Using Large Language Models to Improve Data Loss Prevention in Organizations
Explore how large language models enhance data loss prevention by enabling full-text analysis and document categorization, improving sensitive information detection beyond pattern-based matching.
Women of Search: Challenges and Opportunities in the Search Industry
Explore a case study on women in search, highlighting challenges, successes, and the transformative impact of female leadership in the workplace. Envision an ideal environment celebrating gender diversity.
Are Large Language Models Good at Utility Judgments? - Evaluation Study
Explore the capabilities of Large Language Models in making utility judgments, examining their effectiveness and limitations in evaluation tasks across information retrieval systems.
Large Language Models Can Accurately Predict Searcher Preferences
Explore how Large Language Models effectively predict and understand user search preferences, enhancing information retrieval systems and search result accuracy.
CIQA: A Coding Inspired Question Answering Model - Session W1.4
Discover innovative approaches to question answering through a coding-inspired model that enhances natural language processing and information retrieval capabilities.
Drop Your Decoder: Pre-training with Bag-of-Word Prediction for Dense Passage Retrieval
Explore innovative pre-training techniques for dense passage retrieval using bag-of-word prediction methods, focusing on decoder-free approaches for improved efficiency.
Unbiased Learning to Rank - Lessons from Baidu's Large-Scale Search Dataset
Explore real-world insights from Baidu's search data analysis, examining unbiased learning-to-rank methodologies and their practical implications for search engine optimization.
Unbiased Learning-to-Rank Needs Unconfounded Propensity Estimation
Explore advanced techniques in unbiased learning-to-rank systems, focusing on propensity estimation methods and their impact on fair ranking algorithms and search result optimization.
On the Evaluation of Generated Text SERPs
Explore cutting-edge approaches to evaluating AI-generated search engine results pages (SERPs) and their effectiveness in modern information retrieval systems.
Generative Retrieval as Multi-Vector Dense Retrieval
Explore the innovative approach of treating generative retrieval as a multi-vector dense retrieval system, examining advanced techniques for information retrieval and search optimization.
M2-RAAP: A Multi-Modal Recipe for Advancing Adaptation-based Pre-training for Video-text Retrieval
Explore cutting-edge techniques in multi-modal pre-training for zero-shot video-text retrieval, focusing on adaptation-based methods and efficient implementation strategies.
CaseLink: Inductive Graph Learning for Legal Case Retrieval
Explore innovative graph learning techniques for legal case retrieval, focusing on inductive methods that enhance search accuracy and efficiency in legal document systems.
CFIR: Fast and Effective Long-Text to Image Retrieval for Large Corpora
Discover innovative techniques for efficient long-text to image retrieval systems, focusing on fast and effective methods for handling large-scale multimedia databases.
Short Video Ordering via Position Decoding and Successor Prediction
Explore innovative techniques for short video sequence ordering through position decoding and predictive algorithms, focusing on multimedia content organization and analysis.
Traditional Methods for Similarity Search - Jaccard, W-Shingling, Levenshtein
Explore three traditional similarity search methods: Jaccard Similarity, w-shingling, and Levenshtein distance. Learn their applications in language comparison and document matching for effective search engines.
IndexLSH for Fast Similarity Search in Faiss
Explore fast similarity search using IndexLSH in Faiss. Learn efficient implementation techniques for large-scale data retrieval and comparison in AI applications.
Author Interview - Transformer Memory as a Differentiable Search Index
Explore a novel approach to information retrieval using a single Transformer model that encodes corpus information in its parameters, enabling direct query-to-document mapping without external indices.
Choosing Indexes for Similarity Search - Faiss in Python
Explore Faiss indexes for efficient similarity search, comparing Flat, LSH, HNSW, and IVF to optimize performance in large-scale datasets. Learn to choose and implement the best index for your needs.
FAISS - Introduction to Similarity Search
Explore efficient similarity search with Facebook AI Similarity Search (FAISS). Learn implementation, options, and how FAISS enhances semantic search speed.
Revolutionizing Legal Industry with Spark, NLP and Azure Databricks - Clifford Chance Case Study
Explore how a top law firm revolutionizes operations using advanced analytics, Spark, NLP, and Azure Databricks to handle millions of legal documents and enhance client relationships.
The New ACM Digital Library - User and Administrator Training
Explore ACM's new Digital Library interface, featuring enhanced search capabilities, user profiles, and administrative tools for efficient access to computing research and publications.