pei-Hao Su
Training Neural Response Selection for Task-Oriented Dialogue Systems. CoRR (2019)
Matthew Henderson, Ivan Vulic, Iñigo Casanueva, Pawel Budzianowski, Daniela Gerz, Sam Coope, Georgios Spithourakis, Tsung-Hsien Wen, Nikola Mrksic, Pei-Hao Su
PolyResponse: A Rank-based Approach to Task-Oriented Dialogue with Application in Restaurant Search and Booking. EMNLP/IJCNLP (3) (2019)
Matthew Henderson, Ivan Vulic, Daniela Gerz, Iñigo Casanueva, Pawel Budzianowski, Sam Coope, Georgios Spithourakis, Tsung-Hsien Wen, Nikola Mrksic, Pei-Hao Su
Training Neural Response Selection for Task-Oriented Dialogue Systems. ACL (1) (2019)
Tsung-Hsien Wen, Pei-Hao Su, Pawel Budzianowski, Iñigo Casanueva, Ivan Vulic
Data Collection and End-to-End Learning for Conversational AI. EMNLP/IJCNLP (2) (2019)
Matthew Henderson, Iñigo Casanueva, Nikola Mrksic, Pei-Hao Su, Tsung-Hsien Wen, Ivan Vulic
ConveRT: Efficient and Accurate Conversational Representations from Transformers. CoRR (2019)
Pei-Hao Su, Nikola Mrksic, Iñigo Casanueva, Ivan Vulic
Deep Learning for Conversational AI. NAACL-HLT (Tutorial Abstracts) (2018)
Gellért Weisz, Pawel Budzianowski, Pei-Hao Su, Milica Gasic
Sample Efficient Deep Reinforcement Learning for Dialogue Systems With Large Action Spaces. IEEE ACM Trans. Audio Speech Lang. Process. 26 (11) (2018)
Gellért Weisz, Pawel Budzianowski, Pei-Hao Su, Milica Gasic
Sample Efficient Deep Reinforcement Learning for Dialogue Systems with Large Action Spaces. CoRR (2018)
Iñigo Casanueva, Pawel Budzianowski, Pei-Hao Su, Stefan Ultes, Lina Maria Rojas-Barahona, Bo-Hsiang Tseng, Milica Gasic
Feudal Reinforcement Learning for Dialogue Management in Large Domains. CoRR (2018)
Iñigo Casanueva, Pawel Budzianowski, Pei-Hao Su, Stefan Ultes, Lina Maria Rojas-Barahona, Bo-Hsiang Tseng, Milica Gasic
Feudal Reinforcement Learning for Dialogue Management in Large Domains. NAACL-HLT (2) (2018)
Pei-Hao Su, Milica Gasic, Steve J. Young
Reward estimation for dialogue policy optimisation. Comput. Speech Lang. 51 (2018)
Stefan Ultes, Pawel Budzianowski, Iñigo Casanueva, Nikola Mrksic, Lina Maria Rojas-Barahona, Pei-Hao Su, Tsung-Hsien Wen, Milica Gasic, Steve J. Young
Reward-Balancing for Statistical Spoken Dialogue Systems using Multi-objective Reinforcement Learning. SIGDIAL Conference (2017)
Pawel Budzianowski, Stefan Ultes, Pei-Hao Su, Nikola Mrksic, Tsung-Hsien Wen, Iñigo Casanueva, Lina Maria Rojas-Barahona, Milica Gasic
Sub-domain Modelling for Dialogue Management with Hierarchical Reinforcement Learning. SIGDIAL Conference (2017)
Pei-Hao Su, Pawel Budzianowski, Stefan Ultes, Milica Gasic, Steve J. Young
Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management. SIGDIAL Conference (2017)
Stefan Ultes, Pawel Budzianowski, Iñigo Casanueva, Nikola Mrksic, Lina Maria Rojas-Barahona, Pei-Hao Su, Tsung-Hsien Wen, Milica Gasic, Steve J. Young
Reward-Balancing for Statistical Spoken Dialogue Systems using Multi-objective Reinforcement Learning. CoRR (2017)
Stefan Ultes, Pawel Budzianowski, Iñigo Casanueva, Nikola Mrksic, Lina Maria Rojas-Barahona, Pei-Hao Su, Tsung-Hsien Wen, Milica Gasic, Steve J. Young
Domain-Independent User Satisfaction Reward Estimation for Dialogue Policy Learning. INTERSPEECH (2017)
Iñigo Casanueva, Pawel Budzianowski, Pei-Hao Su, Nikola Mrksic, Tsung-Hsien Wen, Stefan Ultes, Lina Maria Rojas-Barahona, Steve J. Young, Milica Gasic
A Benchmarking Environment for Reinforcement Learning Based Task Oriented Dialogue Management. CoRR (2017)
Milica Gasic, Nikola Mrksic, Lina Maria Rojas-Barahona, Pei-Hao Su, Stefan Ultes, David Vandyke, Tsung-Hsien Wen, Steve J. Young
Dialogue manager domain adaptation using Gaussian process reinforcement learning. Comput. Speech Lang. 45 (2017)
Tsung-Hsien Wen, David Vandyke, Nikola Mrksic, Milica Gasic, Lina Maria Rojas-Barahona, Pei-Hao Su, Stefan Ultes, Steve J. Young
A Network-based End-to-End Trainable Task-oriented Dialogue System. EACL (1) (2017)
Stefan Ultes, Lina Maria Rojas-Barahona, Pei-Hao Su, David Vandyke, Dongho Kim, Iñigo Casanueva, Pawel Budzianowski, Nikola Mrksic, Tsung-Hsien Wen, Milica Gasic, Steve J. Young
PyDial: A Multi-domain Statistical Dialogue System Toolkit. ACL (System Demonstrations) (2017)
Pei-Hao Su, Pawel Budzianowski, Stefan Ultes, Milica Gasic, Steve J. Young
Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management. CoRR (2017)
Pawel Budzianowski, Stefan Ultes, Pei-Hao Su, Nikola Mrksic, Tsung-Hsien Wen, Iñigo Casanueva, Lina Maria Rojas-Barahona, Milica Gasic
Sub-domain Modelling for Dialogue Management with Hierarchical Reinforcement Learning. CoRR (2017)
Lina Maria Rojas-Barahona, Milica Gasic, Nikola Mrksic, Pei-Hao Su, Stefan Ultes, Tsung-Hsien Wen, Steve J. Young
Exploiting Sentence and Context Representations in Deep Neural Models for Spoken Language Understanding. COLING (2016)
Nikola Mrksic, Diarmuid Ó Séaghdha, Blaise Thomson, Milica Gasic, Lina Maria Rojas-Barahona, Pei-Hao Su, David Vandyke, Tsung-Hsien Wen, Steve J. Young
Counter-fitting Word Vectors to Linguistic Constraints. HLT-NAACL (2016)
Tsung-Hsien Wen, Milica Gasic, Nikola Mrksic, Lina Maria Rojas-Barahona, Pei-Hao Su, David Vandyke, Steve J. Young
Multi-domain Neural Network Language Generation for Spoken Dialogue Systems. HLT-NAACL (2016)
Tsung-Hsien Wen, Milica Gasic, Nikola Mrksic, Lina Maria Rojas-Barahona, Pei-Hao Su, Stefan Ultes, David Vandyke, Steve J. Young
Conditional Generation and Snapshot Learning in Neural Dialogue Systems. CoRR (2016)
Nikola Mrksic, Diarmuid Ó Séaghdha, Blaise Thomson, Milica Gasic, Lina Maria Rojas-Barahona, Pei-Hao Su, David Vandyke, Tsung-Hsien Wen, Steve J. Young
Counter-fitting Word Vectors to Linguistic Constraints. CoRR (2016)
Lina Maria Rojas-Barahona, Milica Gasic, Nikola Mrksic, Pei-Hao Su, Stefan Ultes, Tsung-Hsien Wen, Steve J. Young
Exploiting Sentence and Context Representations in Deep Neural Models for Spoken Language Understanding. CoRR (2016)
Tsung-Hsien Wen, Milica Gasic, Nikola Mrksic, Lina Maria Rojas-Barahona, Pei-Hao Su, Stefan Ultes, David Vandyke, Steve J. Young
A Network-based End-to-End Trainable Task-oriented Dialogue System. CoRR (2016)
Pei-Hao Su, Milica Gasic, Nikola Mrksic, Lina Maria Rojas-Barahona, Stefan Ultes, David Vandyke, Tsung-Hsien Wen, Steve J. Young
On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems. CoRR (2016)
Pei-Hao Su, Milica Gasic, Nikola Mrksic, Lina Maria Rojas-Barahona, Stefan Ultes, David Vandyke, Tsung-Hsien Wen, Steve J. Young
Continuously Learning Neural Dialogue Management. CoRR (2016)
Milica Gasic, Nikola Mrksic, Lina Maria Rojas-Barahona, Pei-Hao Su, Stefan Ultes, David Vandyke, Tsung-Hsien Wen, Steve J. Young
Dialogue manager domain adaptation using Gaussian process reinforcement learning. CoRR (2016)
Pei-Hao Su, Milica Gasic, Nikola Mrksic, Lina Maria Rojas-Barahona, Stefan Ultes, David Vandyke, Tsung-Hsien Wen, Steve J. Young
On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems. ACL (1) (2016)
Tsung-Hsien Wen, Milica Gasic, Nikola Mrksic, Lina Maria Rojas-Barahona, Pei-Hao Su, Stefan Ultes, David Vandyke, Steve J. Young
Conditional Generation and Snapshot Learning in Neural Dialogue Systems. EMNLP (2016)
Lu Chen, Pei-Hao Su, Milica Gasic
Hyper-parameter Optimisation of Gaussian Process Reinforcement Learning for Statistical Dialogue Management. SIGDIAL Conference (2015)
Pei-Hao Su, David Vandyke, Milica Gasic, Nikola Mrksic, Tsung-Hsien Wen, Steve J. Young
Reward Shaping with Recurrent Neural Networks for Speeding up On-Line Policy Learning in Spoken Dialogue Systems. SIGDIAL Conference (2015)
Zhuoran Wang, Tsung-Hsien Wen, Pei-Hao Su, Yannis Stylianou
Learning Domain-Independent Dialogue Policies via Ontology Parameterisation. SIGDIAL Conference (2015)
Tsung-Hsien Wen, Milica Gasic, Dongho Kim, Nikola Mrksic, Pei-Hao Su, David Vandyke, Steve J. Young
Stochastic Language Generation in Dialogue using Recurrent Neural Networks with Convolutional Sentence Reranking. SIGDIAL Conference (2015)