no code implementations • 3 Dec 2019 • Octavia-Maria Sulea, Steve Young
The use of Deep Neural Network architectures for Language Modeling has recently seen a tremendous increase in interest in the field of NLP with the advent of transfer learning and the shift in focus from rule-based and predictive models (supervised learning) to generative or unsupervised models to solve the long-standing problems in NLP like Information Extraction or Question Answering.
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.
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 • 29 Nov 2017 • Iñigo Casanueva, Paweł Budzianowski, Pei-Hao Su, Nikola Mrkšić, Tsung-Hsien Wen, Stefan Ultes, Lina Rojas-Barahona, Steve Young, Milica Gašić
Dialogue assistants are rapidly becoming an indispensable daily aid.
no code implementations • WS 2017 • Kyusong Lee, Tiancheng Zhao, Yulun Du, Edward Cai, Allen Lu, Eli Pincus, David Traum, Stefan Ultes, Lina M. Rojas-Barahona, Milica Gasic, Steve Young, Maxine Eskenazi
DialPort collects user data for connected spoken dialog systems.
no code implementations • WS 2017 • Stefan Ultes, Paweł Budzianowski, Iñigo Casanueva, Nikola Mrkšić, Lina Rojas-Barahona, Pei-Hao Su, Tsung-Hsien Wen, Milica Gašić, Steve Young
Reinforcement learning is widely used for dialogue policy optimization where the reward function often consists of more than one component, e. g., the dialogue success and the dialogue length.
Multi-Objective Reinforcement Learning reinforcement-learning +1
no code implementations • WS 2017 • Pei-Hao Su, Pawel Budzianowski, Stefan Ultes, Milica Gasic, Steve Young
Firstly, to speed up the learning process, two sample-efficient neural networks algorithms: trust region actor-critic with experience replay (TRACER) and episodic natural actor-critic with experience replay (eNACER) are presented.
2 code implementations • 1 Jun 2017 • Nikola Mrkšić, Ivan Vulić, Diarmuid Ó Séaghdha, Ira Leviant, Roi Reichart, Milica Gašić, Anna Korhonen, Steve Young
We present Attract-Repel, an algorithm for improving the semantic quality of word vectors by injecting constraints extracted from lexical resources.
no code implementations • ACL 2017 • Ivan Vulić, Nikola Mrkšić, Roi Reichart, Diarmuid Ó Séaghdha, Steve Young, Anna Korhonen
Morphologically rich languages accentuate two properties of distributional vector space models: 1) the difficulty of inducing accurate representations for low-frequency word forms; and 2) insensitivity to distinct lexical relations that have similar distributional signatures.
1 code implementation • ICML 2017 • Tsung-Hsien Wen, Yishu Miao, Phil Blunsom, Steve Young
Developing a dialogue agent that is capable of making autonomous decisions and communicating by natural language is one of the long-term goals of machine learning research.
no code implementations • TACL 2017 • Nikola Mrk{\v{s}}i{\'c}, Ivan Vuli{\'c}, Diarmuid {\'O} S{\'e}aghdha, Ira Leviant, Roi Reichart, Milica Ga{\v{s}}i{\'c}, Anna Korhonen, Steve Young
We present Attract-Repel, an algorithm for improving the semantic quality of word vectors by injecting constraints extracted from lexical resources.
no code implementations • COLING 2016 • Lina M. Rojas Barahona, Milica Gasic, Nikola Mrkšić, Pei-Hao Su, Stefan Ultes, Tsung-Hsien Wen, Steve Young
This paper presents a deep learning architecture for the semantic decoder component of a Statistical Spoken Dialogue System.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +7
no code implementations • 9 Sep 2016 • Milica Gasic, Nikola Mrksic, Lina M. Rojas-Barahona, Pei-Hao Su, Stefan Ultes, David Vandyke, Tsung-Hsien Wen, Steve Young
Spoken dialogue systems allow humans to interact with machines using natural speech.
no code implementations • ACL 2017 • Nikola Mrkšić, Diarmuid Ó Séaghdha, Tsung-Hsien Wen, Blaise Thomson, Steve Young
One of the core components of modern spoken dialogue systems is the belief tracker, which estimates the user's goal at every step of the dialogue.
no code implementations • EMNLP 2016 • Tsung-Hsien Wen, Milica Gasic, Nikola Mrksic, Lina M. Rojas-Barahona, Pei-Hao Su, Stefan Ultes, David Vandyke, Steve Young
Recently a variety of LSTM-based conditional language models (LM) have been applied across a range of language generation tasks.
no code implementations • 8 Jun 2016 • Pei-Hao Su, Milica Gasic, Nikola Mrksic, Lina Rojas-Barahona, Stefan Ultes, David Vandyke, Tsung-Hsien Wen, Steve Young
We describe a two-step approach for dialogue management in task-oriented spoken dialogue systems.
no code implementations • ACL 2016 • Pei-Hao Su, Milica Gasic, Nikola Mrksic, Lina Rojas-Barahona, Stefan Ultes, David Vandyke, Tsung-Hsien Wen, Steve Young
The ability to compute an accurate reward function is essential for optimising a dialogue policy via reinforcement learning.
no code implementations • LREC 2016 • Mahmoud El-Haj, Paul Rayson, Steve Young, Andrew Moore, Martin Walker, Thomas Schleicher, Vasiliki Athanasakou
Previous studies have only applied manual content analysis on a small scale to reveal such a bias in the narrative section of annual financial reports.
1 code implementation • EACL 2017 • Tsung-Hsien Wen, David Vandyke, Nikola Mrksic, Milica Gasic, Lina M. Rojas-Barahona, Pei-Hao Su, Stefan Ultes, Steve Young
Teaching machines to accomplish tasks by conversing naturally with humans is challenging.
no code implementations • NAACL 2016 • Tsung-Hsien Wen, Milica Gasic, Nikola Mrksic, Lina M. Rojas-Barahona, Pei-Hao Su, David Vandyke, Steve Young
Moving from limited-domain natural language generation (NLG) to open domain is difficult because the number of semantic input combinations grows exponentially with the number of domains.
2 code implementations • NAACL 2016 • Nikola Mrkšić, Diarmuid Ó Séaghdha, Blaise Thomson, Milica Gašić, Lina Rojas-Barahona, Pei-Hao Su, David Vandyke, Tsung-Hsien Wen, Steve Young
In this work, we present a novel counter-fitting method which injects antonymy and synonymy constraints into vector space representations in order to improve the vectors' capability for judging semantic similarity.
no code implementations • WS 2015 • Pei-Hao Su, David Vandyke, Milica Gasic, Nikola Mrksic, Tsung-Hsien Wen, Steve Young
Reward shaping is one promising technique for addressing these concerns.
no code implementations • 13 Aug 2015 • Pei-Hao Su, David Vandyke, Milica Gasic, Dongho Kim, Nikola Mrksic, Tsung-Hsien Wen, Steve Young
The models are trained on dialogues generated by a simulated user and the best model is then used to train a policy on-line which is shown to perform at least as well as a baseline system using prior knowledge of the user's task.
2 code implementations • EMNLP 2015 • Tsung-Hsien Wen, Milica Gasic, Nikola Mrksic, Pei-Hao Su, David Vandyke, Steve Young
Natural language generation (NLG) is a critical component of spoken dialogue and it has a significant impact both on usability and perceived quality.
no code implementations • WS 2015 • Tsung-Hsien Wen, Milica Gasic, Dongho Kim, Nikola Mrksic, Pei-Hao Su, David Vandyke, Steve Young
The natural language generation (NLG) component of a spoken dialogue system (SDS) usually needs a substantial amount of handcrafting or a well-labeled dataset to be trained on.
no code implementations • IJCNLP 2015 • Nikola Mrkšić, Diarmuid Ó Séaghdha, Blaise Thomson, Milica Gašić, Pei-Hao Su, David Vandyke, Tsung-Hsien Wen, Steve Young
Dialog state tracking is a key component of many modern dialog systems, most of which are designed with a single, well-defined domain in mind.
no code implementations • WS 2014 • Helen Hastie, Marie-Aude Aufaure, Panos Alexopoulos, Hugues Bouchard, Catherine Breslin, Heriberto Cuay{\'a}huitl, Nina Dethlefs, Milica Ga{\v{s}}i{\'c}, James Henderson, Oliver Lemon, Xingkun Liu, Peter Mika, Nesrine Ben Mustapha, Tim Potter, Verena Rieser, Blaise Thomson, Pirros Tsiakoulis, Yves Vanrompay, Boris Villazon-Terrazas, Majid Yazdani, Steve Young, Yanchao Yu
no code implementations • LREC 2014 • Mahmoud El-Haj, Paul Rayson, Steve Young, Martin Walker
In this paper we present the evaluation of our automatic methods for detecting and extracting document structure in annual financial reports.