Semantic Search for Undergraduate Theses Using Sentence Embeddings

Lukman Hakim, Intan Permatasari

Jurnal Teknologi dan Inovasi, Vol. 1 No. 2 (2026), pp. 49-60

Abstract

Students searching a university thesis repository often fail to find relevant work because keyword search does not match synonyms or paraphrases. We implemented a semantic search service that encodes thesis titles and abstracts with a multilingual sentence embedding model and retrieves results by cosine similarity, combined with the existing keyword index. On a benchmark of 300 queries written by students, the hybrid approach improved normalised discounted cumulative gain at rank ten from 0.52 to 0.71. Gains were largest for conceptual queries written in everyday language. Indexing 21,000 theses took under an hour on a single server, and queries return in under 200 milliseconds. The service is now offered alongside traditional search in the library catalogue.

Keywords: semantic search; sentence embeddings; digital library; information retrieval; academic repository

1. Introduction

This section introduces the problem of information retrieval addressed in this study, reviews the main approaches reported in prior work, and states the research objectives.

2. Methods

We describe the data, the proposed approach, the baselines, and the evaluation protocol used to assess the results summarised in the abstract.

3. Results and Discussion

The results are presented and compared with the baselines. Limitations and practical implications for deployment are discussed.

4. Conclusion

The study shows that the proposed approach is effective for the stated objectives and outlines directions for future work.

References

  1. Reimers, N., & Gurevych, I. (2019). Sentence-BERT: Sentence embeddings using Siamese BERT-networks. Proceedings of EMNLP-IJCNLP 2019, 3982–3992.
  2. Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of NAACL-HLT 2019, 4171–4186.
  3. Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient estimation of word representations in vector space. arXiv:1301.3781.
  4. Koren, Y., Bell, R., & Volinsky, C. (2009). Matrix factorization techniques for recommender systems. Computer, 42(8), 30–37. https://doi.org/10.1109/MC.2009.263