Results 71 to 80 of about 9,135 (197)

A Hybrid Neuro-Symbolic Pipeline for Coreference Resolution and AMR-Based Semantic Parsing

Information
Large Language Models (LLMs) have transformed Natural Language Processing (NLP), yet they continue to struggle with deep semantic understanding, particularly in tasks like coreference resolution and structured semantic inference.
Christos Papakostas, Christos Troussas, Akrivi Krouska, Cleo Sgouropoulou   +3 more
doaj   +1 more source

A preliminary study in zero anaphora coreference resolution for Polish

Cognitive Studies | Études cognitives, 2017
A preliminary study in zero anaphora coreference resolution for Polish Zero anaphora is an element of the coreference resolution task that has not yet been directly addressed in Polish and, in most studies, it has been left as the most challenging ...
Adam Jan Kaczmarek, Michał Marcińczuk
doaj   +1 more source

Long Document Classification in the Transformer Era: A Survey on Challenges, Advances, and Open Issues

WIREs Data Mining and Knowledge Discovery, Volume 15, Issue 2, June 2025.
ABSTRACT Automatic Document Classification (ADC) refers to the process of automatically categorizing or labeling documents into predefined classes or categories. Its effectiveness may depend on various factors, including the models used for the formal representation of documents, the classification techniques applied, or a combination of both. Recently,
Renzo Alva Principe, Nicola Chiarini, Marco Viviani   +2 more
wiley   +1 more source

Mention Detection for Coreference Resolution in Polish. Development of the Formal Grammar

Cognitive Studies | Études cognitives, 2016
Mention Detection for Coreference Resolution in Polish. Development of the Formal Grammar This paper presents the results of an improvement and extension of the Shallow Grammar of Polish, designed for the needs of the Computer-based Methods for ...
Alicja Wójcicka, Mateusz Kopeć
doaj   +1 more source

Lexical Effects on Second Language Grammar Acquisition: Testing Psycholinguistic and Neurocognitive Predictions

Language Learning, Volume 75, Issue 2, Page 424-457, June 2025.
Abstract Second language (L2) grammar learning is difficult. Two frameworks—the psycholinguistic lexical bottleneck hypothesis and the neurocognitive declarative/procedural model—predict that faster L2 lexical processing should facilitate L2 incidental grammar learning.
Holger Hopp, Jana Reifegerste, Michael T. Ullman   +2 more
wiley   +1 more source

Coreference resolution in clinical discharge summaries, progress notes, surgical and pathology reports: a unified lexical approach [PDF]

, 2011
We developed a lexical rule-based system that uses a unified approach to resolving coreference across a wide variety of clinical records comprising discharge summaries, progress notes, pathology, radiology and surgical reports from two corpora (Ontology ...
Gooch, P., Roudsari, A.
core  

Disunity of personal taste

Mind &Language, Volume 40, Issue 3, Page 252-272, June 2025.
The article argues that, linguistically speaking, there is no uniform class of personal taste predicate. There is an F(un)‐type PPT that takes infinitive complements expressing events. In effect, these PPTs are predicates of events involving participants. There is also a T(asty)‐type that cannot take an infinitive complement and does not enter into the
John Collins
wiley   +1 more source

Unsupervised models for coreference resolution [PDF]

Proceedings of the Conference on Empirical Methods in Natural Language Processing - EMNLP '08, 2008
Traditional learning-based coreference resolvers operate by training a mention-pair classifier for determining whether two mentions are coreferent or not. Two independent lines of recent research have attempted to improve these mention-pair classifiers, one by learning a mention-ranking model to rank preceding mentions for a given anaphor, and the ...
openaire   +1 more source

Overcoming Data Shortage in Critical Domains With Data Augmentation for Natural Language Software Requirements

Journal of Software: Evolution and Process, Volume 37, Issue 5, May 2025.
This paper presents four different text augmentation algorithms (PARA, GPT, RTT, and EDA) applied to requirements from European space projects to increase the amount of available data. While the initial findings revealed low semantic preservation and high unpredictability, improvements such as a dynamic glossary led to increased quality.
Robin Korfmann, Patrick Beyersdorffer, Rainer Gerlich, Jürgen Münch, Marco Kuhrmann   +4 more
wiley   +1 more source

Research on Method for Fusion and Mapping of Cyberspace Assets Based on Knowledge Graph

IEEE Access
The fusion and mapping of cyberspace assets represent an effective means of organizing cyber assets and converging asset defense profiles. However, asset fusion and mapping in the context of Internet exposure encounters numerous challenges, including ...
Junyuan Yang, Chungui Li, Xingwen Chen, Kejiu Tan, Yuncheng Zhao, Huan Wang, Jie Wang   +6 more
doaj   +1 more source