@inproceedings{feng-etal-2024-retrieval,
title = "Retrieval-Augmented Modular Prompt Tuning for Low-Resource Data-to-Text Generation",
author = "Feng, Ruitao and
Hong, Xudong and
Jobanputra, Mayank and
Warning, Mattes and
Demberg, Vera",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1224/",
pages = "14053--14062",
abstract = "Data-to-text (D2T) generation describes the task of verbalizing data, often given as attribute-value pairs. While this task is relevant for many different data domains beyond the traditionally well-explored tasks of weather forecasting, restaurant recommendations, and sports reporting, a major challenge to the applicability of data-to-text generation methods is typically data sparsity. For many applications, there is extremely little training data in terms of attribute-value inputs and target language outputs available for training a model. Given the sparse data setting, recently developed prompting methods seem most suitable for addressing D2T tasks since they do not require substantial amounts of training data, unlike finetuning approaches. However, prompt-based approaches are also challenging, as a) the design and search of prompts are non-trivial; and b) hallucination problems may occur because of the strong inductive bias of these models. In this paper, we propose a retrieval-augmented modular prompt tuning () method, which constructs prompts that fit the input data closely, thereby bridging the domain gap between the large-scale language model and the structured input data. Experiments show that our method generates texts with few hallucinations and achieves state-of-the-art performance on a dataset for drone handover message generation."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="feng-etal-2024-retrieval">
<titleInfo>
<title>Retrieval-Augmented Modular Prompt Tuning for Low-Resource Data-to-Text Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruitao</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xudong</namePart>
<namePart type="family">Hong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mayank</namePart>
<namePart type="family">Jobanputra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mattes</namePart>
<namePart type="family">Warning</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Data-to-text (D2T) generation describes the task of verbalizing data, often given as attribute-value pairs. While this task is relevant for many different data domains beyond the traditionally well-explored tasks of weather forecasting, restaurant recommendations, and sports reporting, a major challenge to the applicability of data-to-text generation methods is typically data sparsity. For many applications, there is extremely little training data in terms of attribute-value inputs and target language outputs available for training a model. Given the sparse data setting, recently developed prompting methods seem most suitable for addressing D2T tasks since they do not require substantial amounts of training data, unlike finetuning approaches. However, prompt-based approaches are also challenging, as a) the design and search of prompts are non-trivial; and b) hallucination problems may occur because of the strong inductive bias of these models. In this paper, we propose a retrieval-augmented modular prompt tuning () method, which constructs prompts that fit the input data closely, thereby bridging the domain gap between the large-scale language model and the structured input data. Experiments show that our method generates texts with few hallucinations and achieves state-of-the-art performance on a dataset for drone handover message generation.</abstract>
<identifier type="citekey">feng-etal-2024-retrieval</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1224/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>14053</start>
<end>14062</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Retrieval-Augmented Modular Prompt Tuning for Low-Resource Data-to-Text Generation
%A Feng, Ruitao
%A Hong, Xudong
%A Jobanputra, Mayank
%A Warning, Mattes
%A Demberg, Vera
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F feng-etal-2024-retrieval
%X Data-to-text (D2T) generation describes the task of verbalizing data, often given as attribute-value pairs. While this task is relevant for many different data domains beyond the traditionally well-explored tasks of weather forecasting, restaurant recommendations, and sports reporting, a major challenge to the applicability of data-to-text generation methods is typically data sparsity. For many applications, there is extremely little training data in terms of attribute-value inputs and target language outputs available for training a model. Given the sparse data setting, recently developed prompting methods seem most suitable for addressing D2T tasks since they do not require substantial amounts of training data, unlike finetuning approaches. However, prompt-based approaches are also challenging, as a) the design and search of prompts are non-trivial; and b) hallucination problems may occur because of the strong inductive bias of these models. In this paper, we propose a retrieval-augmented modular prompt tuning () method, which constructs prompts that fit the input data closely, thereby bridging the domain gap between the large-scale language model and the structured input data. Experiments show that our method generates texts with few hallucinations and achieves state-of-the-art performance on a dataset for drone handover message generation.
%U https://aclanthology.org/2024.lrec-main.1224/
%P 14053-14062
Markdown (Informal)
[Retrieval-Augmented Modular Prompt Tuning for Low-Resource Data-to-Text Generation](https://aclanthology.org/2024.lrec-main.1224/) (Feng et al., LREC-COLING 2024)
ACL