paper-with-me

홈 › Papers

MATERIALizing Cross-Language Information Retrieval: A Snapshot

2020-05-01 · LREC 2020 5 · Petra Galuscakova, Douglas Oard, Joe Barrow, Suraj Nair, Shing Han-Chin, Elena Zotkina, Esk, Ramy er, Rui Zhang

At about the midpoint of the IARPA MATERIAL program in October 2019, an evaluation was conducted on systems{'} abilities to find Lithuanian documents based on English queries. Subsequently, both the Lithuanian test collection and results from all three teams were made available for detailed analysis. This paper capitalizes on that opportunity to begin to look at what{'}s working well at this stage of the program, and to identify some promising directions for future work.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Information RetrievalRetrieval

Similar Papers 제목 키워드 기반

LENS: In-Context Search via Latent Evidence Exploration over Dynamic Raw Documents

2026-08-17 · Xingjun Wang, Gongsheng Li, Qi Fan, Yunlin Mao 외 arxiv

LLM agents increasingly answer questions over dynamic raw-document collections, where files may change before preprocessing, and relevant evidence (spans, sections, pages, or tables) is query-dependent. Existing retrieva…

Single Snapshot Distillation for Phase Coded Mask Design in Phase Retrieval

2025-05-23 · Karen Fonseca, Leon Suarez-Rodriguez, Andres Jerez, Felipe Gutierrez-Barragan 외

Phase retrieval (PR) reconstructs phase information from magnitude measurements, known as coded diffraction patterns (CDPs), whose quality depends on the number of snapshots captured using coded phase masks. High-quality…

global-optimizationKnowledge DistillationRetrieval

Gradient-free Task-Conditioned Retrieval for On-Device In-Context Learning

2026-07-30 · Xinyu Luo, Hui Liu, Yihua Shao, Junyi Yang 외 arxiv

On-device in-context learning (ICL) relies on pre-inference retrieval to select demonstrations for useful context before downstream model inference. This retrieval must exploit task-specific information while operating o…

Still Fresh? Evaluating Temporal Drift in Retrieval Benchmarks

2026-03-04 · Nathan Kuissi, Suraj Subrahmanyan, Nandan Thakur, Jimmy Lin arxiv

Information retrieval (IR) benchmarks typically follow the Cranfield paradigm, relying on static and predefined corpora. However, temporal changes in technical corpora, such as API deprecations and code reorganizations, …

Information Retrieval

SeKV: Resolution-Adaptive KV Cache with Hierarchical Semantic Memory for Long-Context LLM Inference

2026-06-30 · Amirhossein Abaskohi, Giuseppe Carenini, Peter West, Yuhang He hf

Large language models increasingly operate over long contexts, where the KV cache becomes a dominant memory bottleneck: its size grows linearly with sequence length and must be retained throughout decoding, making full G…