Search Results for author: Dimitra Gkatzia

Found 22 papers, 1 papers with code

Twenty Years of Confusion in Human Evaluation: NLG Needs Evaluation Sheets and Standardised Definitions

no code implementations INLG (ACL) 2020 David M. Howcroft, Anya Belz, Miruna-Adriana Clinciu, Dimitra Gkatzia, Sadid A. Hasan, Saad Mahamood, Simon Mille, Emiel van Miltenburg, Sashank Santhanam, Verena Rieser

Human assessment remains the most trusted form of evaluation in NLG, but highly diverse approaches and a proliferation of different quality criteria used by researchers make it difficult to compare results and draw conclusions across papers, with adverse implications for meta-evaluation and reproducibility.

Experimental Design

It’s Commonsense, isn’t it? Demystifying Human Evaluations in Commonsense-Enhanced NLG Systems

no code implementations EACL (HumEval) 2021 Miruna-Adriana Clinciu, Dimitra Gkatzia, Saad Mahamood

Common sense is an integral part of human cognition which allows us to make sound decisions, communicate effectively with others and interpret situations and utterances.

Common Sense Reasoning Text Generation

Chefbot: A Novel Framework for the Generation of Commonsense-enhanced Responses for Task-based Dialogue Systems

no code implementations INLG (ACL) 2021 Carl Strathearn, Dimitra Gkatzia

Conversational systems aim to generate responses that are accurate, relevant and engaging, either through utilising neural end-to-end models or through slot filling.

Chatbot Slot Filling

CAPE: Context-Aware Private Embeddings for Private Language Learning

2 code implementations EMNLP 2021 Richard Plant, Dimitra Gkatzia, Valerio Giuffrida

Deep learning-based language models have achieved state-of-the-art results in a number of applications including sentiment analysis, topic labelling, intent classification and others.

Intent Classification Sentiment Analysis

Improving the Naturalness and Expressivity of Language Generation for Spanish

no code implementations WS 2017 Cristina Barros, Dimitra Gkatzia, Elena Lloret

We present a flexible Natural Language Generation approach for Spanish, focused on the surface realisation stage, which integrates an inflection module in order to improve the naturalness and expressivity of the generated language.

Text Generation

Content Selection in Data-to-Text Systems: A Survey

no code implementations26 Oct 2016 Dimitra Gkatzia

Data-to-text systems are powerful in generating reports from data automatically and thus they simplify the presentation of complex data.

Data-to-Text Generation

An Ensemble method for Content Selection for Data-to-text Systems

no code implementations9 Jun 2015 Dimitra Gkatzia, Helen Hastie

We present a novel approach for automatic report generation from time-series data, in the context of student feedback generation.

General Classification Multi-Label Classification +1

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