@inproceedings{shil-jin-2025-esaqueryrank,
    title = "{ESAQ}uery{R}ank: Ranking Query Interpretations for Document Retrieval Using Explicit Semantic Analysis",
    author = "Shil, Avijeet  and
      Jin, Wei",
    editor = "Angelova, Galia  and
      Kunilovskaya, Maria  and
      Escribe, Marie  and
      Mitkov, Ruslan",
    booktitle = "Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era",
    month = sep,
    year = "2025",
    address = "Varna, Bulgaria",
    publisher = "INCOMA Ltd., Shoumen, Bulgaria",
    url = "https://preview.aclanthology.org/issues-pwc/2025.ranlp-1.132/",
    pages = "1148--1152",
    abstract = "Representing query translation into relevant entities is a critical component of an information retrieval system. This paper proposes an unsupervised framework, \textbf{ESAQueryRank}, designed to process natural language queries by mapping n-gram phrases to Wikipedia titles and ranking potential entity and phrase combinations using Explicit Semantic Analysis. Unlike previous approaches, this framework does not rely on query expansion, syntactic parsing, or manual annotation. Instead, it leverages Wikipedia metadata{---}such as titles, redirects, disambiguation pages to disambiguate entities and identify the most relevant ones based on cosine similarity in the ESA space. \textbf{ESAQueryRank} is evaluated using a random set of TREC questions and compared against a keyword-based approach and a context-based question translation model (CBQT). In all comparisons of full category types, \textbf{ESAQueryRank} consistently shows better results against both methods. Notably, the framework excels with more complex queries, achieving improvements in Mean Reciprocal Rank (MRR) of up to 480{\%} for intricate queries like those beginning with ``Why,'' even without explicitly incorporating the question type. These results demonstrate that \textbf{ESAQueryRank} is an effective, transparent, and domain-independent framework for building natural language interfaces."
}