@inproceedings{wallace-etal-2020-interpreting,
title = "Interpreting Predictions of {NLP} Models",
author = "Wallace, Eric and
Gardner, Matt and
Singh, Sameer",
editor = "Villavicencio, Aline and
Van Durme, Benjamin",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-tutorials.3",
doi = "10.18653/v1/2020.emnlp-tutorials.3",
pages = "20--23",
abstract = "Although neural NLP models are highly expressive and empirically successful, they also systematically fail in counterintuitive ways and are opaque in their decision-making process. This tutorial will provide a background on interpretation techniques, i.e., methods for explaining the predictions of NLP models. We will first situate example-specific interpretations in the context of other ways to understand models (e.g., probing, dataset analyses). Next, we will present a thorough study of example-specific interpretations, including saliency maps, input perturbations (e.g., LIME, input reduction), adversarial attacks, and influence functions. Alongside these descriptions, we will walk through source code that creates and visualizes interpretations for a diverse set of NLP tasks. Finally, we will discuss open problems in the field, e.g., evaluating, extending, and improving interpretation methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wallace-etal-2020-interpreting">
<titleInfo>
<title>Interpreting Predictions of NLP Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Wallace</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matt</namePart>
<namePart type="family">Gardner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sameer</namePart>
<namePart type="family">Singh</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: Tutorial Abstracts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Van Durme</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>Although neural NLP models are highly expressive and empirically successful, they also systematically fail in counterintuitive ways and are opaque in their decision-making process. This tutorial will provide a background on interpretation techniques, i.e., methods for explaining the predictions of NLP models. We will first situate example-specific interpretations in the context of other ways to understand models (e.g., probing, dataset analyses). Next, we will present a thorough study of example-specific interpretations, including saliency maps, input perturbations (e.g., LIME, input reduction), adversarial attacks, and influence functions. Alongside these descriptions, we will walk through source code that creates and visualizes interpretations for a diverse set of NLP tasks. Finally, we will discuss open problems in the field, e.g., evaluating, extending, and improving interpretation methods.</abstract>
<identifier type="citekey">wallace-etal-2020-interpreting</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-tutorials.3</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-tutorials.3</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>20</start>
<end>23</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Interpreting Predictions of NLP Models
%A Wallace, Eric
%A Gardner, Matt
%A Singh, Sameer
%Y Villavicencio, Aline
%Y Van Durme, Benjamin
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F wallace-etal-2020-interpreting
%X Although neural NLP models are highly expressive and empirically successful, they also systematically fail in counterintuitive ways and are opaque in their decision-making process. This tutorial will provide a background on interpretation techniques, i.e., methods for explaining the predictions of NLP models. We will first situate example-specific interpretations in the context of other ways to understand models (e.g., probing, dataset analyses). Next, we will present a thorough study of example-specific interpretations, including saliency maps, input perturbations (e.g., LIME, input reduction), adversarial attacks, and influence functions. Alongside these descriptions, we will walk through source code that creates and visualizes interpretations for a diverse set of NLP tasks. Finally, we will discuss open problems in the field, e.g., evaluating, extending, and improving interpretation methods.
%R 10.18653/v1/2020.emnlp-tutorials.3
%U https://aclanthology.org/2020.emnlp-tutorials.3
%U https://doi.org/10.18653/v1/2020.emnlp-tutorials.3
%P 20-23
Markdown (Informal)
[Interpreting Predictions of NLP Models](https://aclanthology.org/2020.emnlp-tutorials.3) (Wallace et al., EMNLP 2020)
ACL
- Eric Wallace, Matt Gardner, and Sameer Singh. 2020. Interpreting Predictions of NLP Models. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts, pages 20–23, Online. Association for Computational Linguistics.