Research Fellow at Dublin City University.
Ireland
Joined August 2017
- Tweets461
- Following150
- Followers185
- Likes1.3K
Dear @SkyUK, I am a little worried about your staff. This Virtual Assistant seems to be quite possessive. Can you please confirm that your premises have not been taken over by an unruly AI.
We now have Mohamed Elaraby presenting their work on "Adding Argumentation into Human Evaluation of Long Document Abstractive Summarization: A Case Study on Legal Opinions". #HumEval2024.
ALT Mohamed presenting the paper.
Another poster from our ReproHum partners at Heriot-Watt. Many of these posters, including this one, are work towards the multi-lab multi-test study of the ReproHum project. reprohum.github.io/
ALT A photo of the poster.
Really good poster presentation by @PSchmidtova and @LangoMateusz on their #HumEval2024 paper "ReproHum #0043-4: Evaluating Summarization Models: investigating the impact of education and language proficiency on reproducibility"
Great poster presentation by @j_corbelle on their poster "ReproHum #0927-3: Reproducing The Human Evaluation Of The DExperts Controlled Text Generation Method"
ALT Photo of Javier with the poster.
Really good poster presentation by @anouckbragg. Poster title: "ReproHum: #0033-03: How Reproducible Are Fluency Ratings of Generated Text? A Reproduction of August"
Excellent poster presentation by Toky Raboanary on their reproduction work with @nqongeveg and Maria Keet. Poster is "ReproHum #0866-04: Another Evaluation of Readers' Reactions to News Headlines"
ALT Photo of Toky with the poster.
Great poster presentation by Andra-Maria Florescu and Marius Micluta-Campeanu for #HumEval2024. "Once Upon a Replication: It is Humans' Turn to Evaluate AI's Understanding of Children's Stories for QA Generation".
Great poster by @MichelaLorandi at #HumEval2024. "Reproducing the Metric-Based Evaluation of a Set of Controllable Text Generation Techniques"
ALT A photo of Michela with the poster "Reproducing the Metric-Based Evaluation of a Set of Controllable Text Generation Techniques"
"ReproHum #1018-09: Reproducing Human Evaluations of Redundancy Errors in Data-To-Text Systems", Great poster by Filip Klubička @lemoncloack.
ALT Poster of Filip Klubička with the poster
"Exploring Reproducibility of Human-Labelled Data for Code-Mixed Sentiment Analysis". Great virtual presentation by @heysachins. An interesting reproduction of both a training corpus and the classifiers which are then trained on it.
ALT A photo of the poster.
Very pleased to have as our second invite talk, Ding Wang from Google Research. The talk is on "All That Agrees Is Not Gold: Evaluating Ground Truth and Conversational Safety". #HumEval2024
We now have Toky Hajatiana Raboanary presenting their reproduction of aclanthology.org/2022.acl-lo… #HumEval2024
ALT Photo of Toky presenting.
Irene Mondella is now presenting their reproduction of aclanthology.org/P19-1037. #HumEval2024
ALT Photo of Irene presenting
Filip Klubička is now presenting their reproduction of aclanthology.org/2022.acl-lo… #HumEval
ALT Photo of Filip presenting
We now have a presentation on "Towards Holistic Human Evaluation of Automatic Text Simplification" by Andreas Säuberli & Luisa Carrer. #HumEval2024
ALT Photo of Andreas Säuberli & Luisa Carrer at their HumEval presentation
Next, we have a presentation of "Extrinsic evaluation of question generation methods with user journey logs" by Elie Antoine. #HumEval2024
ALT Photo of Elie presenting.