Terminology-based Text Embedding for Computing Document Similarities on Technical Content
This addresses document similarity for technical content, but it is incremental as it builds on existing graph and embedding methods.
The paper tackled the problem of computing document similarities for technical content by proposing a hybrid document embedding approach that uses graph techniques to extract keyphrases and rank sentences, resulting in up to 27% improvement in NDCG over baselines.
We propose in this paper a new, hybrid document embedding approach in order to address the problem of document similarities with respect to the technical content. To do so, we employ a state-of-the-art graph techniques to first extract the keyphrases (composite keywords) of documents and, then, use them to score the sentences. Using the ranked sentences, we propose two approaches to embed documents and show their performances with respect to two baselines. With domain expert annotations, we illustrate that the proposed methods can find more relevant documents and outperform the baselines up to 27% in terms of NDCG.