@inproceedings{jin-gildea-2020-generalized,
title = "Generalized Shortest-Paths Encoders for {AMR}-to-Text Generation",
author = "Jin, Lisa and
Gildea, Daniel",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.181",
doi = "10.18653/v1/2020.coling-main.181",
pages = "2004--2013",
abstract = "For text generation from semantic graphs, past neural models encoded input structure via gated convolutions along graph edges. Although these operations provide local context, the distance messages can travel is bounded by the number of encoder propagation steps. We adopt recent efforts of applying Transformer self-attention to graphs to allow global feature propagation. Instead of feeding shortest paths to the vertex self-attention module, we train a model to learn them using generalized shortest-paths algorithms. This approach widens the receptive field of a graph encoder by exposing it to all possible graph paths. We explore how this path diversity affects performance across levels of AMR connectivity, demonstrating gains on AMRs of higher reentrancy counts and diameters. Analysis of generated sentences also supports high semantic coherence of our models for reentrant AMRs. Our best model achieves a 1.4 BLEU and 1.8 chrF++ margin over a baseline that encodes only pairwise-unique shortest paths.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jin-gildea-2020-generalized">
<titleInfo>
<title>Generalized Shortest-Paths Encoders for AMR-to-Text Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lisa</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Gildea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-dec</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>For text generation from semantic graphs, past neural models encoded input structure via gated convolutions along graph edges. Although these operations provide local context, the distance messages can travel is bounded by the number of encoder propagation steps. We adopt recent efforts of applying Transformer self-attention to graphs to allow global feature propagation. Instead of feeding shortest paths to the vertex self-attention module, we train a model to learn them using generalized shortest-paths algorithms. This approach widens the receptive field of a graph encoder by exposing it to all possible graph paths. We explore how this path diversity affects performance across levels of AMR connectivity, demonstrating gains on AMRs of higher reentrancy counts and diameters. Analysis of generated sentences also supports high semantic coherence of our models for reentrant AMRs. Our best model achieves a 1.4 BLEU and 1.8 chrF++ margin over a baseline that encodes only pairwise-unique shortest paths.</abstract>
<identifier type="citekey">jin-gildea-2020-generalized</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.181</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.181</url>
</location>
<part>
<date>2020-dec</date>
<extent unit="page">
<start>2004</start>
<end>2013</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generalized Shortest-Paths Encoders for AMR-to-Text Generation
%A Jin, Lisa
%A Gildea, Daniel
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 dec
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F jin-gildea-2020-generalized
%X For text generation from semantic graphs, past neural models encoded input structure via gated convolutions along graph edges. Although these operations provide local context, the distance messages can travel is bounded by the number of encoder propagation steps. We adopt recent efforts of applying Transformer self-attention to graphs to allow global feature propagation. Instead of feeding shortest paths to the vertex self-attention module, we train a model to learn them using generalized shortest-paths algorithms. This approach widens the receptive field of a graph encoder by exposing it to all possible graph paths. We explore how this path diversity affects performance across levels of AMR connectivity, demonstrating gains on AMRs of higher reentrancy counts and diameters. Analysis of generated sentences also supports high semantic coherence of our models for reentrant AMRs. Our best model achieves a 1.4 BLEU and 1.8 chrF++ margin over a baseline that encodes only pairwise-unique shortest paths.
%R 10.18653/v1/2020.coling-main.181
%U https://aclanthology.org/2020.coling-main.181
%U https://doi.org/10.18653/v1/2020.coling-main.181
%P 2004-2013
Markdown (Informal)
[Generalized Shortest-Paths Encoders for AMR-to-Text Generation](https://aclanthology.org/2020.coling-main.181) (Jin & Gildea, COLING 2020)
ACL