CLIRNov 16, 2021

Multi-Vector Models with Textual Guidance for Fine-Grained Scientific Document Similarity

arXiv:2111.08366v3635 citationsHas Code
AI Analysis

This work addresses the need for more precise similarity measures in scientific document retrieval, offering incremental improvements through novel supervision and matching techniques.

The paper tackles the problem of fine-grained scientific document similarity by using co-citations as textual supervision to learn aspect matching, resulting in improved performance on four datasets with a fast single-match method achieving competitive results.

We present a new scientific document similarity model based on matching fine-grained aspects of texts. To train our model, we exploit a naturally-occurring source of supervision: sentences in the full-text of papers that cite multiple papers together (co-citations). Such co-citations not only reflect close paper relatedness, but also provide textual descriptions of how the co-cited papers are related. This novel form of textual supervision is used for learning to match aspects across papers. We develop multi-vector representations where vectors correspond to sentence-level aspects of documents, and present two methods for aspect matching: (1) A fast method that only matches single aspects, and (2) a method that makes sparse multiple matches with an Optimal Transport mechanism that computes an Earth Mover's Distance between aspects. Our approach improves performance on document similarity tasks in four datasets. Further, our fast single-match method achieves competitive results, paving the way for applying fine-grained similarity to large scientific corpora. Code, data, and models available at: https://github.com/allenai/aspire

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes