A Study on Self-attention Mechanism for AMR-to-text Generation

Sinh, Vu Trong; Nguyen, Le-Minh

doi:10.1007/978-3-030-23281-8_27

Cited by 3 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have found 10 out of 90 papers have main purpose to balance the dataset [6], [51], [69], [85], [86], [118], [121], [132], out 90 papers have worked on data to text [48], [56], [65], [83], [103], [105], [111], [129], and speech to text [68], [84], [101], [106]- [108], [113], [116], respectively.7 papers have worked on script writing [3], [17], [58], [61], [86], 5 papers have worked on machine translation [10], [11], [57], [88], [104], [123]. Apart from these, 4 papers have worked on text summarization [50], [88], [100], [130] and 2 papers [1], [91] have worked on abstract meaning representation (AMR)-AMR to text goal is to generate sentences from abstract meaning representation graphs and its seq2seq or graph2seq problem. In addition, we found 2 applications of product reviews [133], [133] of mobile devices that have worked in text generation.…”

Section: Metrics Groupmentioning

confidence: 99%

See 1 more Smart Citation

A Systematic Literature Review on Text Generation Using Deep Neural Network Models

et al. 2022

View full text Add to dashboard Cite

In recent years, significant progress has been made in text generation. The latest text generation models are revolutionizing the domain by generating human-like text. It has gained wide popularity recently in many domains like news, social networks, movie script writing, poetry composition, to name a few. The application of text generation in various fields has resulted in a lot of interest from the scientific community in this area. To the best of our knowledge, there is a lack of extensive review and up-to-date body of knowledge of text generation deep learning models. Therefore, this paper aims to bring together all the relevant work in a systematic mapping study highlighting key contributions from various researchers over the years, focusing on the past, present, and future trends. In this work, we have identified 90 primary studies from 2015 to 2021 employing the PRISMA framework. We also identified research gaps that are further needed to be explored by the research community. In the end, we provide some future directions for researchers and guidelines for practitioners based on the findings of this review.

show abstract

Section: Metrics Groupmentioning

confidence: 99%

“…It is known for semantics. However, many authors have validated the quality of generated text by using BLEU matrix [91]. 4) Limited resources Lack of resources such as dictionaries, POS taggers for low-resource languages such as Bengali, Arabic, Russian, Korean, Slovak, Spanish, Czech, German, Urdu, Hindi, Macedonian, etc.…”

Section: Identified Gapsmentioning

confidence: 99%

A Systematic Literature Review on Text Generation Using Deep Neural Network Models

et al. 2022

View full text Add to dashboard Cite

show abstract

Machine Learning for Identifying Abusive Content in Text Data

Nayak

Baek

2022

Learning and Analytics in Intelligent Systems

View full text Add to dashboard Cite

GPT-too: A Language-Model-First Approach for AMR-to-Text Generation

Mager¹,

Astudillo²,

Naseem³

et al. 2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

Meaning Representations (AMRs) are broad-coverage sentence-level semantic graphs. Existing approaches to generating text from AMR have focused on training sequenceto-sequence or graph-to-sequence models on AMR annotated data only. In this paper, we propose an alternative approach that combines a strong pre-trained language model with cycle consistency-based re-scoring. Despite the simplicity of the approach, our experimental results show these models outperform all previous techniques on the English LDC2017T10 dataset, including the recent use of transformer architectures. In addition to the standard evaluation metrics, we provide human evaluation experiments that further substantiate the strength of our approach.

show abstract

A Study on Self-attention Mechanism for AMR-to-text Generation

Cited by 3 publications

References 13 publications

A Systematic Literature Review on Text Generation Using Deep Neural Network Models

A Systematic Literature Review on Text Generation Using Deep Neural Network Models

Machine Learning for Identifying Abusive Content in Text Data

GPT-too: A Language-Model-First Approach for AMR-to-Text Generation

Contact Info

Product

Resources

About