Generative retrieval represents a novel approach to information retrieval. It uses an encoder-decoder architecture to directly produce relevant document identifiers (docids) for queries. While this method offers benefits, current approaches are limited to scenarios with binary relevance data, overlooking the potential for documents to have multi-graded relevance. Extending generative retrieval to accommodate multi-graded relevance poses challenges, including the need to reconcile likelihood probabilities for docid pairs and the possibility of multiple relevant documents sharing the same identifier. To address these challenges, we introduce a framework called GRaded Generative Retrieval (GR$^2$). GR$^2$ focuses on two key components: ensuring relevant and distinct identifiers, and implementing multi-graded constrained contrastive training. First, we create identifiers that are both semantically relevant and sufficiently distinct to represent individual documents effectively. This is achieved by jointly optimizing the relevance and distinctness of docids through a combination of docid generation and autoencoder models. Second, we incorporate information about the relationship between relevance grades to guide the training process. We use a constrained contrastive training strategy to bring the representations of queries and the identifiers of their relevant documents closer together, based on their respective relevance grades. Extensive experiments on datasets with both multi-graded and binary relevance demonstrate the effectiveness of GR$^2$.
NTCIR was the first large-scale IR evaluation conference to construct test collections with graded relevance assessments: the NTCIR-1 test collections from 1998 already featured relevant and partially relevant documents. In this paper, I first describe a few graded-relevance measures that originated from NTCIR (and a few variants) which are used across different NTCIR tasks. I then provide a survey on the use of graded relevance assessments and of graded relevance measures in the past NTCIR tasks which primarily tackled ranked retrieval. My survey shows that the majority of the past tasks full…
Recommender systems are frequently used in domains in which users express their preferences in the form of graded judgments, such as ratings. If accurate top-N recommendation lists are to be produced for such graded relevance domains, it is critical to generate a ranked list of recommended items directly rather than predicting ratings. Current techniques choose one of two sub-optimal approaches: either they optimize for a binary metric such as Average Precision, which discards information on relevance grades, or they optimize for Normalized Discounted Cumulative Gain (NDCG), which ignores the …
Evaluation of search engines relies on assessments of search results for selected test queries, from which we would ideally like to draw conclusions in terms of relevance of the results for general (e.g., future, unknown) users. In practice however, most evaluation scenarios only allow us to conclusively determine the relevance towards the particular assessor that provided the judgments. A factor that cannot be ignored when extending conclusions made from assessors towards users, is the possible disagreement on relevance, assuming that a single gold truth label does not exist. This paper prese…
BiXSE: Improving Dense Retrieval via Probabilistic Graded Relevance Distillation
Université de Montéal（蒙特阿尔大学）；Mila - Quebec AI Institute（魁北克AI研究院）；McGill University（麦吉尔大学）；Apple MLR（苹果机器学习研究部）；IVADO, Canada（加拿大IVADO研究所）；CIFAR AI Chair（CIFAR人工智能主席）；ServiceNow Research（ServiceNow研究）
Users of web search engines are known to mostly focus on the top ranked results of the search engine result page. While many studies support this well known information seeking pattern only few studies concentrate on the question what users are missing by neglecting lower ranked results. To learn more about the relevance distributions in the so-called long tail we conducted a relevance assessment study with the Million Short long-tail web search engine. While we see a clear difference in the content between the head and the tail of the search engine result list we see no statistical significan…
There are many existing retrieval and question answering datasets. However, most of them either focus on ranked list evaluation or single-candidate question answering. This divide makes it challenging to properly evaluate approaches concerned with ranking documents and providing snippets or answers for a given query. In this work, we present FiRA: a novel dataset of Fine-Grained Relevance Annotations. We extend the ranked retrieval annotations of the Deep Learning track of TREC 2019 with passage and word level graded relevance annotations for all relevant documents. We use our newly created da…
State Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）
Scenario-based question answering (SQA) requires retrieving and reading paragraphs from a large corpus to answer a question which is contextualized by a long scenario description. Since a scenario contains both keyphrases for retrieval and much noise, retrieval for SQA is extremely difficult. Moreover, it can hardly be supervised due to the lack of relevance labels of paragraphs for SQA. To meet the challenge, in this paper we propose a joint retriever-reader model called JEEVES where the retriever is implicitly supervised only using QA labels via a novel word weighting mechanism. JEEVES signi…
Johns Hopkins University（约翰斯·霍普金斯大学）；University of Maryland, College Park（马里兰大学帕克分校）
HC4 is a new suite of test collections for ad hoc Cross-Language Information Retrieval (CLIR), with Common Crawl News documents in Chinese, Persian, and Russian, topics in English and in the document languages, and graded relevance judgments. New test collections are needed because existing CLIR test collections built using pooling of traditional CLIR runs have systematic gaps in their relevance judgments when used to evaluate neural CLIR methods. The HC4 collections contain 60 topics and about half a million documents for each of Chinese and Persian, and 54 topics and five million documents f…
A Large Language Model-based Framework for Semi-Structured Tender Document Retrieval-Augmented Generation
School of Information Management Sun Yat-sen University Guangzhou, China；School of Information Management Sun Yat-sen University Guangzhou, China corresponding author
