The BM25 ranking function is one of the most well known query relevance document scoring functions and many variations of it are proposed. The BM25F function is one of its adaptations designed for modeling documents with multiple fields. The Expanded Span method extends a BM25-like function by taking into considerations of the proximity between term occurrences. In this note, we combine these two variations into one scoring method in view of proximity-based scoring of documents with multiple fields.
When two terms occur together in a document, the probability of a close relationship between them and the document itself is greater if they are in nearby positions. However, ranking functions including term proximity (TP) require larger indexes than traditional document-level indexing, which slows down query processing. Previous studies also show that this technique is not effective for all types of queries. Here we propose a document ranking model which decides for which queries it would be beneficial to use a proximity-based ranking, based on a collection of features of the query. We use a …
While in a classification or a regression setting a label or a value is assigned to each individual document, in a ranking setting we determine the relevance ordering of the entire input document list. This difference leads to the notion of relative relevance between documents in ranking. The majority of the existing learning-to-rank algorithms model such relativity at the loss level using pairwise or listwise loss functions. However, they are restricted to univariate scoring functions, i.e., the relevance score of a document is computed based on the document itself, regardless of other docume…
We propose a method for using the scoring values of passages to effectively retrieve documents in a Question Answering system. For this, we suggest evaluation function that considers proximity between each question terms in passage. And using this evaluation function , we extract a documents which involves scoring values in the highest collection, as a suitable document for question. The proposed method is very effective in document retrieval of Korean question answering system.
CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring
Shanghai Jiao Tong University（上海交通大学）；Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative（宁波空间智能与数字孪生重点实验室）；Institute of Digital Twin, Eastern Institute of Technology, Ningbo（宁波东方理工大学数字孪生研究院）；University of British Columbia（不列颠哥伦比亚大学）；University of Waterloo（滑铁卢大学）；Google Cloud AI Research（谷歌云人工智能研究）
Successfully managing analytics-based semantic relationships and their provenance enables determinations of document importance and priority, furthering capabilities for machine-based relevancy scoring operations. Semantic technologies are well suited for modeling explicit and fully qualified relationships but struggle with modeling relationships that are qualified in nature, or resultant from applied analytics. Our work seeks to implement the autonomous Directed Qualification of analytic-based relationships by pairing the Prov-O Ontology (W3C Recommendation) with a relevancy ontology supporti…
Proximity full-text search is commonly implemented in contemporary full-text search systems. Let us assume that the search query is a list of words. It is natural to consider a document as relevant if the queried words are near each other in the document. The proximity factor is even more significant for the case where the query consists of frequently occurring words. Proximity full-text search requires the storage of information for every occurrence in documents of every word that the user can search. For every occurrence of every word in a document, we employ additional indexes to store info…
School of Computer Science & Statistics, Trinity College Dublin（都柏林圣三一大学计算机科学与统计学院）
Citation based approaches have seen good progress for recommending research papers using citations in the paper. Citation proximity analysis which uses the in-text citation proximity to find relatedness between two research papers is better than co-citation analysis and bibliographic analysis. However, one common problem which exists in each approach is that paper should be well cited. If documents are not cited properly or not cited at all, then using these approaches will not be helpful. To overcome the problem, this paper discusses the approach Virtual Citation Proximity (VCP) which uses Si…
University of Virginia（弗吉尼亚大学）；Google Research（谷歌研究院）
Recent advances in unbiased learning to rank (LTR) count on Inverse Propensity Scoring (IPS) to eliminate bias in implicit feedback. Though theoretically sound in correcting the bias introduced by treating clicked documents as relevant, IPS ignores the bias caused by (implicitly) treating non-clicked ones as irrelevant. In this work, we first rigorously prove that such use of click data leads to unnecessary pairwise comparisons between relevant documents, which prevent unbiased ranker optimization. Based on the proof, we derive a simple yet well justified new weighting scheme, called Propensit…
This paper outlines a conceptual framework for understanding recent developments in information retrieval and natural language processing that attempts to integrate dense and sparse retrieval methods. I propose a representational approach that breaks the core text retrieval problem into a logical scoring model and a physical retrieval model. The scoring model is defined in terms of encoders, which map queries and documents into a representational space, and a comparison function that computes query-document scores. The physical retrieval model defines how a system produces the top-$k$ scoring …
Leveraging biased click data for optimizing learning to rank systems has been a popular approach in information retrieval. Because click data is often noisy and biased, a variety of methods have been proposed to construct unbiased learning to rank (ULTR) algorithms for the learning of unbiased ranking models. Among them, automatic unbiased learning to rank (AutoULTR) algorithms that jointly learn user bias models (i.e., propensity models) with unbiased rankers have received a lot of attention due to their superior performance and low deployment cost in practice. Despite their differences in th…
Institute of Research in Computer Science LIDI (UNLP-CIC)（LIDI计算机科学研究所（拉普拉塔国立大学-科学研究委员会））；School of Computer Science, National University of La Plata（拉普拉塔国立大学计算机学院）；Universitat Rovira i Virgili（罗维拉-威尔吉利大学）；University of Castilla-La Mancha（卡斯蒂利亚-拉曼恰大学）
Automatic text summarization tools have a great impact on many fields, such as medicine, law, and scientific research in general. As information overload increases, automatic summaries allow handling the growing volume of documents, usually by assigning weights to the extracted phrases based on their significance in the expected summary. Obtaining the main contents of any given document in less time than it would take to do that manually is still an issue of interest. In~this~ article, a new method is presented that allows automatically generating extractive summaries from documents by adequat…
Objectives: Text categorization has been used in biomedical informatics for identifying documents containing relevant topics of interest. We developed a simple method that uses a chi-square-based scoring function to determine the likelihood of MEDLINE citations containing genetic relevant topic. Methods: Our procedure requires construction of a genetic and a nongenetic domain document corpus. We used MeSH descriptors assigned to MEDLINE citations for this categorization task. We compared frequencies of MeSH descriptors between two corpora applying chi-square test. A MeSH descriptor was conside…
