Learning Embeddings to lexicalise RDF Properties

Perez-Beltrachini, Laura; Gardent, Claire

doi:10.18653/v1/s16-2027

Cited by 6 publications

(1 citation statement)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other work has sought to address the issue of content selection for corpus creation, independent of the actual text to be associated with each MR (see also Gkatzia, 2016). For example, Perez-Beltrachini et al (2016) leverage DBPedia to construct trees of semantic triples based on their frequency and relationship to one another in a large ontology, with the goal of selecting content which forms a natural unit that can be later associated with a human-written text.…”

Section: Corpora For Nlgmentioning

confidence: 99%

Most NLG is Low-Resource: here’s what we can do about it

Howcroft¹,

Gkatzia²

2022

Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)

View full text Add to dashboard Cite

Many domains and tasks in natural language generation (NLG) are inherently 'lowresource', where training data, tools and linguistic analyses are scarce. This poses a particular challenge to researchers and system developers in the era of machine-learning-driven NLG. In this position paper, we initially present the challenges researchers & developers often encounter when dealing with low-resource settings in NLG. We then argue that it is unsustainable to collect large aligned datasets or build large language models from scratch for every possible domain due to cost, labour, and time constraints, so researching and developing methods and resources for low-resource settings is vital. We then discuss current approaches to low-resource NLG, followed by proposed solutions and promising avenues for future work in NLG for low-resource settings.

show abstract

Section: Corpora For Nlgmentioning

confidence: 99%

Most NLG is Low-Resource: here’s what we can do about it

Howcroft¹,

Gkatzia²

2022

Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)

View full text Add to dashboard Cite

show abstract

Selected Challenges in Grammar-Based Text Generation from the Semantic Web

Mille¹

2019

Artificial Intelligence

View full text Add to dashboard Cite

Bootstrapping Generators from Noisy Data

Perez-Beltrachini¹,

Lapata²

2018

Proceedings of the 2018 Conference of the North American Chapter Of the Association for Computational Linguistics: Hu

Self Cite

View full text Add to dashboard Cite

A core step in statistical data-to-text generation concerns learning correspondences between structured data representations (e.g., facts in a database) and associated texts. In this paper we aim to bootstrap generators from large scale datasets where the data (e.g., DBPedia facts) and related texts (e.g., Wikipedia abstracts) are loosely aligned. We tackle this challenging task by introducing a special-purpose content selection mechanism. 1 We use multi-instance learning to automatically discover correspondences between data and text pairs and show how these can be used to enhance the content signal while training an encoder-decoder architecture. Experimental results demonstrate that models trained with content-specific objectives improve upon a vanilla encoder-decoder which solely relies on soft attention.

show abstract

Learning Embeddings to lexicalise RDF Properties

Cited by 6 publications

References 11 publications

Most NLG is Low-Resource: here’s what we can do about it

Most NLG is Low-Resource: here’s what we can do about it

Selected Challenges in Grammar-Based Text Generation from the Semantic Web

Bootstrapping Generators from Noisy Data

Contact Info

Product

Resources

About