@inproceedings{yildirim-haug-2023-experiments,
title = "Experiments in training transformer sequence-to-sequence {DRS} parsers",
author = "Yildirim, Ahmet and
Haug, Dag",
editor = "Amblard, Maxime and
Breitholtz, Ellen",
booktitle = "Proceedings of the 15th International Conference on Computational Semantics",
month = jun,
year = "2023",
address = "Nancy, France",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.iwcs-1.9",
pages = "83--88",
abstract = "This work experiments with various configurations of transformer-based sequence-to-sequence neural networks in training a Discourse Representation Structure (DRS) parser, and presents the results along with the code to reproduce our experiments for use by the community working on DRS parsing. These are configurations that have not been tested in prior work on this task. The Parallel Meaning Bank (PMB) English data sets are used to train the models. The results are evaluated on the PMB test sets using Counter, the standard Evaluation tool for DRSs. We show that the performance improves upon the previous state of the art by 0.5 (F1 {\%}) for PMB 2.2.0 and 1.02 (F1 {\%}) for PMB 3.0.0 test sets. We also present results on PMB 4.0.0, which has not been evaluated using Counter in previous research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yildirim-haug-2023-experiments">
<titleInfo>
<title>Experiments in training transformer sequence-to-sequence DRS parsers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmet</namePart>
<namePart type="family">Yildirim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dag</namePart>
<namePart type="family">Haug</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Conference on Computational Semantics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maxime</namePart>
<namePart type="family">Amblard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ellen</namePart>
<namePart type="family">Breitholtz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Nancy, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This work experiments with various configurations of transformer-based sequence-to-sequence neural networks in training a Discourse Representation Structure (DRS) parser, and presents the results along with the code to reproduce our experiments for use by the community working on DRS parsing. These are configurations that have not been tested in prior work on this task. The Parallel Meaning Bank (PMB) English data sets are used to train the models. The results are evaluated on the PMB test sets using Counter, the standard Evaluation tool for DRSs. We show that the performance improves upon the previous state of the art by 0.5 (F1 %) for PMB 2.2.0 and 1.02 (F1 %) for PMB 3.0.0 test sets. We also present results on PMB 4.0.0, which has not been evaluated using Counter in previous research.</abstract>
<identifier type="citekey">yildirim-haug-2023-experiments</identifier>
<location>
<url>https://aclanthology.org/2023.iwcs-1.9</url>
</location>
<part>
<date>2023-06</date>
<extent unit="page">
<start>83</start>
<end>88</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Experiments in training transformer sequence-to-sequence DRS parsers
%A Yildirim, Ahmet
%A Haug, Dag
%Y Amblard, Maxime
%Y Breitholtz, Ellen
%S Proceedings of the 15th International Conference on Computational Semantics
%D 2023
%8 June
%I Association for Computational Linguistics
%C Nancy, France
%F yildirim-haug-2023-experiments
%X This work experiments with various configurations of transformer-based sequence-to-sequence neural networks in training a Discourse Representation Structure (DRS) parser, and presents the results along with the code to reproduce our experiments for use by the community working on DRS parsing. These are configurations that have not been tested in prior work on this task. The Parallel Meaning Bank (PMB) English data sets are used to train the models. The results are evaluated on the PMB test sets using Counter, the standard Evaluation tool for DRSs. We show that the performance improves upon the previous state of the art by 0.5 (F1 %) for PMB 2.2.0 and 1.02 (F1 %) for PMB 3.0.0 test sets. We also present results on PMB 4.0.0, which has not been evaluated using Counter in previous research.
%U https://aclanthology.org/2023.iwcs-1.9
%P 83-88
Markdown (Informal)
[Experiments in training transformer sequence-to-sequence DRS parsers](https://aclanthology.org/2023.iwcs-1.9) (Yildirim & Haug, IWCS 2023)
ACL