SPECTRA: Sparse Structured Text Rationalization
- URL: http://arxiv.org/abs/2109.04552v1
- Date: Thu, 9 Sep 2021 20:39:56 GMT
- Title: SPECTRA: Sparse Structured Text Rationalization
- Authors: Nuno Miguel Guerreiro, Andr\'e F. T. Martins
- Abstract summary: We present a unified framework for deterministic extraction of structured explanations via constrained inference on a factor graph.
Our approach greatly eases training and rationale regularization, generally outperforming previous work on plausibility extracted explanations.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Selective rationalization aims to produce decisions along with rationales
(e.g., text highlights or word alignments between two sentences). Commonly,
rationales are modeled as stochastic binary masks, requiring sampling-based
gradient estimators, which complicates training and requires careful
hyperparameter tuning. Sparse attention mechanisms are a deterministic
alternative, but they lack a way to regularize the rationale extraction (e.g.,
to control the sparsity of a text highlight or the number of alignments). In
this paper, we present a unified framework for deterministic extraction of
structured explanations via constrained inference on a factor graph, forming a
differentiable layer. Our approach greatly eases training and rationale
regularization, generally outperforming previous work on what comes to
performance and plausibility of the extracted rationales. We further provide a
comparative study of stochastic and deterministic methods for rationale
extraction for classification and natural language inference tasks, jointly
assessing their predictive power, quality of the explanations, and model
variability.
Related papers
- Evaluating Human Alignment and Model Faithfulness of LLM Rationale [66.75309523854476]
We study how well large language models (LLMs) explain their generations through rationales.
We show that prompting-based methods are less "faithful" than attribution-based explanations.
arXiv Detail & Related papers (2024-06-28T20:06:30Z) - Plausible Extractive Rationalization through Semi-Supervised Entailment Signal [29.67884478799914]
We take a semi-supervised approach to optimize for the plausibility of extracted rationales.
We adopt a pre-trained natural language inference (NLI) model and further fine-tune it on a small set of supervised rationales.
We show that, by enforcing the alignment agreement between the explanation and answer in a question-answering task, the performance can be improved without access to ground truth labels.
arXiv Detail & Related papers (2024-02-13T14:12:32Z) - Enhancing the Rationale-Input Alignment for Self-explaining
Rationalization [22.74436500022893]
We introduce a novel approach called DAR (textbfDiscriminatively textbfAligned textbfRationalization) to align the selected rationale and the original input.
Experiments on two widely used real-world benchmarks show that the proposed method significantly improves the explanation quality.
arXiv Detail & Related papers (2023-12-07T07:37:15Z) - Towards Trustworthy Explanation: On Causal Rationalization [9.48539398357156]
We propose a new model of rationalization based on two causal desiderata, non-spuriousness and efficiency.
The superior performance of the proposed causal rationalization is demonstrated on real-world review and medical datasets.
arXiv Detail & Related papers (2023-06-25T03:34:06Z) - Rationalizing Predictions by Adversarial Information Calibration [65.19407304154177]
We train two models jointly: one is a typical neural model that solves the task at hand in an accurate but black-box manner, and the other is a selector-predictor model that additionally produces a rationale for its prediction.
We use an adversarial technique to calibrate the information extracted by the two models such that the difference between them is an indicator of the missed or over-selected features.
arXiv Detail & Related papers (2023-01-15T03:13:09Z) - Rationale-Augmented Ensembles in Language Models [53.45015291520658]
We reconsider rationale-augmented prompting for few-shot in-context learning.
We identify rationale sampling in the output space as the key component to robustly improve performance.
We demonstrate that rationale-augmented ensembles achieve more accurate and interpretable results than existing prompting approaches.
arXiv Detail & Related papers (2022-07-02T06:20:57Z) - Interlock-Free Multi-Aspect Rationalization for Text Classification [33.33452117387646]
We show that we address the interlocking problem in the multi-aspect setting.
We propose a multi-stage training method incorporating an additional self-supervised contrastive loss.
Empirical results on the beer review dataset show that our method improves significantly the rationalization performance.
arXiv Detail & Related papers (2022-05-13T16:38:38Z) - Measuring Association Between Labels and Free-Text Rationales [60.58672852655487]
In interpretable NLP, we require faithful rationales that reflect the model's decision-making process for an explained instance.
We demonstrate that pipelines, existing models for faithful extractive rationalization on information-extraction style tasks, do not extend as reliably to "reasoning" tasks requiring free-text rationales.
We turn to models that jointly predict and rationalize, a class of widely used high-performance models for free-text rationalization whose faithfulness is not yet established.
arXiv Detail & Related papers (2020-10-24T03:40:56Z) - Why do you think that? Exploring Faithful Sentence-Level Rationales
Without Supervision [60.62434362997016]
We propose a differentiable training-framework to create models which output faithful rationales on a sentence level.
Our model solves the task based on each rationale individually and learns to assign high scores to those which solved the task best.
arXiv Detail & Related papers (2020-10-07T12:54:28Z) - Invariant Rationalization [84.1861516092232]
A typical rationalization criterion, i.e. maximum mutual information (MMI), finds the rationale that maximizes the prediction performance based only on the rationale.
We introduce a game-theoretic invariant rationalization criterion where the rationales are constrained to enable the same predictor to be optimal across different environments.
We show both theoretically and empirically that the proposed rationales can rule out spurious correlations, generalize better to different test scenarios, and align better with human judgments.
arXiv Detail & Related papers (2020-03-22T00:50:27Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.