Results 61 to 70 of about 7,796 (230)
Conditional Text Generation for AI‐Powered Interviews: A T5‐Based System With GPT‐2 Comparison
Engineering Reports, Volume 8, Issue 4, April 2026.This work introduces an AI‐based interview system that uses T5 to generate context‐specific interview questions and responses. By comparing it with GPT‐2, the study shows T5's ability to produce more coherent and relevant dialogue, supporting advances in automated interview and conversational AI applications.
Kritika Acharya, Rashna K.C., Sudip Rana
wiley +1 more source
The data-driven Bulgarian WordNet: BTBWN
Cognitive Studies | Études cognitives, 2018 The data-driven Bulgarian WordNet: BTBWN The paper presents our work towards the simultaneous creation of a data-driven WordNet for Bulgarian and a manually annotated treebank with semantic information.
Petya Osenova, Kiril Simov
doaj +1 more source
SciLitMiner: An Intelligent System for Scientific Literature Mining and Knowledge Discovery
Advanced Intelligent Systems, Volume 8, Issue 3, March 2026.SciLitMiner is an intelligent system that federately ingests scientific literature, filters it using advanced information retrieval methods, and applies retrieval‐augmented generation tailored to scientific domains. Demonstrated on creep deformation in γ‐TiAl alloys, SciLitMiner provides a controlled workflow for systematic knowledge discovery and ...
Vipul Gupta +3 more
wiley +1 more source
The semantic classification of adjectives in the Bulgarian Wordnet: Towards a multiclass approach
Cognitive Studies | Études cognitives, 2018 The semantic classification of adjectives in the Bulgarian Wordnet: Towards a multiclass approach The paper presents an attempt at semantic classification of adjectives in the Bulgarian wordnet.
Tsvetana Dimitrova, Valentina Stefanova
doaj +1 more source
CPT: Pharmacometrics &Systems Pharmacology, Volume 15, Issue 3, March 2026.ABSTRACT The purpose was to evaluate retrieval‐augmented generative (RAG) artificial intelligence (AI) methods for assessing the regulatory compliance of drug information and adherence to best practices in clinical trial protocols. Integrated systems containing RAG and large language model (LLM) components were employed to evaluate drug information and
Shreyas Waikar +2 more
wiley +1 more source
Extending, trimming and fusing WordNet for technical documents [PDF]
, 2001 This paper describes a tool for the automatic extension and trimming of a multilingual WordNet database for cross-lingual retrieval and multilingual ontology building in intranets and domain-specific document collections.
Vossen, P., Vossen, P.; id_orcid
core
Communications of the ACM, 1992 Because meaningful sentences are composed of meaningful words, any system that hopes to process natural languages as people do must have information about words and their meanings. This information is traditionally provided through dictionaries, and machine-readable dictionaries are now widely available.
openaire +6 more sources
Increasing the Effectiveness of the Romanian Wordnet in NLP Applications [PDF]
Computer Science Journal of Moldova, 2013 The Romanian wordnet is a semantic network under ceaseless enrichment and improvement. Its use in various applications throughout time highlighted the need for further development. In this paper we focus on a question answering scenario.
Verginica Barbu Mititelu
doaj
Building an Arabic Sentiment Lexicon Using Semi-supervised Learning
Journal of King Saud University: Computer and Information Sciences, 2014 Sentiment analysis is the process of determining a predefined sentiment from text written in a natural language with respect to the entity to which it is referring. A number of lexical resources are available to facilitate this task in English.
Fawaz H.H. Mahyoub +2 more
doaj +1 more source
AI and Measurement Concerns: Dealing with Imbalanced Data in Autoscoring
Journal of Educational Measurement, Volume 63, Issue 1, Spring 2026.Abstract Unbiasedness for proficiency estimates is important for autoscoring engines since the outcome might be used for future learning or placement. Imbalanced training data may lead to certain biases and lower the prediction accuracy for classification algorithms.
Yunting Liu +3 more
wiley +1 more source