The search of information in large text repositories has been plagued by the so-called document-query vocabulary gap, i.e. the semantic discordance between the contents in the stored document entities on the one hand and the human query on the other hand. Over the past two decades, a significant body of works has advanced technical retrieval prowess while several studies have shed light on issues pertaining to human search behavior. We believe that these efforts should be conjoined, in the sense that automated retrieval systems have to fully emulate human search behavior and thus consider the procedure according to which users incrementally enhance their initial query. To this end, cognitive reformulation patterns that mimic user search behaviour are highlighted and enhancement terms which are statistically collocated with or lexical-semantically related to the original terms adopted in the retrieval process. We formalize the application of these patterns by considering a query conceptual representation and introducing a set of operations allowing to operate modifications on the initial query. A genetic algorithm-based weighting process allows placing emphasis on terms according to their conceptual role-type. An experimental evaluation on real-world datasets against relevance, language, conceptual and knowledge-based models is conducted. We also show, when compared to language and relevance models, a better performance in terms of mean average precision than a word embedding-based model instantiation.
Image and video retrieval by their semantic content has been an important and challenging task for years, because it ultimately requires bridging the symbolic/subsymbolic gap. Recent successes in deep learning enabled detection of objects belonging to many classes greatly outperforming traditional computer vision techniques. However, deep learning solutions capable of executing retrieval queries are still not available. We propose a hybrid solution consisting of a deep neural network for object detection and a cognitive architecture for query execution. Specifically, we use YOLOv2 and OpenCog.…
SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems
AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark
University of Science and Technology of China（中国科学技术大学）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）；Jina AI（极光科技）；Beijing University of Posts and Telecommunications（北京邮电大学）；Shenzhen University（深圳大学）；State Key Laboratory of Cognitive Intelligence（认知智能国家重点实验室）；Hong Kong Polytechnic University（香港理工大学）
Beyond Semantic Relevance: Counterfactual Risk Minimization for Robust Retrieval-Augmented Generation
National Engineering Research Center for Software Engineering, Peking University（软件工程国家工程研究中心，北京大学）；City University of Hong Kong（香港城市大学）；Tencent Technology（腾讯科技）；Peking University（北京大学）
Center For Automation Research, University of Maryland, College Park（马里兰大学帕克分校自动化研究中心）
Complex event retrieval is a challenging research problem, especially when no training videos are available. An alternative to collecting training videos is to train a large semantic concept bank a priori. Given a text description of an event, event retrieval is performed by selecting concepts linguistically related to the event description and fusing the concept responses on unseen videos. However, defining an exhaustive concept lexicon and pre-training it requires vast computational resources. Therefore, recent approaches automate concept discovery and training by leveraging large amounts of…
This paper reports the use of a document distance-based approach to automatically expand the number of available relevance judgements when these are limited and reduced to only positive judgements. This may happen, for example, when the only available judgements are extracted from a list of references in a published review paper. We compare the results on two document sets: OHSUMED, based on medical research publications, and TREC-8, based on news feeds. We show that evaluations based on these expanded relevance judgements are more reliable than those using only the initially available judgeme…
Computational Video Editing Systems output video generally follows a particular form, e.g. conversation or music videos, in this way they are domain specific. We describe a recent development in our video annotation and segmentation system to support general computational video editing in which we derive a single generic editing strategy from general cinema narrative principles instead of using a hierarchical film gram-mar. We demonstrate how this single principle coupled with a database of scripts derived from annotated videos leverages the existing video editing knowledge encoded within the …
Government College of Engineering and Textile Technology, Berhampore（贝汉布尔政府工程与纺织技术学院）；Indian Institute of Technology, Patna（印度理工学院巴特那分校）
Natural Language Processing (NLP) and Information Retrieval (IR) in the judicial domain is an essential task. With the advent of availability domain-specific data in electronic form and aid of different Artificial intelligence (AI) technologies, automated language processing becomes more comfortable, and hence it becomes feasible for researchers and developers to provide various automated tools to the legal community to reduce human burden. The Competition on Legal Information Extraction/Entailment (COLIEE-2019) run in association with the International Conference on Artificial Intelligence an…
Relevance is an underlying concept in the field of Information Science and Retrieval. It is a cognitive notion consisting of several different criteria or dimensions. Theoretical models of relevance allude to interdependence between these dimensions, where their interaction and fusion leads to the final inference of relevance. We study the interaction between the relevance dimensions using the mathematical framework of Quantum Theory. It is considered a generalised framework to model decision making under uncertainty, involving multiple perspectives and influenced by context. Specifically, we …
We used Lemur Toolkit, an open source toolkit designed for Information Retrieval (IR) research, for our automated indexing and retrieval experiments on a TREC-like test collection for Turkish. We study and compare three retrieval models Lemur supports, especially Language modeling approach to IR, combined with language specific preprocessing techniques. Our experiments show that all retrieval models benefits from language specific preprocessing in terms of retrieval quality. Also Language Modeling approach is the best performing retrieval model when language specific preprocessing applied.
Retrieval-Augmented Large Language Models for Evidence-Informed Guidance on Cannabidiol Use in Older Adults
Lawrence Bloomberg Faculty of Nursing, University of Toronto（多伦多大学劳伦斯·布隆伯格护理学院）；KITE Research Institute, Toronto Rehabilitation Institute, University Health Network（大学健康网络多伦多康复研究所KITE研究所）；College of Engineering and Technology, American University of the Middle East（中东美国大学工程与技术学院）
Most of the existing information retrieval systems are based on bag of words model and are not equipped with common world knowledge. Work has been done towards improving the efficiency of such systems by using intelligent algorithms to generate search queries, however, not much research has been done in the direction of incorporating human-and-society level knowledge in the queries. This paper is one of the first attempts where such information is incorporated into the search queries using Wikipedia semantics. The paper presents an essential shift from conventional token based queries to conce…
Migration, and especially irregular migration, is a critical issue for border agencies and society in general. Migration-related situations and decisions are influenced by various factors, including the perceptions about migration routes and target countries. An improved understanding of such factors can be achieved by systematic automated analyses of media and social media channels, and the videos and images published in them. However, the multifaceted nature of migration and the variety of ways migration-related aspects are expressed in images and videos make the finding and automated analys…
Tsinghua University（清华大学）；Institute for Artificial Intelligence（人工智能研究院）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）
Reading comprehension is a complex cognitive process involving many human brain activities. Plenty of works have studied the patterns and attention allocations of reading comprehension in information retrieval related scenarios. However, little is known about what happens in human brain during reading comprehension and how these cognitive activities can affect information retrieval process. Additionally, with the advances in brain imaging techniques such as electroencephalogram (EEG), it is possible to collect brain signals in almost real time and explore whether it can be utilized as feedback…
