State-of-the-art generalisation research in NLP: a taxonomy and review

D Hupkes, M Giulianelli, V Dankers, M Artetxe… - arxiv preprint arxiv …, 2022 - arxiv.org
The ability to generalise well is one of the primary desiderata of natural language
processing (NLP). Yet, what'good generalisation'entails and how it should be evaluated is …

An overview of sentence ordering task

Y Shi, H Zhang, N Li, T Yang - International Journal of Data Science and …, 2024 - Springer
The sentence ordering task aims to organize complex, unordered sentences into readable
text. This improves accuracy, validity, and reliability in various natural language processing …

Reading order detection in visually-rich documents with multi-modal layout-aware relation prediction

L Qiao, C Li, Z Cheng, Y Xu, Y Niu, X Li - Pattern Recognition, 2024 - Elsevier
Reading order detection aims to arrange the text logically, which is essential in
understanding visual documents. Current methods mostly model the problem as a sequence …

Pointer-Guided Pre-training: Infusing Large Language Models with Paragraph-Level Contextual Awareness

L Hillebrand, P Pradhan, C Bauckhage… - Joint European Conference …, 2024 - Springer
We introduce “pointer-guided segment ordering”(SO), a novel pre-training technique aimed
at enhancing the contextual understanding of paragraph-level text representations in large …

[HTML][HTML] Positional diffusion: Graph-based diffusion models for set ordering

F Giuliari, G Scarpellini, S Fiorini, S James… - Pattern Recognition …, 2024 - Elsevier
Positional reasoning is the process of ordering an unsorted set of parts into a consistent
structure. To address this problem, we present Positional Diffusion, a plug-and-play graph …

Positional diffusion: Ordering unordered sets with diffusion probabilistic models

F Giuliari, G Scarpellini, S James, Y Wang… - arxiv preprint arxiv …, 2023 - arxiv.org
Positional reasoning is the process of ordering unsorted parts contained in a set into a
consistent structure. We present Positional Diffusion, a plug-and-play graph formulation with …

Facing Data Scarcity in Dialogues for Discourse Structure Discovery and Prediction

C Li - 2023 - theses.hal.science
A document is more than a random combination of sentences. It is, instead, a cohesive entity
where sentences interact with each other to create a coherent structure and convey specific …

A framework for crafting data narratives

F El Outa - 2023 - hal.science
The world is filled with an overwhelming amount of information, and making sense of it all is
a significant challenge. Narratives have long been recognized as powerful tools of …

Ordering Problems in Natural Language Generation

F Farahnak - 2023 - spectrum.library.concordia.ca
Language is the main mechanism used in human communication. For decades, researchers
have tried to build computers capable of communicating with humans in natural languages …

[PDF][PDF] State-of-the-art generalisation research in NLP

D Hupkes, M Giulianelli, V Dankers, M Artetxe, Y Elazar… - genbench.org
The ability to generalise well is one of the primary desiderata of natural language
processing (NLP). Yet, what 'good generalisation'entails and how it should be evaluated is …