Peeking inside the black box: A Commonsense-aware Generative Framework for Explainable Complaint Detection

Challenge:	Complaining is an expression of negative emotions communicated due to a discrepancy between reality and expectations.
Approach:	They propose to use an explainable complaint dataset to generate a commonsense-aware generative framework that can predict the complaint cause, severity level, emotion, and polarity of the text.
Outcome:	The proposed model can predict the complaint cause, severity level, emotion, and polarity of the text in addition to detecting whether it is a complaint or not.

Similar Papers

Overview

Challenge

Approach

Outcome

GenEx: A Commonsense-aware Unified Generative Framework for Explainable Cyberbullying Detection (2023.emnlp-main)

Copied to clipboard

Krishanu Maity, Raghav Jain, Prince Jha, Sriparna Saha, Pushpak Bhattacharyya

Reasoning

Challenge:	a significant gap exists in understanding code-mixed languages and the need for explainability in this context.
Approach:	They propose to annotate posts with four labels to identify bullies in code-mixed languages . they propose to use a generative framework to reimagine the multitask problem as a text-to-text generation task.
Outcome:	The proposed model outperforms baseline models and state-of-the-art models on the BullyExplain dataset.

Federated Meta-Learning for Emotion and Sentiment Aware Multi-modal Complaint Identification (2023.emnlp-main)

Copied to clipboard

Apoorva Singh, Siddarth Chandrasekar, Sriparna Saha, Tanmay Sen

Multimodality

Challenge:	Existing studies on complaint identification are limited to text.
Approach:	They propose a meta-learning-based multi-modal multi-task framework for identifying complaints using emotion recognition and sentiment analysis as auxiliary tasks.
Outcome:	The proposed framework outperforms baselines and state-of-the-art approaches in centralized and federated meta-learning settings.

Towards Explainable NLP: A Generative Explanation Framework for Text Classification (P19-1)

Copied to clipboard

Hui Liu, Qingyu Yin, William Yang Wang

Explainability & Interpretability in NLP

Challenge:	Existing approaches for explainable machine learning systems focus on interpreting outputs or connections between inputs and outputs.
Approach:	They propose a generative explanation framework that learns to make classification decisions and generates fine-grained explanations at the same time.
Outcome:	The proposed framework surpasses all baselines on two datasets and generates concise explanations at the same time.

Improve Interpretability of Neural Networks via Sparse Contrastive Coding (2022.findings-emnlp)

Copied to clipboard

Junhong Liu, Yijie Lin, Liang Jiang, Jia Liu, Zujie Wen, Xi Peng

Explainability & Interpretability in NLP

Challenge:	XAI has achieved remarkable advances, but few efforts have been devoted to solving the problem.
Approach:	They propose a model-agnostic explanation method termed Sparse Contrastive Coding . they use model-based explanations to explain the black-box in a more model-oriented way .
Outcome:	The proposed method outperforms five state-of-the-art methods in interpretability and classification metrics.

Complaint Identification in Social Media with Transformer Networks (2020.coling-main)

Copied to clipboard

Mali Jin, Nikolaos Aletras

Language Models

Challenge:	Existing work on identifying complaints in social media has focused on feature-based and task-specific neural network models.
Approach:	They evaluate a battery of neural models underpinned by transformer networks and combine them with linguistic information to predict complaints.
Outcome:	The proposed models outperform state-of-the-art methods on a publicly available dataset achieving a macro F1 up to 87.

Modeling the Severity of Complaints in Social Media (2021.naacl-main)

Copied to clipboard

Mali Jin, Nikolaos Aletras

Linguistics & Cognitive NLP

Challenge:	Complaining is a speech act used by humans to communicate a negative mismatch between reality and expectations . recent work on modeling complaints in natural language processing (NLP) has focused on distinguishing complaints from non-complaints in social media.
Approach:	They propose to classify complaints into various severity levels based on the face-threat that the complainer is willing to undertake and their purpose.
Outcome:	The proposed model achieves 55.7 macro F1 on binary complaint classification and 88.2 macro F1.

SenticNet 7: A Commonsense-based Neurosymbolic AI Framework for Explainable Sentiment Analysis (2022.lrec-1)

Copied to clipboard

Erik Cambria, Qian Liu, Sergio Decherchi, Frank Xing, Kenneth Kwok

Responsible & Trustworthy NLP

Challenge:	Despite recent advances, AI still struggles with complex tasks that require commonsense reasoning such as natural language understanding.
Approach:	They propose a commonsense-based framework that aims to overcome these limitations in the context of sentiment analysis.
Outcome:	The proposed framework overcomes these limitations in the context of sentiment analysis.

InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanations (2023.findings-emnlp)

Copied to clipboard

Nils Feldhus, Qianli Wang, Tatiana Anikina, Sahil Chopra, Cennet Oguz, Sebastian Möller

Natural Language Interfaces

Challenge:	Recent work on NLP explainability methods lacks a dialogue-based interpretability framework that can convey faithful explanations in human-understandable terms.
Approach:	They adapt the conversational explanation framework TalkToModel to the NLP domain and add new NLP-specific operations such as free-text rationalization to illustrate its generalizability.
Outcome:	The proposed framework can be used to explain models on three NLP tasks and is generalizable to different datasets, use cases and models.

A Survey of the State of Explainable AI for Natural Language Processing (2020.aacl-main)

Copied to clipboard

Marina Danilevsky, Kun Qian, Ranit Aharonov, Yannis Katsis, Ban Kawas, Prithviraj Sen

Explainability & Interpretability in NLP

Challenge:	Recent years have seen significant advances in the quality of state-of-the-art models, but they have come at the expense of models becoming less interpretable.
Approach:	This survey examines the current state of Explainable AI within the domain of NLP . they detail the operations and explainability techniques currently available for generating explanations for NLP models .
Outcome:	This survey examines the state of explainable AI (XAI) within the domain of natural language processing . it focuses on the operations and explainability techniques currently available for NLP models .

LESA: Linguistic Encapsulation and Semantic Amalgamation Based Generalised Claim Detection from Online Content (2021.eacl-main)

Copied to clipboard

Shreya Gupta, Parantak Singh, Megha Sundriyal, Md. Shad Akhtar, Tanmoy Chakraborty

Responsible & Trustworthy NLP

Challenge:	Existing work on claim detection is built on the basis of a 'segregation' of claims across different domains.
Approach:	They propose a generalized generalized model that captures syntactic features through part-of-speech and dependency embeddings, as well as contextual features through a fine-tuned language model.
Outcome:	The proposed model outperforms baselines on six claim datasets by an average of 3 claim-F1 points and 2 claim-f1 points on the general-domain experiments.