Zobrazeno 1 - 10
of 37
pro vyhledávání: '"Mrkšić, Nikola"'
Autor:
Vulić, Ivan, Su, Pei-Hao, Coope, Sam, Gerz, Daniela, Budzianowski, Paweł, Casanueva, Iñigo, Mrkšić, Nikola, Wen, Tsung-Hsien
Transformer-based language models (LMs) pretrained on large text collections are proven to store a wealth of semantic knowledge. However, 1) they are not effective as sentence encoders when used off-the-shelf, and 2) thus typically lag behind convers
Externí odkaz:
http://arxiv.org/abs/2109.10126
Autor:
Gerz, Daniela, Su, Pei-Hao, Kusztos, Razvan, Mondal, Avishek, Lis, Michał, Singhal, Eshan, Mrkšić, Nikola, Wen, Tsung-Hsien, Vulić, Ivan
We present a systematic study on multilingual and cross-lingual intent detection from spoken data. The study leverages a new resource put forth in this work, termed MInDS-14, a first training and evaluation resource for the intent detection task with
Externí odkaz:
http://arxiv.org/abs/2104.08524
Autor:
Mrkšić, Nikola
Spoken dialogue systems provide a natural conversational interface to computer applications. In recent years, the substantial improvements in the performance of speech recognition engines have helped shift the research focus to the next component of
Externí odkaz:
https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.744899
Autor:
Henderson, Matthew, Casanueva, Iñigo, Mrkšić, Nikola, Su, Pei-Hao, Wen, Tsung-Hsien, Vulić, Ivan
General-purpose pretrained sentence encoders such as BERT are not ideal for real-world conversational AI applications; they are computationally heavy, slow, and expensive to train. We propose ConveRT (Conversational Representations from Transformers)
Externí odkaz:
http://arxiv.org/abs/1911.03688
Autor:
Henderson, Matthew, Vulić, Ivan, Casanueva, Iñigo, Budzianowski, Paweł, Gerz, Daniela, Coope, Sam, Spithourakis, Georgios, Wen, Tsung-Hsien, Mrkšić, Nikola, Su, Pei-Hao
We present PolyResponse, a conversational search engine that supports task-oriented dialogue. It is a retrieval-based approach that bypasses the complex multi-component design of traditional task-oriented dialogue systems and the use of explicit sema
Externí odkaz:
http://arxiv.org/abs/1909.01296
Autor:
Henderson, Matthew, Vulić, Ivan, Gerz, Daniela, Casanueva, Iñigo, Budzianowski, Paweł, Coope, Sam, Spithourakis, Georgios, Wen, Tsung-Hsien, Mrkšić, Nikola, Su, Pei-Hao
Despite their popularity in the chatbot literature, retrieval-based models have had modest impact on task-oriented dialogue systems, with the main obstacle to their application being the low-data regime of most task-oriented dialogue tasks. Inspired
Externí odkaz:
http://arxiv.org/abs/1906.01543
Autor:
Henderson, Matthew, Budzianowski, Paweł, Casanueva, Iñigo, Coope, Sam, Gerz, Daniela, Kumar, Girish, Mrkšić, Nikola, Spithourakis, Georgios, Su, Pei-Hao, Vulić, Ivan, Wen, Tsung-Hsien
Publikováno v:
Proceedings of the Workshop on NLP for Conversational AI (2019)
Progress in Machine Learning is often driven by the availability of large datasets, and consistent evaluation metrics for comparing modeling approaches. To this end, we present a repository of conversational datasets consisting of hundreds of million
Externí odkaz:
http://arxiv.org/abs/1904.06472
Semantic specialization is the process of fine-tuning pre-trained distributional word vectors using external lexical knowledge (e.g., WordNet) to accentuate a particular semantic relation in the specialized vector space. While post-processing special
Externí odkaz:
http://arxiv.org/abs/1809.04163
Autor:
Mrkšić, Nikola, Vulić, Ivan
This paper proposes an improvement to the existing data-driven Neural Belief Tracking (NBT) framework for Dialogue State Tracking (DST). The existing NBT model uses a hand-crafted belief state update mechanism which involves an expensive manual retun
Externí odkaz:
http://arxiv.org/abs/1805.11350
Word vector specialisation (also known as retrofitting) is a portable, light-weight approach to fine-tuning arbitrary distributional word vector spaces by injecting external knowledge from rich lexical resources such as WordNet. By design, these post
Externí odkaz:
http://arxiv.org/abs/1805.03228