Multilevel Text Alignment with Cross-Document Attention

Abstract

Text alignment finds application in tasks such as citation recommendation and plagiarism detection. Existing alignment methods operate at a single, predefined level and cannot learn to align texts at, for example, sentence and document levels. We propose a new learning approach that equips previously established hierarchical attention encoders for representing documents with a cross-document attention component, enabling structural comparisons across different levels (document-to-document and sentence-to-document). Our component is weakly supervised from document pairs and can align at multiple levels. Our evaluation on predicting document-to-document relationships and sentence-to-document relationships on the tasks of citation recommendation and plagiarism detection shows that our approach outperforms previously established hierarchical, attention encoders based on recurrent and transformer contextualization that are unaware of structural correspondence between documents.

arXiv commentEMNLP 2020

References in corpus (9)

• Efficient Estimation of Word Representations in Vector Space
• Natural Language Processing (almost) from Scratch
• BilBOWA: Fast Bilingual Distributed Representations without Word Alignments
• Structured Attention Networks
• Beyond 512 Tokens: Siamese Multi-depth Transformer-based Hierarchical Encoder for Long-Form Document Matching
• Latent Alignment and Variational Attention
• GLoMo: Unsupervisedly Learned Relational Graphs as Transferable Representations
• Textual Entailment with Structured Attentions and Composition
• Hierarchical Question Answering for Long Documents