Zobrazeno 1 - 10
of 135
pro vyhledávání: '"Anand, Avishek"'
As information retrieval systems continue to evolve, accurate evaluation and benchmarking of these systems become pivotal. Web search datasets, such as MS MARCO, primarily provide short keyword queries without accompanying intent or descriptions, pos
Externí odkaz:
http://arxiv.org/abs/2408.17103
Local feature selection in machine learning provides instance-specific explanations by focusing on the most relevant features for each prediction, enhancing the interpretability of complex models. However, such methods tend to produce misleading expl
Externí odkaz:
http://arxiv.org/abs/2407.11778
Open-domain complex Question Answering (QA) is a difficult task with challenges in evidence retrieval and reasoning. The complexity of such questions could stem from questions being compositional, hybrid evidence, or ambiguity in questions. While ret
Externí odkaz:
http://arxiv.org/abs/2406.17158
Autor:
Richtmann, Lea, Schmiesing, Viktoria-S., Wilken, Dennis, Heine, Jan, Tranter, Aaron, Anand, Avishek, Osborne, Tobias J., Heurs, Michèle
Experimental control involves a lot of manual effort with non-trivial decisions for precise adjustments. Here, we study the automatic experimental alignment for coupling laser light into an optical fiber using reinforcement learning (RL). We face sev
Externí odkaz:
http://arxiv.org/abs/2405.15421
Publikováno v:
Advances in Information Retrieval - 46th European Conference on Information Retrieval, {ECIR} 2024, Glasgow, UK, March 24-28, 2024, Proceedings, Part {IV}
Neural ranking models have become increasingly popular for real-world search and recommendation systems in recent years. Unlike their tree-based counterparts, neural models are much less interpretable. That is, it is very difficult to understand thei
Externí odkaz:
http://arxiv.org/abs/2405.07782
An important problem in text-ranking systems is handling the hard queries that form the tail end of the query distribution. The difficulty may arise due to the presence of uncommon, underspecified, or incomplete queries. In this work, we improve the
Externí odkaz:
http://arxiv.org/abs/2404.02587
Automated fact checking has gained immense interest to tackle the growing misinformation in the digital era. Existing systems primarily focus on synthetic claims on Wikipedia, and noteworthy progress has also been made on real-world claims. In this w
Externí odkaz:
http://arxiv.org/abs/2403.17169
Feature attributions are a commonly used explanation type, when we want to posthoc explain the prediction of a trained model. Yet, they are not very well explored in IR. Importantly, feature attribution has rarely been rigorously defined, beyond attr
Externí odkaz:
http://arxiv.org/abs/2403.16085
Large language models (LLMs) have recently gained significant attention due to their unparalleled ability to perform various natural language processing tasks. These models, benefiting from their advanced natural language understanding capabilities,
Externí odkaz:
http://arxiv.org/abs/2401.12078
Autor:
Leonhardt, Jurek, Müller, Henrik, Rudra, Koustav, Khosla, Megha, Anand, Abhijit, Anand, Avishek
Dual-encoder-based dense retrieval models have become the standard in IR. They employ large Transformer-based language models, which are notoriously inefficient in terms of resources and latency. We propose Fast-Forward indexes -- vector forward inde
Externí odkaz:
http://arxiv.org/abs/2311.01263