Coherence-Based Distributed Document Representation Learning for Scientific Documents

TL;DR

This paper introduces a novel document embedding method that emphasizes the coherence of scientific documents by using coupled text pairs, improving tasks like information retrieval and recommendation.

Contribution

The paper proposes the CTPE model that incorporates document coherence through coupled text pairs, a novel approach for scientific document representation.

Findings

The CTPE model outperforms baseline methods in information retrieval.

The model improves recommendation task accuracy.

Experimental results validate the effectiveness of coherence-based embeddings.

Abstract

Distributed document representation is one of the basic problems in natural language processing. Currently distributed document representation methods mainly consider the context information of words or sentences. These methods do not take into account the coherence of the document as a whole, e.g., a relation between the paper title and abstract, headline and description, or adjacent bodies in the document. The coherence shows whether a document is meaningful, both logically and syntactically, especially in scientific documents (papers or patents, etc.). In this paper, we propose a coupled text pair embedding (CTPE) model to learn the representation of scientific documents, which maintains the coherence of the document with coupled text pairs formed by segmenting the document. First, we divide the document into two parts (e.g., title and abstract, etc) which construct a coupled text pair. Then, we adopt negative sampling to construct uncoupled text pairs whose two parts are from different documents. Finally, we train the model to judge whether the text pair is coupled or uncoupled and use the obtained embedding of coupled text pairs as the embedding of documents. We perform experiments on three datasets for one information retrieval task and two recommendation tasks. The experimental results verify the effectiveness of the proposed CTPE model.