A systematic review of multidimensional relevance estimation in information retrieval
In information retrieval, relevance is perceived as a multidimensional and dynamic concept
influenced by user, task, and domain factors. Relying on this perspective, researchers have …
influenced by user, task, and domain factors. Relying on this perspective, researchers have …
Unifying Token-and Span-level Supervisions for Few-shot Sequence Labeling
Few-shot sequence labeling aims to identify novel classes based on only a few labeled
samples. Existing methods solve the data scarcity problem mainly by designing token-level …
samples. Existing methods solve the data scarcity problem mainly by designing token-level …
Learning structural co-occurrences for structured web data extraction in low-resource settings
Extracting structured information from all manner of webpages is an important problem with
the potential to automate many real-world applications. Recent work has shown the …
the potential to automate many real-world applications. Recent work has shown the …
Fast and Multi-aspect Mining of Complex Time-stamped Event Streams
Given a huge, online stream of time-evolving events with multiple attributes, such as online
shop** logs:(item, price, brand, time), how can we summarize large, dynamic high-order …
shop** logs:(item, price, brand, time), how can we summarize large, dynamic high-order …
Improving Retrieval in Theme-specific Applications using a Corpus Topical Taxonomy
Document retrieval has greatly benefited from the advancements of large-scale pre-trained
language models (PLMs). However, their effectiveness is often limited in theme-specific …
language models (PLMs). However, their effectiveness is often limited in theme-specific …
Enhancing BERTopic with Pre-Clustered Knowledge: Reducing Feature Sparsity in Short Text Topic Modeling
Q Wang, B Ma - Journal of Data Analysis and Information Processing, 2024 - scirp.org
Modeling topics in short texts presents significant challenges due to feature sparsity,
particularly when analyzing content generated by large-scale online users. This sparsity can …
particularly when analyzing content generated by large-scale online users. This sparsity can …
[PDF][PDF] TRIO: An Entity Retrieval Method Using Entity Embedding and Topic Modeling
Current entity search models predominantly rely on term frequency and semantic similarity,
often failing to fully exploit the information in the knowledge graphs. This limitation leads to …
often failing to fully exploit the information in the knowledge graphs. This limitation leads to …
[PDF][PDF] Smart Chatbot with Document Retrieval and Extractive Question Answering
MVBDSP Godse - pijet.org
Support engineers on various projects deal with many problems while carrying out their
daily work. When they face an issue in a project, they have to read a large amount of …
daily work. When they face an issue in a project, they have to read a large amount of …
[معلومات الإصدار][C] Improving biomedical literature search engines for medical professionals
S Frihat - Dissertation, Duisburg, Essen …