@inproceedings{chen-etal-2019-enhancing,
title = "Enhancing Neural Data-To-Text Generation Models with External Background Knowledge",
author = "Chen, Shuang and
Wang, Jinpeng and
Feng, Xiaocheng and
Jiang, Feng and
Qin, Bing and
Lin, Chin-Yew",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1299",
doi = "10.18653/v1/D19-1299",
pages = "3022--3032",
abstract = "Recent neural models for data-to-text generation rely on massive parallel pairs of data and text to learn the writing knowledge. They often assume that writing knowledge can be acquired from the training data alone. However, when people are writing, they not only rely on the data but also consider related knowledge. In this paper, we enhance neural data-to-text models with external knowledge in a simple but effective way to improve the fidelity of generated text. Besides relying on parallel data and text as in previous work, our model attends to relevant external knowledge, encoded as a temporary memory, and combines this knowledge with the context representation of data before generating words. This allows the model to infer relevant facts which are not explicitly stated in the data table from an external knowledge source. Experimental results on twenty-one Wikipedia infobox-to-text datasets show our model, KBAtt, consistently improves a state-of-the-art model on most of the datasets. In addition, to quantify when and why external knowledge is effective, we design a metric, KBGain, which shows a strong correlation with the observed performance boost. This result demonstrates the relevance of external knowledge and sparseness of original data are the main factors affecting system performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2019-enhancing">
<titleInfo>
<title>Enhancing Neural Data-To-Text Generation Models with External Background Knowledge</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shuang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinpeng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaocheng</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Feng</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chin-Yew</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent neural models for data-to-text generation rely on massive parallel pairs of data and text to learn the writing knowledge. They often assume that writing knowledge can be acquired from the training data alone. However, when people are writing, they not only rely on the data but also consider related knowledge. In this paper, we enhance neural data-to-text models with external knowledge in a simple but effective way to improve the fidelity of generated text. Besides relying on parallel data and text as in previous work, our model attends to relevant external knowledge, encoded as a temporary memory, and combines this knowledge with the context representation of data before generating words. This allows the model to infer relevant facts which are not explicitly stated in the data table from an external knowledge source. Experimental results on twenty-one Wikipedia infobox-to-text datasets show our model, KBAtt, consistently improves a state-of-the-art model on most of the datasets. In addition, to quantify when and why external knowledge is effective, we design a metric, KBGain, which shows a strong correlation with the observed performance boost. This result demonstrates the relevance of external knowledge and sparseness of original data are the main factors affecting system performance.</abstract>
<identifier type="citekey">chen-etal-2019-enhancing</identifier>
<identifier type="doi">10.18653/v1/D19-1299</identifier>
<location>
<url>https://aclanthology.org/D19-1299</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>3022</start>
<end>3032</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Neural Data-To-Text Generation Models with External Background Knowledge
%A Chen, Shuang
%A Wang, Jinpeng
%A Feng, Xiaocheng
%A Jiang, Feng
%A Qin, Bing
%A Lin, Chin-Yew
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F chen-etal-2019-enhancing
%X Recent neural models for data-to-text generation rely on massive parallel pairs of data and text to learn the writing knowledge. They often assume that writing knowledge can be acquired from the training data alone. However, when people are writing, they not only rely on the data but also consider related knowledge. In this paper, we enhance neural data-to-text models with external knowledge in a simple but effective way to improve the fidelity of generated text. Besides relying on parallel data and text as in previous work, our model attends to relevant external knowledge, encoded as a temporary memory, and combines this knowledge with the context representation of data before generating words. This allows the model to infer relevant facts which are not explicitly stated in the data table from an external knowledge source. Experimental results on twenty-one Wikipedia infobox-to-text datasets show our model, KBAtt, consistently improves a state-of-the-art model on most of the datasets. In addition, to quantify when and why external knowledge is effective, we design a metric, KBGain, which shows a strong correlation with the observed performance boost. This result demonstrates the relevance of external knowledge and sparseness of original data are the main factors affecting system performance.
%R 10.18653/v1/D19-1299
%U https://aclanthology.org/D19-1299
%U https://doi.org/10.18653/v1/D19-1299
%P 3022-3032
Markdown (Informal)
[Enhancing Neural Data-To-Text Generation Models with External Background Knowledge](https://aclanthology.org/D19-1299) (Chen et al., EMNLP-IJCNLP 2019)
ACL
- Shuang Chen, Jinpeng Wang, Xiaocheng Feng, Feng Jiang, Bing Qin, and Chin-Yew Lin. 2019. Enhancing Neural Data-To-Text Generation Models with External Background Knowledge. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3022–3032, Hong Kong, China. Association for Computational Linguistics.