← Back to papers
2022 NAACL NAACL 2022

WueDevils at SemEval-2022 Task 8: Multilingual News Article Similarity via Pair-Wise Sentence Similarity Matrices

Abstract

AbstractWe present a system that creates pair-wise cosine and arccosine sentence similarity matrices using multilingual sentence embeddings obtained from pre-trained SBERT and Universal Sentence Encoder (USE) models respectively. For each news article sentence, it searches the most similar sentence from the other article and computes an average score. Further, a convolutional neural network calculates a total similarity score for the article pairs on these matrices. Finally, a random forest regressor merges the previous results to a final score that can optionally be extended with a publishing date score.

🌉 Interdisciplinary Bridge — Deep Learning and Machine Learning
🧭 Keyword Pioneer — sentence similarity matrix
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio

Authors

Dirk Wangsadirdja , Felix Heinickel , Simon Trapp , Albin Zehe , Konstantin Kobs , Andreas Hotho

Topics

Machine Learning > Core Methods > Regression Machine Learning > Core Methods > Representation Learning Deep Learning > Architectures > Neural Networks

Keywords

convolutional neural network random forest cosine similarity sentence embedding sentence similarity matrix
Download PDF

Related papers

EVI: Multilingual Spoken Dialogue Tasks and Dataset for Knowledge-Based Enrolment, Verification, and Identification 2022
Generating Complement Data for Aspect Term Extraction with GPT-2 2022
Regularized Training of Nearest Neighbor Language Models 2022
Systematicity Emerges in Transformers when Abstract Grammatical Roles Guide Attention 2022
Neural Retriever and Go Beyond: A Thesis Proposal 2022