Enhanced News Retrieval: Passages Lead the Way!

Matteo Catena, Ophir Frieder, Cristina Ioana Muntean, Franco Maria Nardini, Raffaele Perego, Nicola Tonellotto

Abstract

We observe that most relevant terms in unstructured news articles are primarily concentrated towards the beginning and the end of the document. Exploiting this observation, we propose a novel version of the classical BM25 weighting model, called BM25 Passage (BM25P), which scores query results by computing a linear combination of term statistics in the different portions of news articles. Our experimentation, conducted using three publicly available news datasets, demonstrates that BM25P markedly outperforms BM25 in term of effectiveness by up to 17.44% in [email protected] and 85% in [email protected]
BibTeX
@inproceedings{catena2019enhanced,
  author = {Matteo Catena and Ophir Frieder and Cristina Ioana Muntean and Franco Maria Nardini and Raffaele Perego and Nicola Tonellotto},
  title = {{Enhanced News Retrieval: Passages Lead the Way!}},
  booktitle = {International ACM SIGIR Conference on Research and Development in Information Retrieval},
  year = {2019},
  doi = {10.1145/3331184.3331373},
}

Loading related content...

Figure