Towards Explainable NLP: A Generative Explanation Framework for Text Classification

By Hui Liu, Qingyu Yin, William Yang Wang. 2018

160 citations recorded by the source corpus.

Building explainable systems is a critical problem in the field of Natural Language Processing (NLP), since most machine learning models provide no explanations for the predictions. Existing approaches for explainable machine learning systems tend to focus on interpreting the outputs or the connections between inputs and outputs. However, the fine-grained information (e.g. textual explanations for the labels) is often ignored, and the systems do not explicitly generate the human-readable explanations. To solve this problem, we propose a novel generative explanation framework that learns to make classification decisions and generate fine-grained explanations at the same time. More specifically, we introduce the explainable factor and the minimum risk training approach that learn to generate more reasonable explanations. We construct two new datasets that contain summaries, rating scores, and fine-grained reasons. We conduct experiments on both datasets, comparing with several strong neural network baseline systems. Experimental results show that our method surpasses all baselines on both datasets, and is able to generate concise explanations at the same time.

Subfields: Artificial Intelligence, Management Science and Operations Research, 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 Management Science and Operations Research

In Natural Language Processing

Citations in the corpus

Few-Shot Out-of-Domain Transfer Learning of Natural Language Explanations (2021, background): “There are three main focuses in NLE generation: quality improvement (Camburu et al., 2018; Narang et al., 2020; Valentino et al., 2022), NLE faithfulness (Kumar and Talukdar, 2020; Wiegreffe et al., 2021; Liu et al., 2019; Latcinnik and Berant, 2020), and transfer learning of NLEs.”
Few-Shot Self-Rationalization with Natural Language Prompts (2021, methodology): “On the other hand, a standard method for generating free-text explanations is to use human-written explanations (Liu et al., 2019; Wu and Mooney, 2019; Narang et al., 2020, among others).”
Measuring Association Between Labels and Free-Text Rationales (2020, methodology): “Method Following related work (Wang et al., 2019; Lakshmi Narayan et al., 2019; Liu et al., 2019b), we add zero-mean Gaussian noise N (0 , σ 2 ) to each input embedding in the I → OR encoder at inference time.”
PEER: A Collaborative Language Model (2022, background): “Finally, the intention behind this edit can optionally be clarified by providing a textual explanation et; this is especially relevant in collaborative settings where explanations can facilitate evaluating the quality and usefulness of an edit (Liu et al., 2019).”
Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions (2020, background): “…of models for certain tasks and properties (Liu et al., 2019b; Hewitt and Liang, 2019), and generative approaches that make the model jointly extract or generate natural language explanations to support predictions (Lei et al., 2016; Camburu et al., 2018; Liu et al., 2019a; Rajani et al., 2019).”
PRover: Proof Generation for Interpretable Reasoning over Rules (2020, methodology): “Clark et al. (2020) propose RuleTakers, a ﬁne-tuned RoBERTa model (Liu et al., 2019b) to show that transformers can act as “soft theorem provers” by predicting the ﬁ-nal answer in such reasoning-based problems with high accuracy.”
Improving the Interpretability of Neural Sentiment Classifiers via Data Augmentation (2019, background): “Beyond sentiment analysis, building explainable models has been widely recognized on general text classification (Lei et al., 2016; Liu et al., 2018; Nguyen, 2018), other NLP tasks (Zhao et al.”
Explainable Artificial Intelligence Applications in Cyber Security: State-of-the-Art in Research (2022, unknown): “For instance, text-based explanation methods are widely utilized in the field of Natural Language Processing (NLP) to fine-grained information and generate humanreadable explanations [64].”
A Survey of the State of Explainable AI for Natural Language Processing (2020, background): “This design may also be applied to surrogate models that generate explanations for predictions (Rajani et al., 2019a; Liu et al., 2019).”
TOWARDS HIERARCHICAL IMPORTANCE ATTRIBU- (2019, background): “Recent advances in deep neural networks have led to impressive results on a range of natural language processing (NLP) tasks, by learning latent, compositional vector representations of text data (Peters et al., 2018; Devlin et al., 2018; Liu et al., 2019b).”
Post-hoc Interpretability for Neural NLP: A Survey (2021, methodology): “The specifc intrinsic methods shown are: Attention [9], GEF [69], NILE [63].”
Interpretable deep learning: interpretation, interpretability, trustworthiness, and beyond (2021, methodology): “A joint outputexplanation model is trained to produce an prediction and simultaneously generate an explanation for the reason of that prediction [14, 93, 109].”
The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generation (2021, methodology): “Each paper was published between 2018 and 2020 at ACL, NAACL, or EMNLP, and we exclude papers that use AMT to evaluate more wellestablished generation tasks like machine translation, or summarization.3 Unlike previous surveys of evaluating generated text (Çelikyilmaz et al., 2020; van der Lee et al.”
Human-grounded Evaluations of Explanation Methods for Text Classification (2019, background): “Generally, there are several ways to explain a result given by a deep learning model, such as explaining by examples (Kim et al., 2014) and generating textual explanations (Liu et al., 2019).”
Why Attention is Not Explanation: Surgical Intervention and Causal Reasoning about Neural Models (2020, background): “…generated plaintext, partially or entirely independent of the actual classiﬁcation or factual content but facially plausible (Xu et al., 2015b; Liu et al., 2019); or direct exposure of structure in the underlying model, such as traversals through a graph (Yang et al., 2018; Moon et al.,…”
Human-in-the-loop Debugging Deep Text Classifiers (2020, methodology): “Explaining predictions from text classifiers – Several methods have been devised to generate explanations supporting classifications in many forms, such as natural language texts (Liu et al., 2019), rules (Ribeiro et al.”