@inproceedings{salam-etal-2021-generating,
title = "Generating and Modifying Natural Language Explanations",
author = "Salam, Abdus and
Schwitter, Rolf and
Orgun, Mehmet",
editor = "Rahimi, Afshin and
Lane, William and
Zuccon, Guido",
booktitle = "Proceedings of the 19th Annual Workshop of the Australasian Language Technology Association",
month = dec,
year = "2021",
address = "Online",
publisher = "Australasian Language Technology Association",
url = "https://aclanthology.org/2021.alta-1.15",
pages = "149--157",
abstract = "HESIP is a hybrid explanation system for image predictions that combines sub-symbolic and symbolic machine learning techniques to explain the predictions of image classification tasks. The sub-symbolic component makes a prediction for an image and the symbolic component learns probabilistic symbolic rules in order to explain that prediction. In HESIP, the explanations are generated in controlled natural language from the learned probabilistic rules using a bi-directional logic grammar. In this paper, we present an explanation modification method where a human-in-the-loop can modify an incorrect explanation generated by the HESIP system and afterwards, the modified explanation is used by HESIP to learn a better explanation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="salam-etal-2021-generating">
<titleInfo>
<title>Generating and Modifying Natural Language Explanations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdus</namePart>
<namePart type="family">Salam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rolf</namePart>
<namePart type="family">Schwitter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mehmet</namePart>
<namePart type="family">Orgun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Annual Workshop of the Australasian Language Technology Association</title>
</titleInfo>
<name type="personal">
<namePart type="given">Afshin</namePart>
<namePart type="family">Rahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="family">Lane</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guido</namePart>
<namePart type="family">Zuccon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Australasian Language Technology Association</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>HESIP is a hybrid explanation system for image predictions that combines sub-symbolic and symbolic machine learning techniques to explain the predictions of image classification tasks. The sub-symbolic component makes a prediction for an image and the symbolic component learns probabilistic symbolic rules in order to explain that prediction. In HESIP, the explanations are generated in controlled natural language from the learned probabilistic rules using a bi-directional logic grammar. In this paper, we present an explanation modification method where a human-in-the-loop can modify an incorrect explanation generated by the HESIP system and afterwards, the modified explanation is used by HESIP to learn a better explanation.</abstract>
<identifier type="citekey">salam-etal-2021-generating</identifier>
<location>
<url>https://aclanthology.org/2021.alta-1.15</url>
</location>
<part>
<date>2021-12</date>
<extent unit="page">
<start>149</start>
<end>157</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generating and Modifying Natural Language Explanations
%A Salam, Abdus
%A Schwitter, Rolf
%A Orgun, Mehmet
%Y Rahimi, Afshin
%Y Lane, William
%Y Zuccon, Guido
%S Proceedings of the 19th Annual Workshop of the Australasian Language Technology Association
%D 2021
%8 December
%I Australasian Language Technology Association
%C Online
%F salam-etal-2021-generating
%X HESIP is a hybrid explanation system for image predictions that combines sub-symbolic and symbolic machine learning techniques to explain the predictions of image classification tasks. The sub-symbolic component makes a prediction for an image and the symbolic component learns probabilistic symbolic rules in order to explain that prediction. In HESIP, the explanations are generated in controlled natural language from the learned probabilistic rules using a bi-directional logic grammar. In this paper, we present an explanation modification method where a human-in-the-loop can modify an incorrect explanation generated by the HESIP system and afterwards, the modified explanation is used by HESIP to learn a better explanation.
%U https://aclanthology.org/2021.alta-1.15
%P 149-157
Markdown (Informal)
[Generating and Modifying Natural Language Explanations](https://aclanthology.org/2021.alta-1.15) (Salam et al., ALTA 2021)
ACL
- Abdus Salam, Rolf Schwitter, and Mehmet Orgun. 2021. Generating and Modifying Natural Language Explanations. In Proceedings of the 19th Annual Workshop of the Australasian Language Technology Association, pages 149–157, Online. Australasian Language Technology Association.