Results 21 to 30 of about 8,669 (85)

Bag-of-Word approach is not dead: A performance analysis on a myriad of text classification challenges

Natural Language Processing Journal
The Bag-of-Words (BoW) representation, enhanced with a classifier, was a pioneering approach to solving text classification problems. However, with the advent of transformers and, in general, deep learning architectures, the field has dynamically shifted
Mario Graff, Daniela Moctezuma, Eric S. Téllez   +2 more
doaj   +1 more source

Dealing with common ground in Human Translation and Neural Machine Translation: A case study on Italian equivalents of German Modal Particles

AI-Linguistica
The purpose of this chapter is to examine the neural machine translation of modal particles and to compare it to human translation. The quantitatively-oriented study focuses on Italian lexical translation equivalents of German eben and einfach.
Franz Meier
doaj   +1 more source

A Graph-based Model for Joint Chinese Word Segmentation and Dependency Parsing

Transactions of the Association for Computational Linguistics, 2020
Chinese word segmentation and dependency parsing are two fundamental tasks for Chinese natural language processing. The dependency parsing is defined at the word-level.
Yan, Hang, Qiu, Xipeng, Huang, Xuanjing
doaj   +1 more source

Exploiting ChatGPT to simplify Italian bureaucratic and professional texts

AI-Linguistica
This paper investigates the use of ChatGPT, a large language model, for simplifying long sentences and nominal clusters in professional texts belonging to administrative and legal domains.
Walter Paci, Lorenzo Gregori, Giovanni Acerboni, Alessandro Panunzi, Maria Roberta Perugini   +4 more
doaj   +1 more source

Membership Inference Attacks on Sequence-to-Sequence Models: Is My Data In Your Machine Translation System?

Transactions of the Association for Computational Linguistics, 2020
Data privacy is an important issue for “machine learning as a service” providers. We focus on the problem of membership inference attacks: Given a data sample and black-box access to a model’s API, determine whether the sample existed in the model’s ...
Hisamoto, Sorami, Post, Matt, Duh, Kevin
doaj   +1 more source

The fine art of fine-tuning: A structured review of advanced LLM fine-tuning techniques

Natural Language Processing Journal
Transformer-based models have consistently demonstrated superior accuracy compared to various traditional models across a range of downstream tasks.
Samar Pratap, Alston Richard Aranha, Divyanshu Kumar, Gautam Malhotra, Anantharaman Palacode Narayana Iyer, Shylaja S.S.   +5 more
doaj   +1 more source

Machine Learning–Driven Language Assessment

Transactions of the Association for Computational Linguistics, 2020
We describe a method for rapidly creating language proficiency assessments, and provide experimental evidence that such tests can be valid, reliable, and secure.
Settles, Burr, T. LaFlair, Geoffrey, Hagiwara, Masato   +2 more
doaj   +1 more source

A novel Data Extraction Framework Using Natural Language Processing (DEFNLP) techniques

Natural Language Processing Journal
Evidence through data is critical if government has to address threats faced by the nation, such as pandemics or climate change. Yet several facts about data necessary to inform evidence and science are locked inside publications.
Tayyaba Hussain, Muhammad Usman Akram, Anum Abdul Salam   +2 more
doaj   +1 more source

It is all in the [MASK]: Simple instruction-tuning enables BERT-like masked language models as generative classifiers

Natural Language Processing Journal
While encoder-only models such as BERT and ModernBERT are ubiquitous in real-world NLP applications, their conventional reliance on task-specific classification heads can limit their applicability compared to decoder-based large language models (LLMs ...
Benjamin Clavié, Nathan Cooper, Benjamin Warner   +2 more
doaj   +1 more source

A transformer based multi task learning approach to multimodal hate speech detection

Natural Language Processing Journal
Online hate speech has become a major social issue in recent years, affecting both individuals and society as a whole. Memes are a multimodal kind of internet hate speech that is growing more common. Online memes are often entertaining and harmless.
Prashant Kapil, Asif Ekbal
doaj   +1 more source