Summary of Passage Retrieval Of Polish Texts Using Okapi Bm25 and An Ensemble Of Cross Encoders, by Jakub Pokrywka
Passage Retrieval of Polish Texts Using OKAPI BM25 and an Ensemble of Cross Encoders
by Jakub Pokrywka
First submitted to arxiv on: 6 Oct 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper presents a winning solution to the Poleval 2023 Task 3: Passage Retrieval challenge, which involves retrieving passages of Polish texts in three domains: trivia, legal, and customer support. The method combines OKAPI BM25 algorithm with an ensemble of publicly available multilingual Cross Encoders for Reranking. While fine-tuning the reranker models slightly improves performance in the training domain, it worsens in other domains. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps solve a big problem called Passage Retrieval. Right now, people use old methods like TF-IDF and BM25 to find relevant text passages. Some new neural network models do better, but they have some issues. They need lots of labeled data and can struggle with new situations. This paper presents a solution that works really well on one kind of passage (trivia) and tries to adapt it to other types. It’s an important step forward in making search engines more accurate. |
Keywords
» Artificial intelligence » Fine tuning » Neural network » Tf idf
