Search Results for author: Arash Eshghi

Found 31 papers, 8 papers with code

Combine to Describe: Evaluating Compositional Generalization in Image Captioning

no code implementations ACL 2022 George Pantazopoulos, Alessandro Suglia, Arash Eshghi

Compositionality – the ability to combine simpler concepts to understand & generate arbitrarily more complex conceptual structures – has long been thought to be the cornerstone of human language capacity.

Image Captioning

Incremental Graph-Based Semantics and Reasoning for Conversational AI

no code implementations ReInAct 2021 Angus Addlesee, Arash Eshghi

The next generation of conversational AI systems need to: (1) process language incrementally, token-by-token to be more responsive and enable handling of conversational phenomena such as pauses, restarts and self-corrections; (2) reason incrementally allowing meaning to be established beyond what is said; (3) be transparent and controllable, allowing designers as well as the system itself to easily establish reasons for particular behaviour and tailor to particular user groups, or domains.

Dialogue Act and Slot Recognition in Italian Complex Dialogues

no code implementations EURALI (LREC) 2022 Irene Sucameli, Michele De Quattro, Arash Eshghi, Alessandro Suglia, Maria Simi

Since the advent of Transformer-based, pretrained language models (LM) such as BERT, Natural Language Understanding (NLU) components in the form of Dialogue Act Recognition (DAR) and Slot Recognition (SR) for dialogue systems have become both more accurate and easier to create for specific application domains.

Natural Language Understanding

Multitask Multimodal Prompted Training for Interactive Embodied Task Completion

no code implementations7 Nov 2023 Georgios Pantazopoulos, Malvina Nikandrou, Amit Parekh, Bhathiya Hemanthage, Arash Eshghi, Ioannis Konstas, Verena Rieser, Oliver Lemon, Alessandro Suglia

Interactive and embodied tasks pose at least two fundamental challenges to existing Vision & Language (VL) models, including 1) grounding language in trajectories of actions and observations, and 2) referential disambiguation.

Text Generation

Learning to generate and corr- uh I mean repair language in real-time

1 code implementation22 Aug 2023 Arash Eshghi, Arash Ashrafzadeh

We further do a zero-shot evaluation of the ability of the same model to generate self-repairs when the generation goal changes mid-utterance.

'What are you referring to?' Evaluating the Ability of Multi-Modal Dialogue Models to Process Clarificational Exchanges

1 code implementation28 Jul 2023 Javier Chiyah-Garcia, Alessandro Suglia, Arash Eshghi, Helen Hastie

Referential ambiguities arise in dialogue when a referring expression does not uniquely identify the intended referent for the addressee.

Referring Expression

Exploring Multi-Modal Representations for Ambiguity Detection & Coreference Resolution in the SIMMC 2.0 Challenge

2 code implementations25 Feb 2022 Javier Chiyah-Garcia, Alessandro Suglia, José Lopes, Arash Eshghi, Helen Hastie

Anaphoric expressions, such as pronouns and referential descriptions, are situated with respect to the linguistic context of prior turns, as well as, the immediate visual environment.


A Study of Automatic Metrics for the Evaluation of Natural Language Explanations

1 code implementation EACL 2021 Miruna Clinciu, Arash Eshghi, Helen Hastie

As transparency becomes key for robotics and AI, it will be necessary to evaluate the methods through which transparency is provided, including automatically generated natural language (NL) explanations.

Text Generation

A Comprehensive Evaluation of Incremental Speech Recognition and Diarization for Conversational AI

2 code implementations COLING 2020 Angus Addlesee, Yanchao Yu, Arash Eshghi

Automatic Speech Recognition (ASR) systems are increasingly powerful and more accurate, but also more numerous with several options existing currently as a service (e. g. Google, IBM, and Microsoft).

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Benchmarking Natural Language Understanding Services for building Conversational Agents

8 code implementations13 Mar 2019 Xingkun Liu, Arash Eshghi, Pawel Swietojanski, Verena Rieser

We have recently seen the emergence of several publicly available Natural Language Understanding (NLU) toolkits, which map user utterances to structured, but more abstract, Dialogue Act (DA) or Intent specifications, while making this process accessible to the lay developer.

Benchmarking General Classification +3

Multi-Task Learning for Domain-General Spoken Disfluency Detection in Dialogue Systems

no code implementations8 Oct 2018 Igor Shalyminov, Arash Eshghi, Oliver Lemon

To test the model's generalisation potential, we evaluate the same model on the bAbI+ dataset, without any additional training.

Multi-Task Learning Test

Learning how to learn: an adaptive dialogue agent for incrementally learning visually grounded word meanings

no code implementations WS 2017 Yanchao Yu, Arash Eshghi, Oliver Lemon

We present an optimised multi-modal dialogue agent for interactive learning of visually grounded word meanings from a human tutor, trained on real human-human tutoring data.

Reinforcement Learning (RL)

The BURCHAK corpus: a Challenge Data Set for Interactive Learning of Visually Grounded Word Meanings

no code implementations WS 2017 Yanchao Yu, Arash Eshghi, Gregory Mills, Oliver Joseph Lemon

We motivate and describe a new freely available human-human dialogue dataset for interactive learning of visually grounded word meanings through ostensive definition by a tutor to a learner.

Training an adaptive dialogue policy for interactive learning of visually grounded word meanings

no code implementations WS 2016 Yanchao Yu, Arash Eshghi, Oliver Lemon

We present a multi-modal dialogue system for interactive learning of perceptually grounded word meanings from a human tutor.

Semantic Parsing

Challenging Neural Dialogue Models with Natural Data: Memory Networks Fail on Incremental Phenomena

1 code implementation22 Sep 2017 Igor Shalyminov, Arash Eshghi, Oliver Lemon

Results show that the semantic accuracy of the MemN2N model drops drastically; and that although it is in principle able to learn to process the constructions in bAbI+, it needs an impractical amount of training data to do so.


VOILA: An Optimised Dialogue System for Interactively Learning Visually-Grounded Word Meanings (Demonstration System)

no code implementations WS 2017 Yanchao Yu, Arash Eshghi, Oliver Lemon

We present VOILA: an optimised, multi-modal dialogue agent for interactive learning of visually grounded word meanings from a human user.

Active Learning

Bootstrapping incremental dialogue systems: using linguistic knowledge to learn from minimal data

no code implementations1 Dec 2016 Dimitrios Kalatzis, Arash Eshghi, Oliver Lemon

We present a method for inducing new dialogue systems from very small amounts of unannotated dialogue data, showing how word-level exploration using Reinforcement Learning (RL), combined with an incremental and semantic grammar - Dynamic Syntax (DS) - allows systems to discover, generate, and understand many new dialogue variants.

Dialogue Management Management +2

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