The Eval4NLP Shared Task on Explainable Quality Estimation: Overview and Results

Abstract

In this paper, we introduce the Eval4NLP-2021shared task on explainable quality estimation. Given a source-translation pair, this shared task requires not only to provide a sentence-level score indicating the overall quality of the translation, but also to explain this score by identifying the words that negatively impact translation quality. We present the data, annotation guidelines and evaluation setup of the shared task, describe the six participating systems, and analyze the results. To the best of our knowledge, this is the first shared task on explainable NLP evaluation metrics. Datasets and results are available at https://github.com/eval4nlp/SharedTask2021.

References in corpus (13)

• Towards A Rigorous Science of Interpretable Machine Learning
• Axiomatic Attribution for Deep Networks
• Learning Important Features Through Propagating Activation Differences
• Not Just a Black Box: Learning Important Features Through Propagating Activation Differences
• Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translation
• A Survey of the State of Explainable AI for Natural Language Processing
• fairseq: A Fast, Extensible Toolkit for Sequence Modeling
• Multilingual Translation with Extensible Multilingual Pretraining and Finetuning
• Attention is Not Only a Weight: Analyzing Transformers with Vector Norms
• Better than Average: Paired Evaluation of NLP Systems
• Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control
• On the Limitations of Cross-lingual Encoders as Exposed by Reference-Free Machine Translation Evaluation
• Quality Estimation without Human-labeled Data