@inproceedings{wang-etal-2022-fine,
title = "A Fine-grained Interpretability Evaluation Benchmark for Neural {NLP}",
author = "Wang, Lijie and
Shen, Yaozong and
Peng, Shuyuan and
Zhang, Shuai and
Xiao, Xinyan and
Liu, Hao and
Tang, Hongxuan and
Chen, Ying and
Wu, Hua and
Wang, Haifeng",
editor = "Fokkens, Antske and
Srikumar, Vivek",
booktitle = "Proceedings of the 26th Conference on Computational Natural Language Learning (CoNLL)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.conll-1.6",
doi = "10.18653/v1/2022.conll-1.6",
pages = "70--84",
abstract = "While there is increasing concern about the interpretability of neural models, the evaluation of interpretability remains an open problem, due to the lack of proper evaluation datasets and metrics. In this paper, we present a novel benchmark to evaluate the interpretability of both neural models and saliency methods. This benchmark covers three representative NLP tasks: sentiment analysis, textual similarity and reading comprehension, each provided with both English and Chinese annotated data. In order to precisely evaluate the interpretability, we provide token-level rationales that are carefully annotated to be sufficient, compact and comprehensive. We also design a new metric, i.e., the consistency between the rationales before and after perturbations, to uniformly evaluate the interpretability on different types of tasks. Based on this benchmark, we conduct experiments on three typical models with three saliency methods, and unveil their strengths and weakness in terms of interpretability. We will release this benchmark (\url{https://www.luge.ai/#/luge/task/taskDetail?taskId=15}) and hope it can facilitate the research in building trustworthy systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2022-fine">
<titleInfo>
<title>A Fine-grained Interpretability Evaluation Benchmark for Neural NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lijie</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaozong</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuyuan</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuai</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyan</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongxuan</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ying</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hua</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haifeng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 26th Conference on Computational Natural Language Learning (CoNLL)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antske</namePart>
<namePart type="family">Fokkens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>While there is increasing concern about the interpretability of neural models, the evaluation of interpretability remains an open problem, due to the lack of proper evaluation datasets and metrics. In this paper, we present a novel benchmark to evaluate the interpretability of both neural models and saliency methods. This benchmark covers three representative NLP tasks: sentiment analysis, textual similarity and reading comprehension, each provided with both English and Chinese annotated data. In order to precisely evaluate the interpretability, we provide token-level rationales that are carefully annotated to be sufficient, compact and comprehensive. We also design a new metric, i.e., the consistency between the rationales before and after perturbations, to uniformly evaluate the interpretability on different types of tasks. Based on this benchmark, we conduct experiments on three typical models with three saliency methods, and unveil their strengths and weakness in terms of interpretability. We will release this benchmark (https://www.luge.ai/#/luge/task/taskDetail?taskId=15) and hope it can facilitate the research in building trustworthy systems.</abstract>
<identifier type="citekey">wang-etal-2022-fine</identifier>
<identifier type="doi">10.18653/v1/2022.conll-1.6</identifier>
<location>
<url>https://aclanthology.org/2022.conll-1.6</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>70</start>
<end>84</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Fine-grained Interpretability Evaluation Benchmark for Neural NLP
%A Wang, Lijie
%A Shen, Yaozong
%A Peng, Shuyuan
%A Zhang, Shuai
%A Xiao, Xinyan
%A Liu, Hao
%A Tang, Hongxuan
%A Chen, Ying
%A Wu, Hua
%A Wang, Haifeng
%Y Fokkens, Antske
%Y Srikumar, Vivek
%S Proceedings of the 26th Conference on Computational Natural Language Learning (CoNLL)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F wang-etal-2022-fine
%X While there is increasing concern about the interpretability of neural models, the evaluation of interpretability remains an open problem, due to the lack of proper evaluation datasets and metrics. In this paper, we present a novel benchmark to evaluate the interpretability of both neural models and saliency methods. This benchmark covers three representative NLP tasks: sentiment analysis, textual similarity and reading comprehension, each provided with both English and Chinese annotated data. In order to precisely evaluate the interpretability, we provide token-level rationales that are carefully annotated to be sufficient, compact and comprehensive. We also design a new metric, i.e., the consistency between the rationales before and after perturbations, to uniformly evaluate the interpretability on different types of tasks. Based on this benchmark, we conduct experiments on three typical models with three saliency methods, and unveil their strengths and weakness in terms of interpretability. We will release this benchmark (https://www.luge.ai/#/luge/task/taskDetail?taskId=15) and hope it can facilitate the research in building trustworthy systems.
%R 10.18653/v1/2022.conll-1.6
%U https://aclanthology.org/2022.conll-1.6
%U https://doi.org/10.18653/v1/2022.conll-1.6
%P 70-84
Markdown (Informal)
[A Fine-grained Interpretability Evaluation Benchmark for Neural NLP](https://aclanthology.org/2022.conll-1.6) (Wang et al., CoNLL 2022)
ACL
- Lijie Wang, Yaozong Shen, Shuyuan Peng, Shuai Zhang, Xinyan Xiao, Hao Liu, Hongxuan Tang, Ying Chen, Hua Wu, and Haifeng Wang. 2022. A Fine-grained Interpretability Evaluation Benchmark for Neural NLP. In Proceedings of the 26th Conference on Computational Natural Language Learning (CoNLL), pages 70–84, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.