Graph neural networks for natural language processing: A survey

L Wu, Y Chen, K Shen, X Guo, H Gao… - … and Trends® in …, 2023 - nowpublishers.com
Deep learning has become the dominant approach in addressing various tasks in Natural
Language Processing (NLP). Although text inputs are typically represented as a sequence …

Graph pre-training for AMR parsing and generation

X Bai, Y Chen, Y Zhang - arXiv preprint arXiv:2203.07836, 2022 - arxiv.org
Abstract meaning representation (AMR) highlights the core semantic information of text in a
graph structure. Recently, pre-trained language models (PLMs) have advanced tasks of …

AMR-based network for aspect-based sentiment analysis

F Ma, X Hu, A Liu, Y Yang, SY Philip… - Proceedings of the 61st …, 2023 - aclanthology.org
Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment classification task.
Many recent works have used dependency trees to extract the relation between aspects and …

Structural adapters in pretrained language models for amr-to-text generation

LFR Ribeiro, Y Zhang, I Gurevych - arXiv preprint arXiv:2103.09120, 2021 - arxiv.org
Pretrained language models (PLM) have recently advanced graph-to-text generation, where
the input graph is linearized into a sequence and fed into the PLM to obtain its …

Semantic representation for dialogue modeling

X Bai, Y Chen, L Song, Y Zhang - arXiv preprint arXiv:2105.10188, 2021 - arxiv.org
Although neural models have achieved competitive results in dialogue systems, they have
shown limited ability in representing core semantics, such as ignoring important entities. To …

De-confounded variational encoder-decoder for logical table-to-text generation

W Chen, J Tian, Y Li, H He, Y Jin - … of the 59th Annual Meeting of …, 2021 - aclanthology.org
Logical table-to-text generation aims to automatically generate fluent and logically faithful
text from tables. The task remains challenging where deep learning models often generated …

Promoting graph awareness in linearized graph-to-text generation

A Hoyle, A Marasović, N Smith - arXiv preprint arXiv:2012.15793, 2020 - arxiv.org
Generating text from structured inputs, such as meaning representations or RDF triples, has
often involved the use of specialized graph-encoding neural networks. However, recent …

Abstract meaning representation of Turkish

E Oral, A Acar, G Eryiğit - Natural Language Engineering, 2024 - cambridge.org
Abstract meaning representation (AMR) is a graph-based sentence-level meaning
representation that has become highly popular in recent years. AMR is a knowledge-based …

Semantic-based pre-training for dialogue understanding

X Bai, L Song, Y Zhang - arXiv preprint arXiv:2209.09146, 2022 - arxiv.org
Pre-trained language models have made great progress on dialogue tasks. However, these
models are typically trained on surface dialogue text, thus are proven to be weak in …

Neural Methods for Data-to-text Generation

M Sharma, AK Gogineni, N Ramakrishnan - ACM Transactions on …, 2024 - dl.acm.org
The neural boom that has sparked natural language processing (NLP) research throughout
the last decade has similarly led to significant innovations in data-to-text generation (D2T) …