Workshop on Human Evaluation of NLP Systems
Programme
This is the preliminary workshop programme (All timings are in CEST)
| Time | Event |
|---|---|
| 09:00–09:10 | Opening Chairs: Anya Belz and Yvette Graham |
| 09:10–10:00 | Invited Talk: Disagreement in Human Evaluation: Blame the Task not the Annotators by Lucia Specia, Imperial College London and University of Sheffield It is well known that human evaluators are prone to disagreement and that this is a problem for reliability and reproducibility of evaluation experiments. The reasons for disagreement can fall into two broad categories: (1) human evaluator, including under-trained, under-incentivised, lacking expertise, or ill-intended individuals, e.g., cheaters; and (2) task, including ill-definition, poor guidelines, suboptimal setup, or inherent subjectivity. While in an ideal evaluation experiment many of these elements will be controlled for, I argue that task subjectivity is a much harder issue. In this talk I will cover a number of evaluation experiments on tasks with variable degrees of subjectivity, discuss their levels of disagreement along with other issues, and cover a few practical approaches do address them. I hope this will lead to an open discussion on possible strategies and directions to alleviate this problem. [Video] |
| 10:00–11:00 | Oral Session 1 (NLG) Chairs: Anastasia Shimorina and Shubham Agarwal |
| 10:00–10:20 | It’s Commonsense, isn’t it? Demystifying Human Evaluations in Commonsense-Enhanced NLG systems Miruna-Adriana Clinciu, Dimitra Gkatzia and Saad Mahamood [Video] |
| 10:20–10:40 | Estimating Subjective Crowd-Evaluations as an Additional Objective to Improve Natural Language Generation Jakob Nyberg, Maike Paetzel and Ramesh Manuvinakurike [Video] |
| 10:40–11:00 | Trading Off Diversity and Quality in Natural Language Generation Hugh Zhang, Daniel Duckworth, Daphne Ippolito and Arvind Neelakantan [Video] |
| 11:00–11:30 | Break |
| 11:30–12:10 | Oral Session 2 (MT) Chairs: Yvette Graham and Anastasia Shimorina |
| 11:30–11:50 | Towards Document-Level Human MT Evaluation: On the Issues of Annotator Agreement, Effort and Misevaluation Sheila Castilho [Video] |
| 11:50–12:10 | Is This Translation Error Critical?: Classification-Based Human and Automatic Machine Translation Evaluation Focusing on Critical Errors Katsuhito Sudoh, Kosuke Takahashi and Satoshi Nakamura [Video] |
| 12:10–13:30 | Poster Session - Towards Objectively Evaluating the Quality of Generated Medical Summaries Francesco Moramarco, Damir Juric, Aleksandar Savkov and Ehud Reiter - A Preliminary Study on Evaluating Consultation Notes With Post-Editing Francesco Moramarco, Alex Papadopoulos Korfiatis, Aleksandar Savkov and Ehud Reiter - The Great Misalignment Problem in Human Evaluation of NLP Methods Mika Hämäläinen and Khalid Alnajjar - A View From the Crowd: Evaluation Challenges for Time-Offset Interaction Applications Alberto Chierici and Nizar Habash - Reliability of Human Evaluation for Text Summarization: Lessons Learned and Challenges Ahead Neslihan Iskender, Tim Polzehl and Sebastian Möller - On User Interfaces for Large-Scale Document-Level Human Evaluation of Machine Translation Outputs Roman Grundkiewicz, Marcin Junczys-Dowmunt, Christian Federmann and Tom Kocmi - Eliciting Explicit Knowledge From Domain Experts in Direct Intrinsic Evaluation of Word Embeddings for Specialized Domains Goya van Boven and Jelke Bloem - Detecting Post-Edited References and Their Effect on Human Evaluation Věra Kloudová, Ondřej Bojar and Martin Popel |
| 13:30–15:00 | Lunch |
| 15:00–15:40 | Oral Session 3 Chairs: Dimitra Gkatzia and Ehud Reiter |
| 15:00–15:20 | A Case Study of Efficacy and Challenges in Practical Human-in-Loop Evaluation of NLP Systems Using Checklist Shaily Bhatt, Rahul Jain, Sandipan Dandapat and Sunayana Sitaram [Video] |
| 15:20–15:40 | Interrater Disagreement Resolution: A Systematic Procedure to Reach Consensus in Annotation Tasks Yvette Oortwijn, Thijs Ossenkoppele and Arianna Betti [Video] |
| 15:40–16:40 | Open-Mic Discussion Panel Chairs: Ehud Reiter and Anya Belz Discussion session will be open to all participants. Anyone who is interested in speaking for 3 mins about any topic relevant to the workshop should email Ehud Reiter (e.reiter@abdn.ac.uk). We will follow these short presentations by a general discussion. |
| 16:40–17:00 | Break |
| 17:00–17:50 | Invited Talk: The Ins and Outs of Ethics-Informed Evaluation by Margaret Mitchell The modern train/test paradigm in Artificial Intelligence (AI) and Machine Learning (ML) narrows what we can understand about AI models, and skews our understanding of models’ robustness in different environments. In this talk, I will work through the different factors involved in ethics-informed AI evaluation, including connections to ML training and ML fairness, and present an overarching evaluation protocol that addresses a multitude of considerations in developing ethical AI. [Video] |
| 17:50–18:00 | Closing |