Interpreting Neural Networks to Improve Politeness Comprehension

By Malika Aubakirova, Mohit Bansal. 2016

60 citations recorded by the source corpus.

We present an interpretable neural network approach to predicting and understanding politeness in natural language requests. Our models are based on simple convolutional neural networks directly on raw text, avoiding any manual identification of complex sentiment or syntactic features, while performing better than such feature-based models from previous work. More importantly, we use the challenging task of politeness prediction as a testbed to next present a much-needed understanding of what these successful networks are actually learning. For this, we present several network visualizations based on activation clusters, first derivative saliency, and embedding space transformations, helping us automatically identify several subtle linguistics markers of politeness theories. Further, this analysis reveals multiple novel, high-scoring politeness strategies which, when added back as new features, reduce the accuracy gap between the original featurized system and the neural model, thus providing a clear quantitative interpretation of the success of these neural networks.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Analysis Methods in Neural Language Processing: A Survey (2018, background): “The important or salient features can then be visualized in selected examples (Li et al., 2016a; Aubakirova and Bansal, 2016; Sundararajan et al., 2017; Arras et al., 2017a,b; Ding et al., 2017; Murdoch et al., 2018; Mudrakarta et al., 2018; Montavon et al., 2018; Godin et al., 2018).”
Detecting Linguistic Characteristics of Alzheimer’s Dementia by Interpreting Neural Models (2018, methodology): “Activation Clusters: Activation clustering treats the activation values of n neurons per input as coordinates in an n-dimensional space (Girshick et al., 2014; Aubakirova and Bansal, 2016).”
A Survey of the State of Explainable AI for Natural Language Processing (2020, unknown): “As suggested by its name and deﬁnition, ﬁrst-derivative saliency can be used to enable feature importance explainability, especially on word/token-level features (Aubakirova and Bansal, 2016; Karlekar et al., 2018).”
Conversations Gone Awry: Detecting Early Signs of Conversational Failure (2018, background): “Recent studies have computationally operationalized prior formulations of politeness by extracting linguistic cues that reflect politeness strategies (Danescu-Niculescu-Mizil et al., 2013; Aubakirova and Bansal, 2016).”
On internal language representations in deep learning: an analysis of machine translation and speech recognition (2018, background): “The important or salient features can then be visualized in selected examples [12, 203, 247, 248, 317].”
Fair Transfer of Multiple Style Attributes in Text (2019, background): “More recent work has attempted to transfer individual soft styles such as impolite to polite and informal to formal [1], [12].”