News Aggregation with Diverse Viewpoint Identification Using Neural Embeddings and Semantic Understanding Models

Mark Carlebach, Ria Cheruvu, Brandon Walker, Cesar Ilharco, Sylvain Jaume

Proceedings of the 7th Workshop on Argument Mining (ArgMining), COLING 2020

Abstract: Today’s news volume makes it impractical for readers to get a diverse and comprehensive view of published articles written from opposing viewpoints. We introduce a transformer-based news aggregation system, composed of topic modeling, hypothesis extraction, semantic clustering, premise extraction, and textual entailment that identifies viewpoints presented in articles within a semantic cluster and classifies them into positive, neutral and negative entailments. Our novel embedded topic model using BERT-based embeddings outperforms baseline topic modeling algorithms by an 11% relative improvement. We compare recent semantic similarity models in the context of news aggregation, evaluate transformer-based models for claim extraction on news data, and demonstrate the use of textual entailment models for diverse viewpoint identification.

 @inproceedings{newsaggregation2020,
  title        = {News Aggregation with Diverse Viewpoint Identification Using Neural Embeddings and Semantic Understanding Models},
  author       = {Carlebach, Mark and Cheruvu, Ria and Walker, Brandon and Ilharco, Cesar and Jaume, Sylvain},
  editor       = {Association for Computational Linguistics},
  booktitle    = {Proceedings of the 7th Workshop on Argument Mining},
  booksubtitle = {ArgMining@ACL, COLING 2020},
  date         = {2020},
  publisher    = {ACL},
  }