@inproceedings{kedzie-mckeown-2020-controllable,
title = "Controllable Meaning Representation to Text Generation: Linearization and Data Augmentation Strategies",
author = "Kedzie, Chris and
McKeown, Kathleen",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.419",
doi = "10.18653/v1/2020.emnlp-main.419",
pages = "5160--5185",
abstract = "We study the degree to which neural sequence-to-sequence models exhibit fine-grained controllability when performing natural language generation from a meaning representation. Using two task-oriented dialogue generation benchmarks, we systematically compare the effect of four input linearization strategies on controllability and faithfulness. Additionally, we evaluate how a phrase-based data augmentation method can improve performance. We find that properly aligning input sequences during training leads to highly controllable generation, both when training from scratch or when fine-tuning a larger pre-trained model. Data augmentation further improves control on difficult, randomly generated utterance plans.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kedzie-mckeown-2020-controllable">
<titleInfo>
<title>Controllable Meaning Representation to Text Generation: Linearization and Data Augmentation Strategies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Kedzie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kathleen</namePart>
<namePart type="family">McKeown</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We study the degree to which neural sequence-to-sequence models exhibit fine-grained controllability when performing natural language generation from a meaning representation. Using two task-oriented dialogue generation benchmarks, we systematically compare the effect of four input linearization strategies on controllability and faithfulness. Additionally, we evaluate how a phrase-based data augmentation method can improve performance. We find that properly aligning input sequences during training leads to highly controllable generation, both when training from scratch or when fine-tuning a larger pre-trained model. Data augmentation further improves control on difficult, randomly generated utterance plans.</abstract>
<identifier type="citekey">kedzie-mckeown-2020-controllable</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.419</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.419</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>5160</start>
<end>5185</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Controllable Meaning Representation to Text Generation: Linearization and Data Augmentation Strategies
%A Kedzie, Chris
%A McKeown, Kathleen
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F kedzie-mckeown-2020-controllable
%X We study the degree to which neural sequence-to-sequence models exhibit fine-grained controllability when performing natural language generation from a meaning representation. Using two task-oriented dialogue generation benchmarks, we systematically compare the effect of four input linearization strategies on controllability and faithfulness. Additionally, we evaluate how a phrase-based data augmentation method can improve performance. We find that properly aligning input sequences during training leads to highly controllable generation, both when training from scratch or when fine-tuning a larger pre-trained model. Data augmentation further improves control on difficult, randomly generated utterance plans.
%R 10.18653/v1/2020.emnlp-main.419
%U https://aclanthology.org/2020.emnlp-main.419
%U https://doi.org/10.18653/v1/2020.emnlp-main.419
%P 5160-5185
Markdown (Informal)
[Controllable Meaning Representation to Text Generation: Linearization and Data Augmentation Strategies](https://aclanthology.org/2020.emnlp-main.419) (Kedzie & McKeown, EMNLP 2020)
ACL