Towards Interpretable Natural Language Understanding with Explanations as Latent Variables
Beihang University（北京航空航天大学）；Tsinghua University（清华大学）；South China University of Technology（华南理工大学）；Sun Yat-sen University（中山大学）；Microsoft Research（微软研究院）；Mila-Québec AI Institute（Mila-魁北克人工智能研究所）；HEC Montréal（蒙特利尔高等商学院）
Recently generating natural language explanations has shown very promising results in not only offering interpretable explanations but also providing additional information and supervision for prediction. However, existing approaches usually require a large set of human annotated explanations for training while collecting a large set of explanations is not only time consuming but also expensive. In this paper, we develop a general framework for interpretable natural language understanding that requires only a small set of human annotated explanations for training. Our framework treats natural language explanations as latent variables that model the underlying reasoning process of a neural model. We develop a variational EM framework for optimization where an explanation generation module and an explanation-augmented prediction module are alternatively optimized and mutually enhance each other. Moreover, we further propose an explanation-based self-training method under this framework for semi-supervised learning. It alternates between assigning pseudo-labels to unlabeled data and generating new explanations to iteratively improve each other. Experiments on two natural language understanding tasks demonstrate that our framework can not only make effective predictions in both supervised and semi-supervised settings, but also generate good natural language explanation.
Latent Diffusion Energy-Based Model for Interpretable Text Modeling
UCLA（加州大学洛杉矶分校）；Beijing Institute for General Artificial Intelligence（北京通用人工智能研究院）；Salesforce Research（赛富时研究院）；Google Brain（谷歌大脑）；Peking University（北京大学）；Tsinghua University（清华大学）
Many predictive tasks, such as diagnosing a patient based on their medical chart, are ultimately defined by the decisions of human experts. Unfortunately, encoding experts' knowledge is often time consuming and expensive. We propose a simple way to use fuzzy and informal knowledge from experts to guide discovery of interpretable latent topics in text. The underlying intuition of our approach is that latent factors should be informative about both correlations in the data and a set of relevance variables specified by an expert. Mathematically, this approach is a combination of the information b…
Charles University, Faculty of Mathematics and Physics（查理大学数学与物理学院）
We present a novel architecture for explainable modeling of task-oriented dialogues with discrete latent variables to represent dialogue actions. Our model is based on variational recurrent neural networks (VRNN) and requires no explicit annotation of semantic information. Unlike previous works, our approach models the system and user turns separately and performs database query modeling, which makes the model applicable to task-oriented dialogues while producing easily interpretable action latent variables. We show that our model outperforms previous approaches with less supervision in terms …
Beijing Institute for General Artificial Intelligence（北京通用人工智能研究院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, Beijing University of Posts and Telecommunications（北京邮电大学人工智能学院）；School of Artificial Intelligence for Science, Peking University（北京大学科学人工智能学院）
Interpretability of machine learning (ML) models becomes more relevant with their increasing adoption. In this work, we address the interpretability of ML based question answering (QA) models on a combination of knowledge bases (KB) and text documents. We adapt post hoc explanation methods such as LIME and input perturbation (IP) and compare them with the self-explanatory attention mechanism of the model. For this purpose, we propose an automatic evaluation paradigm for explanation methods in the context of QA. We also conduct a study with human annotators to evaluate whether explanations help…
Using attention weights to identify information that is important for models' decision-making is a popular approach to interpret attention-based neural networks. This is commonly realized in practice through the generation of a heat-map for every single document based on attention weights. However, this interpretation method is fragile, and easy to find contradictory examples. In this paper, we propose a corpus-level explanation approach, which aims to capture causal relationships between keywords and model predictions via learning the importance of keywords for predicted labels across a train…
SLIM: Sparse Latent Steering for Interpretable and Property-Directed LLM-Based Molecular Editing
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；The 63rd Research Institute, National University of Defense Technology, Nanjing（国防科技大学第六三研究所，南京）
Recent works in Explainable AI mostly address the transparency issue of black-box models or create explanations for any kind of models (i.e., they are model-agnostic), while leaving explanations of interpretable models largely underexplored. In this paper, we fill this gap by focusing on explanations for a specific interpretable model, namely pattern-based logistic regression (PLR) for binary text classification. We do so because, albeit interpretable, PLR is challenging when it comes to explanations. In particular, we found that a standard way to extract explanations from this model does not …
Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）；Center for Data Science, AAIS, Peking University（北京大学人工智能研究院数据科学中心）；Tencent AI Lab（腾讯人工智能实验室）；Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；Beijing Institute for General Artificial Intelligence（北京通用人工智能研究院）
With the availability of massive general-domain dialogue data, pre-trained dialogue generation appears to be super appealing to transfer knowledge from the general domain to downstream applications. In most existing work, such transferable ability is mainly obtained by fitting a large model with hundreds of millions of parameters on massive data in an exhaustive way, leading to inefficient running and poor interpretability. This paper proposes a novel dialogue generation model with a latent structure that is easily transferable from the general domain to downstream tasks in a lightweight and t…
iPOE: Interpretable Prompt Optimization via Explanations
Fundamentals of Natural Language Processing, University of Bamberg, Germany（自然语言处理基础，巴姆堡大学，德国）；Leibniz-Institut für Psychologie (ZPID), Trier, Germany（莱比锡心理学研究所（ZPID），特里尔，德国）
Amazon TTS-Research（亚马逊文本转语音研究部）；Gdansk University of Technology（格但斯克工业大学）
This paper proposed a novel approach for the detection and reconstruction of dysarthric speech. The encoder-decoder model factorizes speech into a low-dimensional latent space and encoding of the input text. We showed that the latent space conveys interpretable characteristics of dysarthria, such as intelligibility and fluency of speech. MUSHRA perceptual test demonstrated that the adaptation of the latent space let the model generate speech of improved fluency. The multi-task supervised approach for predicting both the probability of dysarthric speech and the mel-spectrogram helps improve the…
