Search Results for author: Milica Gašić

Found 34 papers, 7 papers with code

Speech-based Slot Filling using Large Language Models

no code implementations13 Nov 2023 Guangzhi Sun, Shutong Feng, Dongcheng Jiang, Chao Zhang, Milica Gašić, Philip C. Woodland

Recently, advancements in large language models (LLMs) have shown an unprecedented ability across various language tasks.

In-Context Learning slot-filling +1

CAMELL: Confidence-based Acquisition Model for Efficient Self-supervised Active Learning with Label Validation

no code implementations13 Oct 2023 Carel van Niekerk, Christian Geishauser, Michael Heck, Shutong Feng, Hsien-Chin Lin, Nurul Lubis, Benjamin Ruppik, Renato Vukovic, Milica Gašić

Supervised neural approaches are hindered by their dependence on large, meticulously annotated datasets, a requirement that is particularly cumbersome for sequential tasks.

Active Learning

Affect Recognition in Conversations Using Large Language Models

no code implementations22 Sep 2023 Shutong Feng, Guangzhi Sun, Nurul Lubis, Chao Zhang, Milica Gašić

This study delves into the capacity of large language models (LLMs) to recognise human affect in conversations, with a focus on both open-domain chit-chat dialogues and task-oriented dialogues.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

EmoUS: Simulating User Emotions in Task-Oriented Dialogues

no code implementations2 Jun 2023 Hsien-Chin Lin, Shutong Feng, Christian Geishauser, Nurul Lubis, Carel van Niekerk, Michael Heck, Benjamin Ruppik, Renato Vukovic, Milica Gašić

Existing user simulators (USs) for task-oriented dialogue systems only model user behaviour on semantic and natural language levels without considering the user persona and emotions.

Language Modelling Large Language Model +1

Dialogue Term Extraction using Transfer Learning and Topological Data Analysis

no code implementations SIGDIAL (ACL) 2022 Renato Vukovic, Michael Heck, Benjamin Matthias Ruppik, Carel van Niekerk, Marcus Zibrowius, Milica Gašić

Goal oriented dialogue systems were originally designed as a natural language interface to a fixed data-set of entities that users might inquire about, further described by domain, slots, and values.

Goal-Oriented Dialogue Systems Language Modelling +4

Robust Dialogue State Tracking with Weak Supervision and Sparse Data

no code implementations7 Feb 2022 Michael Heck, Nurul Lubis, Carel van Niekerk, Shutong Feng, Christian Geishauser, Hsien-Chin Lin, Milica Gašić

Our architecture and training strategies improve robustness towards sample sparsity, new concepts and topics, leading to state-of-the-art performance on a range of benchmarks.

Dialogue State Tracking

LAVA: Latent Action Spaces via Variational Auto-encoding for Dialogue Policy Optimization

1 code implementation COLING 2020 Nurul Lubis, Christian Geishauser, Michael Heck, Hsien-Chin Lin, Marco Moresi, Carel van Niekerk, Milica Gašić

In this paper, we explore three ways of leveraging an auxiliary task to shape the latent variable distribution: via pre-training, to obtain an informed prior, and via multitask learning.

Decision Making Reinforcement Learning (RL) +1

Topology of Word Embeddings: Singularities Reflect Polysemy

no code implementations Joint Conference on Lexical and Computational Semantics 2020 Alexander Jakubowski, Milica Gašić, Marcus Zibrowius

We argue that we should, more accurately, expect them to live on a pinched manifold: a singular quotient of a manifold obtained by identifying some of its points.

Word Embeddings Word Sense Induction

Tree-Structured Semantic Encoder with Knowledge Sharing for Domain Adaptation in Natural Language Generation

no code implementations WS 2019 Bo-Hsiang Tseng, Paweł Budzianowski, Yen-chen Wu, Milica Gašić

Domain adaptation in natural language generation (NLG) remains challenging because of the high complexity of input semantics across domains and limited data of a target domain.

Domain Adaptation Informativeness +1

Addressing Objects and Their Relations: The Conversational Entity Dialogue Model

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.

Spoken Dialogue Systems

MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling

5 code implementations EMNLP 2018 Paweł Budzianowski, Tsung-Hsien Wen, Bo-Hsiang Tseng, Iñigo Casanueva, Stefan Ultes, Osman Ramadan, Milica Gašić

Even though machine learning has become the major scene in dialogue research community, the real breakthrough has been blocked by the scale of data available.

Response Generation

Sample Efficient Deep Reinforcement Learning for Dialogue Systems with Large Action Spaces

no code implementations11 Feb 2018 Gellért Weisz, Paweł Budzianowski, Pei-Hao Su, Milica Gašić

A part of this effort is the policy optimisation task, which attempts to find a policy describing how to respond to humans, in the form of a function taking the current state of the dialogue and returning the response of the system.

reinforcement-learning Reinforcement Learning (RL) +1

Uncertainty Estimates for Efficient Neural Network-based Dialogue Policy Optimisation

no code implementations30 Nov 2017 Christopher Tegho, Paweł Budzianowski, Milica Gašić

This paper examines approaches to extract uncertainty estimates from deep Q-networks (DQN) in the context of dialogue management.

Dialogue Management Efficient Exploration +2

Counter-fitting Word Vectors to Linguistic Constraints

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.

Dialogue State Tracking Semantic Similarity +1

Cannot find the paper you are looking for? You can Submit a new open access paper.