Peter Vickers


pdf bib
We Need to Talk About Classification Evaluation Metrics in NLP
Peter Vickers | Loic Barrault | Emilio Monti | Nikolaos Aletras
Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)


pdf bib
CogNLP-Sheffield at CMCL 2021 Shared Task: Blending Cognitively Inspired Features with Transformer-based Language Models for Predicting Eye Tracking Patterns
Peter Vickers | Rosa Wainwright | Harish Tayyar Madabushi | Aline Villavicencio
Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics

The CogNLP-Sheffield submissions to the CMCL 2021 Shared Task examine the value of a variety of cognitively and linguistically inspired features for predicting eye tracking patterns, as both standalone model inputs and as supplements to contextual word embeddings (XLNet). Surprisingly, the smaller pre-trained model (XLNet-base) outperforms the larger (XLNet-large), and despite evidence that multi-word expressions (MWEs) provide cognitive processing advantages, MWE features provide little benefit to either model.

pdf bib
In Factuality: Efficient Integration of Relevant Facts for Visual Question Answering
Peter Vickers | Nikolaos Aletras | Emilio Monti | Loïc Barrault
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)

Visual Question Answering (VQA) methods aim at leveraging visual input to answer questions that may require complex reasoning over entities. Current models are trained on labelled data that may be insufficient to learn complex knowledge representations. In this paper, we propose a new method to enhance the reasoning capabilities of a multi-modal pretrained model (Vision+Language BERT) by integrating facts extracted from an external knowledge base. Evaluation on the KVQA dataset benchmark demonstrates that our method outperforms competitive baselines by 19%, achieving new state-of-the-art results. We also perform an extensive analysis highlighting the limitations of our best performing model through an ablation study.