Results 1 to 10 of about 302,572 (324)
NLP Questions Answering Using DBpedia and YAGO [PDF]
In this paper, we present results of employing DBpedia and YAGO as lexical databases for answering questions formulated in the natural language. The proposed solution has been evaluated for answering class 1 and class 2 questions (out of 5 classes ...
Tomasz Boiński +5 more
doaj +1 more source
POS Tagging and its Applications for Mathematics
Content analysis of scientific publications is a nontrivial task, but a useful and important one for scientific information services. In the Gutenberg era it was a domain of human experts; in the digital age many machine-based methods, e.g., graph ...
J.C. Platt, T.D. Nguyen, U. Schöneberg
core +1 more source
Multiple-choice benchmarks are widely used to assess LLMs, yet their accuracy scores often conflate memorization—understood as pattern-based recall—with genuine reasoning, that is, inference beyond surface pattern transfer, especially when ...
Eva Sanchez Salido +2 more
doaj +1 more source
Using NLP technology in CALL [PDF]
This paper outlines the research and guiding research principles of the (I)CALL group at Dublin City University, Ireland. Our research activities include the development of (I)CALL systems targeted at a variety of user groups including advanced Romance ...
Greene, Cara N. +5 more
core +3 more sources
On Measuring Large Language Models Performance with Inferential Statistics
Measuring the reliability of performance evaluations is particularly important when we evaluate non-deterministic models. This is the case of using large language models (LLMs) in classification tasks, where different runs generate different outputs ...
Jesús M. Fraile-Hernández +1 more
doaj +1 more source
Natural Language Processing and Complex Network based Tourism Social Big Data Analysis [PDF]
Unlike traditional research methods such as questionnaire surveys and individual interviews, this article proposes a big data based analytical framework for tourism research.
Yin Lijie
doaj +1 more source
Towards Automatic Generation of Shareable Synthetic Clinical Notes Using Neural Language Models
Large-scale clinical data is invaluable to driving many computational scientific advances today. However, understandable concerns regarding patient privacy hinder the open dissemination of such data and give rise to suboptimal siloed research.
Melamud, Oren, Shivade, Chaitanya
core +1 more source
YouTube AV 50K: An Annotated Corpus for Comments in Autonomous Vehicles
With one billion monthly viewers, and millions of users discussing and sharing opinions, comments below YouTube videos are rich sources of data for opinion mining and sentiment analysis.
Choi, Minsoo +5 more
core +1 more source
A Spanish Language Proficiency Dataset for AI Evaluation
Benchmarking Spanish reading comprehension remains challenging due to the scarcity of proficiency-calibrated resources grounded in authentic human assessments. We introduce IC-UNED-RC-ES, a benchmark comprising more than 6000 items derived from Instituto
Anselmo Peñas +6 more
doaj +1 more source
Heavy quarkonium production and polarization
We present a perturbative QCD factorization formalism for the production of heavy quarkonia of large transverse momentum $p_T$ at collider energies, which includes both the leading power (LP) and next-to-leading power (NLP) contributions to the cross ...
Kang, Zhong-Bo +2 more
core +1 more source

