Retrieving Diverse Perspectives on Complex and Contentious Questions
Existing information retrieval systems mostly optimize for relevance to the question, ignoring diversity. This work proposes a benchmark and task to evaluate the ability of retrieval systems to surface diverse perspectives on complex and contentious questions.
Unified Embedding-Based Personalized Product Retrieval in Etsy Search
A novel two-tower model with a unified embedding-based product encoder and joint user-query encoder to handle diverse search queries and provide personalized product recommendations on an e-commerce platform.
Limitations of Using Large Language Models for Relevance Judgments in Information Retrieval Evaluation
Using large language models (LLMs) to generate relevance judgments for information retrieval evaluation is problematic, as it limits the ability to measure systems that may outperform the LLM-generated judgments.
Leveraging User Behaviors to Enhance Short-Video Search Engagement through Personalization
Personalization can significantly improve user engagement in short-video search by leveraging user profiles, long-term interests, and real-time behaviors to retrieve and rank relevant content.
Optimizing Retrieval-Augmented Generation Systems: Evaluating Document Splitting Methods and Retrieval Techniques Across Diverse Content Types
Effective retrieval strategies are crucial for Retrieval-Augmented Generation (RAG) systems to provide accurate and relevant responses. This study evaluates the performance of different document splitting methods and retrieval techniques across diverse document types, including textbooks, articles, and novels, to identify optimal approaches for enhancing retrieval accuracy and efficiency.
Counterfactual Explanation Framework for Improving Ranking of Documents in Information Retrieval Models
The proposed counterfactual framework can identify the terms that need to be added to a document to improve its ranking with respect to a specific retrieval model and query.
MessIRve: A Large-Scale Spanish Information Retrieval Dataset Covering Diverse Dialects and Topics
MessIRve is a large-scale Spanish information retrieval dataset that accounts for the diverse dialects and topics across Spanish-speaking countries, aiming to advance Spanish IR research and improve information access for Spanish speakers.
Rs4rs: A Semantic Search Tool for Recent Publications from Top Recommendation System Conferences and Journals
Rs4rs is a web application that enables semantic search to efficiently find recent, high-quality publications from top conferences and journals related to Recommender Systems.
Efficient Human-in-the-Loop Query Development for Cross-Lingual Information Retrieval
QueryBuilder, an interactive system, allows novice users to efficiently create fine-grained queries for cross-lingual information retrieval by leveraging an English development corpus and a combination of probabilistic and neural information retrieval models.
Fusion-in-T5: A Unified Model for Effective Document Ranking by Integrating Multiple Signals
Fusion-in-T5 (FiT5) is a unified document ranking model that integrates text matching, ranking features, and global document information through attention fusion, outperforming complex cascade ranking pipelines.
© 2024 by Linnk AI