Let the CAT out of the bag: Contrastive Attributed explanations for Text
- URL: http://arxiv.org/abs/2109.07983v1
- Date: Thu, 16 Sep 2021 13:44:55 GMT
- Title: Let the CAT out of the bag: Contrastive Attributed explanations for Text
- Authors: Saneem Chemmengath, Amar Prakash Azad, Ronny Luss, Amit Dhurandhar
- Abstract summary: We propose a method Contrastive Attributed explanations for Text (CAT)
Our method provides contrastive explanations for natural language text data with a novel twist.
We show through qualitative examples and a user study that our method not only conveys more insight because of these attributes, but also leads to better quality (contrastive) text.
- Score: 10.703346059899637
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Contrastive explanations for understanding the behavior of black box models
has gained a lot of attention recently as they provide potential for recourse.
In this paper, we propose a method Contrastive Attributed explanations for Text
(CAT) which provides contrastive explanations for natural language text data
with a novel twist as we build and exploit attribute classifiers leading to
more semantically meaningful explanations. To ensure that our contrastive
generated text has the fewest possible edits with respect to the original text,
while also being fluent and close to a human generated contrastive, we resort
to a minimal perturbation approach regularized using a BERT language model and
attribute classifiers trained on available attributes. We show through
qualitative examples and a user study that our method not only conveys more
insight because of these attributes, but also leads to better quality
(contrastive) text. Moreover, quantitatively we show that our method is more
efficient than other state-of-the-art methods with it also scoring higher on
benchmark metrics such as flip rate, (normalized) Levenstein distance, fluency
and content preservation.
Related papers
- Constructing Vec-tionaries to Extract Message Features from Texts: A
Case Study of Moral Appeals [5.336592570916432]
We present an approach to construct vec-tionary measurement tools that boost validated dictionaries with word embeddings.
A vec-tionary can produce additional metrics to capture the ambivalence of a message feature beyond its strength in texts.
arXiv Detail & Related papers (2023-12-10T20:37:29Z) - Text Attribute Control via Closed-Loop Disentanglement [72.2786244367634]
We propose a novel approach to achieve a robust control of attributes while enhancing content preservation.
In this paper, we use a semi-supervised contrastive learning method to encourage the disentanglement of attributes in latent spaces.
We conducted experiments on three text datasets, including the Yelp Service review dataset, the Amazon Product review dataset, and the GoEmotions dataset.
arXiv Detail & Related papers (2023-12-01T01:26:38Z) - Active Learning for Abstractive Text Summarization [50.79416783266641]
We propose the first effective query strategy for Active Learning in abstractive text summarization.
We show that using our strategy in AL annotation helps to improve the model performance in terms of ROUGE and consistency scores.
arXiv Detail & Related papers (2023-01-09T10:33:14Z) - Fine-Grained Visual Entailment [51.66881737644983]
We propose an extension of this task, where the goal is to predict the logical relationship of fine-grained knowledge elements within a piece of text to an image.
Unlike prior work, our method is inherently explainable and makes logical predictions at different levels of granularity.
We evaluate our method on a new dataset of manually annotated knowledge elements and show that our method achieves 68.18% accuracy at this challenging task.
arXiv Detail & Related papers (2022-03-29T16:09:38Z) - Obtaining Better Static Word Embeddings Using Contextual Embedding
Models [53.86080627007695]
Our proposed distillation method is a simple extension of CBOW-based training.
As a side-effect, our approach also allows a fair comparison of both contextual and static embeddings.
arXiv Detail & Related papers (2021-06-08T12:59:32Z) - A Novel Estimator of Mutual Information for Learning to Disentangle
Textual Representations [27.129551973093008]
This paper introduces a novel variational upper bound to the mutual information between an attribute and the latent code of an encoder.
It aims at controlling the approximation error via the Renyi's divergence, leading to both better disentangled representations and a precise control of the desirable degree of disentanglement.
We show the superiority of this method on fair classification and on textual style transfer tasks.
arXiv Detail & Related papers (2021-05-06T14:05:06Z) - Improving Disentangled Text Representation Learning with
Information-Theoretic Guidance [99.68851329919858]
discrete nature of natural language makes disentangling of textual representations more challenging.
Inspired by information theory, we propose a novel method that effectively manifests disentangled representations of text.
Experiments on both conditional text generation and text-style transfer demonstrate the high quality of our disentangled representation.
arXiv Detail & Related papers (2020-06-01T03:36:01Z) - The Explanation Game: Towards Prediction Explainability through Sparse
Communication [6.497816402045099]
We provide a unified perspective of explainability as a problem between an explainer and a layperson.
We use this framework to compare several prior approaches for extracting explanations.
We propose new embedded methods for explainability, through the use of selective, sparse attention.
arXiv Detail & Related papers (2020-04-28T22:27:19Z) - Heavy-tailed Representations, Text Polarity Classification & Data
Augmentation [11.624944730002298]
We develop a novel method to learn a heavy-tailed embedding with desirable regularity properties.
A classifier dedicated to the tails of the proposed embedding is obtained which performance outperforms the baseline.
Numerical experiments on synthetic and real text data demonstrate the relevance of the proposed framework.
arXiv Detail & Related papers (2020-03-25T19:24:05Z) - Learning to Select Bi-Aspect Information for Document-Scale Text Content
Manipulation [50.01708049531156]
We focus on a new practical task, document-scale text content manipulation, which is the opposite of text style transfer.
In detail, the input is a set of structured records and a reference text for describing another recordset.
The output is a summary that accurately describes the partial content in the source recordset with the same writing style of the reference.
arXiv Detail & Related papers (2020-02-24T12:52:10Z)
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.