activity
20172022
most citedTraining Neural Response Selection for Task-Oriented Dialogue Systems

55 citations · 72 across the 10 of their papers we have counts for

collaborators

17 papers

cs.CL20222 cited

NLU++: A Multi-Label, Slot-Rich, Generalisable Dataset for Natural Language Understanding in Task-Oriented Dialogue

Iñigo Casanueva, Ivan Vulić, Georgios P. Spithourakis +1

We present NLU++, a novel dataset for natural language understanding (NLU) in task-oriented dialogue (ToD) systems, with the aim to provide a much more challenging evaluation envir…

cs.CL2022

EVI: Multilingual Spoken Dialogue Tasks and Dataset for Knowledge-Based Enrolment, Verification, and Identification

Georgios P. Spithourakis, Ivan Vulić, Michał Lis +2

Knowledge-based authentication is crucial for task-oriented spoken dialogue systems that offer personalised and privacy-focused services. Such systems should be able to enrol (E),…

cs.CL20225 cited

Improved and Efficient Conversational Slot Labeling through Question Answering

Gabor Fuisz, Ivan Vulić, Samuel Gibbons +2

Transformer-based pretrained language models (PLMs) offer unmatched performance across the majority of natural language understanding (NLU) tasks, including a body of question answ…

cs.CL20211 cited

ConvFiT: Conversational Fine-Tuning of Pretrained Language Models

Ivan Vulić, Pei-Hao Su, Sam Coope +5

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 enco…

cs.CL2020

Efficient Intent Detection with Dual Sentence Encoders

Iñigo Casanueva, Tadas Temčinas, Daniela Gerz +2

Building conversational systems in new domains and with added functionality requires resource-efficient models that work under low-data regimes (i.e., in few-shot setups). Motivate…

cs.CL2019

ConveRT: Efficient and Accurate Conversational Representations from Transformers

Matthew Henderson, Iñigo Casanueva, Nikola Mrkšić +3

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.…