{"title":"An in-depth analysis of passage-level label transfer for contextual document ranking","authors":"Koustav Rudra, Zeon Trevor Fernando, Avishek Anand","doi":"10.1007/s10791-023-09430-5","DOIUrl":"https://doi.org/10.1007/s10791-023-09430-5","url":null,"abstract":"<p>Pre-trained contextual language models such as BERT, GPT, and XLnet work quite well for document retrieval tasks. Such models are fine-tuned based on the query-document/query-passage level relevance labels to capture the ranking signals. However, the documents are longer than the passages and such document ranking models suffer from the token limitation (512) of BERT. Researchers proposed ranking strategies that either truncate the documents beyond the token limit or chunk the documents into units that can fit into the BERT. In the later case, the relevance labels are either directly transferred from the original query-document pair or learned through some external model. In this paper, we conduct a detailed study of the design decisions about splitting and label transfer on retrieval effectiveness and efficiency. We find that direct transfer of relevance labels from documents to passages introduces <i>label noise</i> that strongly affects retrieval effectiveness for large training datasets. We also find that query processing times are adversely affected by fine-grained splitting schemes. As a remedy, we propose a careful passage level labelling scheme using weak supervision that delivers improved performance (3–14% in terms of nDCG score) over most of the recently proposed models for ad-hoc retrieval while maintaining manageable computational complexity on four diverse document retrieval datasets.</p>","PeriodicalId":54352,"journal":{"name":"Information Retrieval Journal","volume":"64 1","pages":""},"PeriodicalIF":2.5,"publicationDate":"2023-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138556906","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yifan Qiao, Shiyu Ji, Changhai Wang, Jinjin Shao, Tao Yang
{"title":"Privacy-aware document retrieval with two-level inverted indexing","authors":"Yifan Qiao, Shiyu Ji, Changhai Wang, Jinjin Shao, Tao Yang","doi":"10.1007/s10791-023-09428-z","DOIUrl":"https://doi.org/10.1007/s10791-023-09428-z","url":null,"abstract":"<p>Previous work on privacy-aware ranking has addressed the minimization of information leakage when scoring top <i>k</i> documents, and has not studied on how to retrieve these top documents and their features for ranking. This paper proposes a privacy-aware document retrieval scheme with a two-level inverted index structure. In this scheme, posting records are grouped with bucket tags and runtime query processing produces query-specific tags in order to gather encoded features of matched documents with a privacy protection during index traversal. To thwart leakage-abuse attacks, our design minimizes the chance that a server processes unauthorized queries or identifies document sharing across posting lists through index inspection or across-query association. This paper presents the evaluation and analytic results of the proposed scheme to demonstrate the tradeoffs in its design considerations for privacy, efficiency, and relevance.</p>","PeriodicalId":54352,"journal":{"name":"Information Retrieval Journal","volume":"576 ","pages":""},"PeriodicalIF":2.5,"publicationDate":"2023-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138518618","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Lucas Albarede, Philippe Mulhem, Lorraine Goeuriot, Sylvain Marié, Claude Le Pape-Gardeux, Trinidad Chardin-Segui
{"title":"Heterogeneous graph attention networks for passage retrieval","authors":"Lucas Albarede, Philippe Mulhem, Lorraine Goeuriot, Sylvain Marié, Claude Le Pape-Gardeux, Trinidad Chardin-Segui","doi":"10.1007/s10791-023-09424-3","DOIUrl":"https://doi.org/10.1007/s10791-023-09424-3","url":null,"abstract":"<p>This paper presents an exploration of the usage of Heterogeneous Graph Attention Networks, or HGATs, for the task of Passage Retrieval. More precisely, we study how these models perform to alleviate the problem of passage contextualization, that is incorporating information about the context of a passage (its containing document, neighbouring passages, etc.) in its relevance estimation. We first propose several configurations to compute contextualized passage representations, including a document graph representation composed of contextualizing signals and judiciously modified HGAT architectures. We then present how we integrate these configurations in a neural passage ranking model. We evaluate our approach on a Passage Retrieval task on patent documents: CLEF-IP2013, as these documents possess several different contextualizing signals fully exploited in our models. Our results show that some HGAT architecture modifications allow for a better context representation leading to improved performances and stability.</p>","PeriodicalId":54352,"journal":{"name":"Information Retrieval Journal","volume":"102 ","pages":""},"PeriodicalIF":2.5,"publicationDate":"2023-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138518632","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Constructing and meta-evaluating state-aware evaluation metrics for interactive search systems","authors":"Marco Markwald, Jiqun Liu, Ran Yu","doi":"10.1007/s10791-023-09426-1","DOIUrl":"https://doi.org/10.1007/s10791-023-09426-1","url":null,"abstract":"Abstract Evaluation metrics such as precision, recall and normalized discounted cumulative gain have been widely applied in ad hoc retrieval experiments. They have facilitated the assessment of system performance in various topics over the past decade. However, the effectiveness of such metrics in capturing users’ in-situ search experience, especially in complex search tasks that trigger interactive search sessions, is limited. To address this challenge, it is necessary to adaptively adjust the evaluation strategies of search systems to better respond to users’ changing information needs and evaluation criteria. In this work, we adopt a taxonomy of search task states that a user goes through in different scenarios and moments of search sessions, and perform a meta-evaluation of existing metrics to better understand their effectiveness in measuring user satisfaction. We then built models for predicting task states behind queries based on in-session signals. Furthermore, we constructed and meta-evaluated new state-aware evaluation metrics. Our analysis and experimental evaluation are performed on two datasets collected from a field study and a laboratory study, respectively. Results demonstrate that the effectiveness of individual evaluation metrics varies across task states. Meanwhile, task states can be detected from in-session signals. Our new state-aware evaluation metrics could better reflect in-situ user satisfaction than an extensive list of the widely used measures we analyzed in this work in certain states. Findings of our research can inspire the design and meta-evaluation of user-centered adaptive evaluation metrics, and also shed light on the development of state-aware interactive search systems.","PeriodicalId":54352,"journal":{"name":"Information Retrieval Journal","volume":"2013 24","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135813980","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Tayfun Alpay, Sven Magg, Philipp Broze, Daniel Speck
{"title":"Multimodal video retrieval with CLIP: a user study","authors":"Tayfun Alpay, Sven Magg, Philipp Broze, Daniel Speck","doi":"10.1007/s10791-023-09425-2","DOIUrl":"https://doi.org/10.1007/s10791-023-09425-2","url":null,"abstract":"Abstract Recent machine learning advances demonstrate the effectiveness of zero-shot models trained on large amounts of data collected from the internet. Among these, CLIP (Contrastive Language-Image Pre-training) has been introduced as a multimodal model with high accuracy on a number of different tasks and domains. However, the unconstrained nature of the model begs the question whether it can be deployed in open-domain real-word applications effectively in front of non-technical users. In this paper, we evaluate whether CLIP can be used for multimodal video retrieval in a real-world environment. For this purpose, we implemented impa , an efficient shot-based retrieval system powered by CLIP. We additionally implemented advanced query functionality in a unified graphical user interface to facilitate an intuitive and efficient usage of CLIP for video retrieval tasks. Finally, we empirically evaluated our retrieval system by performing a user study with video editing professionals and journalists working in the TV news media industry. After having the participants solve open-domain video retrieval tasks, we collected data via questionnaires, interviews, and UI interaction logs. Our evaluation focused on the perceived intuitiveness of retrieval using natural language, retrieval accuracy, and how users interacted with the system’s UI. We found that our advanced features yield higher task accuracy, user ratings, and more efficient queries. Overall, our results show the importance of designing intuitive and efficient user interfaces to be able to deploy large models such as CLIP effectively in real-world scenarios.","PeriodicalId":54352,"journal":{"name":"Information Retrieval Journal","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135194990","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}