ALICE: Active Learning with Contrastive Natural Language Explanations

By Weixin Liang, James Y. Zou, Zhou Yu. 2020

56 citations recorded by the source corpus.

Training a supervised neural network classifier typically requires many annotated training samples. Collecting and annotating a large number of data points are costly and sometimes even infeasible. Traditional annotation process uses a low-bandwidth human-machine communication interface: classification labels, each of which only provides several bits of information. We propose Active Learning with Contrastive Explanations (ALICE), an expert-in-the-loop training framework that utilizes contrastive natural language explanations to improve data efficiency in learning. ALICE learns to first use active learning to select the most informative pairs of label classes to elicit contrastive natural language explanations from experts. Then it extracts knowledge from these explanations using a semantic parser. Finally, it incorporates the extracted knowledge through dynamically changing the learning model's structure. We applied ALICE in two visual recognition tasks, bird species classification and social relationship classification. We found by incorporating contrastive explanations, our models outperform baseline models that are trained with 40-100% more training data. We found that adding 1 explanation leads to similar performance gain as adding 13-30 labeled training data points.

Subfields: Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Learning Transferable Visual Models From Natural Language Supervision (2021, background): “More recently, He & Peng (2017) and (Liang et al., 2020) demonstrated using natural language descriptions and explanations to improve fine-grained visual classification of birds.”
When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data (2021, background): “…the learned model (Zaidan et al., 2007; Small et al., 2011; Ba et al., 2015; Zhang et al., 2016; Srivastava et al., 2017; Andreas et al., 2018; Liang et al., 2020), to automatically label data for data augmentation (Hancock et al., 2018; Wang et al., 2019a; Awasthi et al., 2020), as…”
Explaining NLP Models via Minimal Contrastive Editing (MiCE) (2020, background): “Madaan et al. (2021) applies con-such as free-text rationales (Liang et al., 2020) or highlights (Jacovi and Goldberg, 2020).”
Advances, challenges and opportunities in creating data for trustworthy AI (2022, background): “Another human-in-the-loop approach to reduce annotation costs is to prioritize the most valuable data for humans to annotate with active learning 64–66 .”
Learning to Recognize Dialect Features (2020, background): “Finally, Liang et al. (2020) use contrastive explanations as part of an active learning framework to improve data efficiency.”
Natural Language Inference with a Human Touch: Using Human Explanations to Guide Model Attention (2021, background): “…to improve performance on a range of domains, including commonsense reasoning (Rajani et al., 2019), relation extraction (Murty et al., 2020), visual clas-siﬁcation tasks (Liang et al., 2020; Mu et al., 2020), sentiment analysis (Pruthi et al., 2020) and question answering (Pruthi et al., 2020).”
Leveraging Language to Learn Program Abstractions and Search Heuristics (2021, methodology): “Natural language has also been used to scaffold latent representation learning (Frome et al., 2013; Jia & Liang, 2016; Andreas et al., 2017; Ye et al., 2020b; Goyal et al., 2020; Liang et al., 2020; Mu et al., 2019; Luketina et al., 2019), and as a high-level specification for program synthesis task”
Supervising Model Attention with Human Explanations for Robust Natural Language Inference (2021, background): “More widely, explanations have improved performance on a range of domains, including commonsense reasoning (Rajani et al. 2019), relation extraction (Murty, Koh, and Liang 2020) and visual classiﬁcation tasks (Liang, Zou, and Yu 2020; Mu, Liang, and Goodman 2020).”