• Corpus ID: 252383168

TalkToModel: Explaining Machine Learning Models with Interactive Natural Language Conversations

  title={TalkToModel: Explaining Machine Learning Models with Interactive Natural Language Conversations},
  author={Dylan Slack and Satyapriya Krishna and Himabindu Lakkaraju and Sameer Singh},
Machine Learning (ML) models are increasingly used to make critical decisions in real-world applications, yet they have become more complex, making them harder to understand. To this end, researchers have proposed several techniques to explain model predictions. However, practitioners struggle to use these explainability techniques because they often do not know which one to choose and how to interpret the results of the explanations. In this work, we address these challenges by introducing… 



A Survey of Natural Language Generation Techniques with a Focus on Dialogue Systems - Past, Present and Future Directions

This work provides a comprehensive review towards building open domain dialogue systems, an important application of natural language generation, and finds that, predominantly, the approaches for building dialogue systems use seq2seq or language models architecture.

The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective

This work introduces and study the disagreement problem in explainable machine learning, formalizes the notion of disagreement between explanations, and analyzes how often such disagreements occur in practice, and how do practitioners resolve these disagreements.

Model-Agnostic Interpretability of Machine Learning

This paper argues for explaining machine learning predictions using model-agnostic approaches, treating the machine learning models as black-box functions, which provide crucial flexibility in the choice of models, explanations, and representations, improving debugging, comparison, and interfaces for a variety of users and models.

Neural Approaches to Conversational AI

This tutorial surveys neural approaches to conversational AI that were developed in the last few years, and presents a review of state-of-the-art neural approaches, drawing the connection between neural approaches and traditional symbolic approaches.

Assessing the Local Interpretability of Machine Learning Models

Evidence that as the number of operations increases, participant accuracy on the local interpretability tasks decreases decreases is found, consistent with the common intuition that decision trees and logistic regression models are interpretable and are more interpretable than neural networks.

Model Agnostic Supervised Local Explanations

It is demonstrated, on several UCI datasets, that MAPLE is at least as accurate as random forests and that it produces more faithful local explanations than LIME, a popular interpretability system.

Calibrate Before Use: Improving Few-Shot Performance of Language Models

This work first estimates the model's bias towards each answer by asking for its prediction when given the training prompt and a content-free test input such as "N/A", and then fits calibration parameters that cause the prediction for this input to be uniform across answers.

Generating High-Quality and Informative Conversation Responses with Sequence-to-Sequence Models

This work focuses on the single turn setting, introduces a stochastic beam-search algorithm with segment-by-segment reranking which lets us inject diversity earlier in the generation process, and proposes a practical approach, called the glimpse-model, for scaling to large datasets.

Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

This systematic study compares pre-training objectives, architectures, unlabeled datasets, transfer approaches, and other factors on dozens of language understanding tasks and achieves state-of-the-art results on many benchmarks covering summarization, question answering, text classification, and more.

End-to-End Task-Completion Neural Dialogue Systems

The end-to-end system not only outperforms modularized dialogue system baselines for both objective and subjective evaluation, but also is robust to noises as demonstrated by several systematic experiments with different error granularity and rates specific to the language understanding module.