Multilevel Text Alignment with Cross-Document Attention
This work addresses a limitation in text alignment for applications like citation recommendation and plagiarism detection by enabling multi-level alignment, representing an incremental improvement over single-level methods.
The paper tackles the problem of text alignment at multiple levels, such as sentence and document, by proposing a cross-document attention component for hierarchical encoders, resulting in improved performance over existing methods in citation recommendation and plagiarism detection tasks.
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.