L
Lina Maria Rojas-Barahona
Researcher at University of Cambridge
Publications - 53
Citations - 2887
Lina Maria Rojas-Barahona is an academic researcher from University of Cambridge. The author has contributed to research in topics: Reinforcement learning & Computer science. The author has an hindex of 19, co-authored 45 publications receiving 2335 citations. Previous affiliations of Lina Maria Rojas-Barahona include University of Pavia.
Papers
More filters
Proceedings ArticleDOI
A Network-based End-to-End Trainable Task-oriented Dialogue System
Tsung-Hsien Wen,David Vandyke,Nikola Mrkšić,Milica Gasic,Lina Maria Rojas-Barahona,Pei-Hao Su,Stefan Ultes,Steve Young +7 more
TL;DR: The authors introduced a neural network-based text-in, text-out end-to-end trainable goal-oriented dialogue system along with a new way of collecting dialogue data based on a novel pipe-lined Wizard-of-Oz framework.
Proceedings ArticleDOI
Counter-fitting word vectors to linguistic constraints
Nikola Mrkšić,Diarmuid Ó Séaghdha,Blaise Thomson,Milica Gasic,Lina Maria Rojas-Barahona,Pei-Hao Su,David Vandyke,Tsung-Hsien Wen,Steve Young +8 more
TL;DR: The authors injects antonymy and synonymy constraints into vector space representations in order to improve the vectors' capability for judging semantic similarity, leading to a new state-of-the-art performance on the SimLex-999 dataset.
Posted Content
A Network-based End-to-End Trainable Task-oriented Dialogue System
Tsung-Hsien Wen,David Vandyke,Nikola Mrkšić,Milica Gasic,Lina Maria Rojas-Barahona,Pei-Hao Su,Stefan Ultes,Steve Young +7 more
TL;DR: This article introduced a neural network-based text-in, text-out end-to-end trainable goal-oriented dialogue system along with a new way of collecting dialogue data based on a novel pipe-lined Wizard-of-Oz framework.
Proceedings ArticleDOI
Multi-domain Neural Network Language Generation for Spoken Dialogue Systems
Tsung-Hsien Wen,Milica Gasic,Nikola Mrkšić,Lina Maria Rojas-Barahona,Pei-Hao Su,David Vandyke,Steve Young +6 more
TL;DR: This paper proposes a procedure to train multi-domain, Recurrent Neural Network-based (RNN) language generators via multiple adaptation steps, and shows that the proposed procedure can achieve competitive performance in terms of BLEU score and slot error rate while significantly reducing the data needed to train generators in new, unseen domains.
Proceedings ArticleDOI
PyDial: A Multi-domain Statistical Dialogue System Toolkit
Stefan Ultes,Lina Maria Rojas-Barahona,Pei-Hao Su,David Vandyke,Dongho Kim,Iñigo Casanueva,Paweł Budzianowski,Nikola Mrkšić,Tsung-Hsien Wen,Milica Gasic,Steve Young +10 more
TL;DR: PyDial is an opensource end-to-end statistical spoken dialogue system toolkit which provides implementations of statistical approaches for all dialogue system modules and has been extended to provide multidomain conversational functionality.