CoChat

MARTA: Leveraging Human Rationales for Explainable Text Classification

Open access
Arous, Ines, Dolamic, Ljiljana, Yang, Jie, Bhardwaj, Akansha, Cuccu, Giuseppe, Cudré-Mauroux, Philippe · 2021 · Proceedings of the AAAI Conference on Artificial Intelligence
Cited by 41

The DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.

Abstract

Explainability is a key requirement for text classification in many application domains ranging from sentiment analysis to medical diagnosis or legal reviews. Existing methods often rely on "attention" mechanisms for explaining classification results by estimating the relative importance of input units. However, recent studies have shown that such mechanisms tend to mis-identify irrelevant input units in their explanation. In this work, we propose a hybrid human-AI approach that incorporates human rationales into attention-based text classification models to improve the explainability of classification results. Specifically, we ask workers to provide rationales for their annotation by selecting relevant pieces of text. We introduce MARTA, a Bayesian framework that jointly learns an attention-based model and the reliability of workers while injecting human rationales into model training. We derive a principled optimization algorithm based on variational inference with efficient updating rules for learning MARTA parameters. Extensive validation on real-world datasets shows that our framework significantly improves the state of the art both in terms of classification explainability and accuracy.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1609/aaai.v35i7.16734

Cites

13 of 13 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Cited by

  • A survey of human-in-the-loop for machine learning

    Wu, X., Xiao, L., Sun, Y., Zhang, J., Ma, T., & He, L. (2022) · Future Generation Computer Systems · doi:10.1016/j.future.2022.05.014 · Cited by 800

    “[83] put forward a hybrid human-AI framework that gives a moral idea to reinforce human reliability in merging human rationales into a deep learning algorithm.”
    Background
  • Explainability for Large Language Models: A Survey

    Zhao, H., Chen, H., Yang, F., Liu, N., Deng, H., Cai, H., Wang, S., Yin, D., & Du, M. (2024) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3639372 · Cited by 681

    “To make attention explainable, technical solutions have also been explored by optimizing input representation (Mohankumar et al., 2020), regularizing learning objectives (Moradi et al., 2021), avoiding biased learning (Bai et al., 2021) and even incorporating human rationales (Arous et al., 2021).”
    Background
  • Nano: Nested Human-in-the-Loop Reward Learning for Few-shot Language Model Control

    Fan, X., Lyu, Y., Liang, P. P., Salakhutdinov, R., & Morency, L.-P. (2023) · Findings of the Association for Computational Linguistics: ACL 2023 · doi:10.18653/v1/2023.findings-acl.758 · Cited by 3

    “Previous works on HITL in NLP (Wu et al., 2021a) utilizes HITL to improve text classification (Arous et al., 2021; Kar-makharm et al., 2019), semantic parsing (Yao et al., 2019a,b), text summarization (Stiennon et al., 2020; Ziegler et al., 2019), dialog and question answering (Hancock et al.,…”
    Method

See all 41

Metadata

Authors
Arous, I., Dolamic, L., Yang, J., Bhardwaj, A., Cuccu, G., & Cudré-Mauroux, P.
Venue
Proceedings of the AAAI Conference on Artificial Intelligence
Published
2021-05-18
Volume
35
Issue
7
Pages
5868-5876
ISSN
  • 2159-5399 (ISSN-L)
  • 2374-3468
OpenAlex
W3174254835
Cited by
41
References
13
FWCI
3.33
Type
conference paper
Language
en
Open access
diamond

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.