@inproceedings{xiang-etal-2022-asdot,
title = "{ASDOT}: Any-Shot Data-to-Text Generation with Pretrained Language Models",
author = "Xiang, Jiannan and
Liu, Zhengzhong and
Zhou, Yucheng and
Xing, Eric and
Hu, Zhiting",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.136",
doi = "10.18653/v1/2022.findings-emnlp.136",
pages = "1886--1899",
abstract = "Data-to-text generation is challenging due to the great variety of the input data in terms of domains (e.g., finance vs sports) or schemata (e.g., diverse predicates). Recent end-to-end neural methods thus require substantial training examples to learn to disambiguate and describe the data. Yet, real-world data-to-text problems often suffer from various data-scarce issues: one may have access to only a handful of or no training examples, and/or have to rely on examples in a different domain or schema. To fill this gap, we propose Any-Shot Data-to-Text (ASDOT), a new approach flexibly applicable to diverse settings by making efficient use of any given (or no) examples. ASDOT consists of two steps, data disambiguation and sentence fusion, both of which are amenable to be solved with off-the-shelf pretrained language models (LMs) with optional finetuning. In the data disambiguation stage, we employ the prompted GPT-3 model to understand possibly ambiguous triples from the input data and convert each into a short sentence with reduced ambiguity. The sentence fusion stage then uses an LM like T5 to fuse all the resulting sentences into a coherent paragraph as the final description. We evaluate extensively on various datasets in different scenarios, including the zero-/few-/full-shot settings, and generalization to unseen predicates and out-of-domain data. Experimental results show that ASDOT consistently achieves significant improvement over baselines, e.g., a 30.81 BLEU gain on the DART dataset under the zero-shot setting.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xiang-etal-2022-asdot">
<titleInfo>
<title>ASDOT: Any-Shot Data-to-Text Generation with Pretrained Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiannan</namePart>
<namePart type="family">Xiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengzhong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yucheng</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Xing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiting</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Data-to-text generation is challenging due to the great variety of the input data in terms of domains (e.g., finance vs sports) or schemata (e.g., diverse predicates). Recent end-to-end neural methods thus require substantial training examples to learn to disambiguate and describe the data. Yet, real-world data-to-text problems often suffer from various data-scarce issues: one may have access to only a handful of or no training examples, and/or have to rely on examples in a different domain or schema. To fill this gap, we propose Any-Shot Data-to-Text (ASDOT), a new approach flexibly applicable to diverse settings by making efficient use of any given (or no) examples. ASDOT consists of two steps, data disambiguation and sentence fusion, both of which are amenable to be solved with off-the-shelf pretrained language models (LMs) with optional finetuning. In the data disambiguation stage, we employ the prompted GPT-3 model to understand possibly ambiguous triples from the input data and convert each into a short sentence with reduced ambiguity. The sentence fusion stage then uses an LM like T5 to fuse all the resulting sentences into a coherent paragraph as the final description. We evaluate extensively on various datasets in different scenarios, including the zero-/few-/full-shot settings, and generalization to unseen predicates and out-of-domain data. Experimental results show that ASDOT consistently achieves significant improvement over baselines, e.g., a 30.81 BLEU gain on the DART dataset under the zero-shot setting.</abstract>
<identifier type="citekey">xiang-etal-2022-asdot</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.136</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.136</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>1886</start>
<end>1899</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ASDOT: Any-Shot Data-to-Text Generation with Pretrained Language Models
%A Xiang, Jiannan
%A Liu, Zhengzhong
%A Zhou, Yucheng
%A Xing, Eric
%A Hu, Zhiting
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F xiang-etal-2022-asdot
%X Data-to-text generation is challenging due to the great variety of the input data in terms of domains (e.g., finance vs sports) or schemata (e.g., diverse predicates). Recent end-to-end neural methods thus require substantial training examples to learn to disambiguate and describe the data. Yet, real-world data-to-text problems often suffer from various data-scarce issues: one may have access to only a handful of or no training examples, and/or have to rely on examples in a different domain or schema. To fill this gap, we propose Any-Shot Data-to-Text (ASDOT), a new approach flexibly applicable to diverse settings by making efficient use of any given (or no) examples. ASDOT consists of two steps, data disambiguation and sentence fusion, both of which are amenable to be solved with off-the-shelf pretrained language models (LMs) with optional finetuning. In the data disambiguation stage, we employ the prompted GPT-3 model to understand possibly ambiguous triples from the input data and convert each into a short sentence with reduced ambiguity. The sentence fusion stage then uses an LM like T5 to fuse all the resulting sentences into a coherent paragraph as the final description. We evaluate extensively on various datasets in different scenarios, including the zero-/few-/full-shot settings, and generalization to unseen predicates and out-of-domain data. Experimental results show that ASDOT consistently achieves significant improvement over baselines, e.g., a 30.81 BLEU gain on the DART dataset under the zero-shot setting.
%R 10.18653/v1/2022.findings-emnlp.136
%U https://aclanthology.org/2022.findings-emnlp.136
%U https://doi.org/10.18653/v1/2022.findings-emnlp.136
%P 1886-1899
Markdown (Informal)
[ASDOT: Any-Shot Data-to-Text Generation with Pretrained Language Models](https://aclanthology.org/2022.findings-emnlp.136) (Xiang et al., Findings 2022)
ACL