Zobrazeno 1 - 10
of 402
pro vyhledávání: '"FRIEDER, OPHIR"'
Publikováno v:
ACM Symposium on Document Engineering 2024 (DocEng '24), August 20-23, 2024, San Jose, CA, USA. ACM, New York, NY, USA
Sparse retrieval methods like BM25 are based on lexical overlap, focusing on the surface form of the terms that appear in the query and the document. The use of inverted indices in these methods leads to high retrieval efficiency. On the other hand,
Externí odkaz:
http://arxiv.org/abs/2409.05882
Publikováno v:
The Second Workshop on Generative Information Retrieval at ACM SIGIR 2024
Generative language models hallucinate. That is, at times, they generate factually flawed responses. These inaccuracies are particularly insidious because the responses are fluent and well-articulated. We focus on the task of Grounded Answer Generati
Externí odkaz:
http://arxiv.org/abs/2409.00085
Retrieval approaches that score documents based on learned dense vectors (i.e., dense retrieval) rather than lexical signals (i.e., conventional retrieval) are increasingly popular. Their ability to identify related documents that do not necessarily
Externí odkaz:
http://arxiv.org/abs/2307.16779
Autor:
Frieder, Ophir, Mele, Ida, Muntean, Cristina Ioana, Nardini, Franco Maria, Perego, Raffaele, Tonellotto, Nicola
Rapid response, namely low latency, is fundamental in search applications; it is particularly so in interactive search sessions, such as those encountered in conversational settings. An observation with a potential to reduce latency asserts that conv
Externí odkaz:
http://arxiv.org/abs/2211.14155
Learning Electronic Health Records (EHRs) representation is a preeminent yet under-discovered research topic. It benefits various clinical decision support applications, e.g., medication outcome prediction or patient similarity search. Current approa
Externí odkaz:
http://arxiv.org/abs/2209.00655
Content moderation (removing or limiting the distribution of posts based on their contents) is one tool social networks use to fight problems such as harassment and disinformation. Manually screening all content is usually impractical given the scale
Externí odkaz:
http://arxiv.org/abs/2108.12752
Technology-assisted review (TAR) workflows based on iterative active learning are widely used in document review applications. Most stopping rules for one-phase TAR workflows lack valid statistical guarantees, which has discouraged their use in some
Externí odkaz:
http://arxiv.org/abs/2108.12746
Technology-assisted review (TAR) refers to human-in-the-loop active learning workflows for finding relevant documents in large collections. These workflows often must meet a target for the proportion of relevant documents found (i.e. recall) while al
Externí odkaz:
http://arxiv.org/abs/2106.09871
Technology-assisted review (TAR) refers to human-in-the-loop machine learning workflows for document review in legal discovery and other high recall review tasks. Attorneys and legal technologists have debated whether review should be a single iterat
Externí odkaz:
http://arxiv.org/abs/2106.09866
Technology-assisted review (TAR) refers to iterative active learning workflows for document review in high recall retrieval (HRR) tasks. TAR research and most commercial TAR software have applied linear models such as logistic regression to lexical f
Externí odkaz:
http://arxiv.org/abs/2105.01044