Search Results for author: Mark Hepple

Found 11 papers, 0 papers with code

Igbo-English Machine Translation: An Evaluation Benchmark

no code implementations1 Apr 2020 Ignatius Ezeani, Paul Rayson, Ikechukwu Onyenwe, Chinedu Uchechukwu, Mark Hepple

Although researchers and practitioners are pushing the boundaries and enhancing the capacities of NLP tools and methods, works on African languages are lagging.

Machine Translation Part-Of-Speech Tagging +1

Igbo Diacritic Restoration using Embedding Models

no code implementations NAACL 2018 Ignatius Ezeani, Mark Hepple, Ikechukwu Onyenwe, Enemouh Chioma

In this work, we applied embedding models to the diacritic restoration task and compared their performances to those of n-gram models.

Machine Translation Word Embeddings

Lexical Disambiguation of Igbo using Diacritic Restoration

no code implementations WS 2017 Ignatius Ezeani, Mark Hepple, Ikechukwu Onyenwe

However, as a classification task, diacritic restoration is well suited for and will be more generalisable with machine learning.

General Classification

What's the Issue Here?: Task-based Evaluation of Reader Comment Summarization Systems

no code implementations LREC 2016 Emma Barker, Monica Paramita, Adam Funk, Emina Kurtic, Ahmet Aker, Jonathan Foster, Mark Hepple, Robert Gaizauskas

Second, we define a task-based evaluation framework for reader comment summarization that allows summarization systems to be assessed in terms of how well they support users in a time-limited task of identifying issues and characterising opinion on issues in comments.

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