Stance Reasoner: Zero-Shot Stance Detection on Social Media with Explicit Reasoning
- URL: http://arxiv.org/abs/2403.14895v1
- Date: Fri, 22 Mar 2024 00:58:28 GMT
- Title: Stance Reasoner: Zero-Shot Stance Detection on Social Media with Explicit Reasoning
- Authors: Maksym Taranukhin, Vered Shwartz, Evangelos Milios,
- Abstract summary: We present Stance Reasoner, an approach to zero-shot stance detection on social media.
We use a pre-trained language model as a source of world knowledge, with the chain-of-thought in-context learning approach to generate intermediate reasoning steps.
Stance Reasoner outperforms the current state-of-the-art models on 3 Twitter datasets.
- Score: 10.822701164802307
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Social media platforms are rich sources of opinionated content. Stance detection allows the automatic extraction of users' opinions on various topics from such content. We focus on zero-shot stance detection, where the model's success relies on (a) having knowledge about the target topic; and (b) learning general reasoning strategies that can be employed for new topics. We present Stance Reasoner, an approach to zero-shot stance detection on social media that leverages explicit reasoning over background knowledge to guide the model's inference about the document's stance on a target. Specifically, our method uses a pre-trained language model as a source of world knowledge, with the chain-of-thought in-context learning approach to generate intermediate reasoning steps. Stance Reasoner outperforms the current state-of-the-art models on 3 Twitter datasets, including fully supervised models. It can better generalize across targets, while at the same time providing explicit and interpretable explanations for its predictions.
Related papers
- Generating Zero-shot Abstractive Explanations for Rumour Verification [46.897767694062004]
We reformulate the task to generate model-centric free-text explanations of a rumour's veracity.
We exploit the few-shot learning capabilities of a large language model (LLM)
Our experiments show that LLMs can have similar agreement to humans in evaluating summaries.
arXiv Detail & Related papers (2024-01-23T12:29:37Z) - Revisiting Self-supervised Learning of Speech Representation from a
Mutual Information Perspective [68.20531518525273]
We take a closer look into existing self-supervised methods of speech from an information-theoretic perspective.
We use linear probes to estimate the mutual information between the target information and learned representations.
We explore the potential of evaluating representations in a self-supervised fashion, where we estimate the mutual information between different parts of the data without using any labels.
arXiv Detail & Related papers (2024-01-16T21:13:22Z) - Explaining Explainability: Towards Deeper Actionable Insights into Deep
Learning through Second-order Explainability [70.60433013657693]
Second-order explainable AI (SOXAI) was recently proposed to extend explainable AI (XAI) from the instance level to the dataset level.
We demonstrate for the first time, via example classification and segmentation cases, that eliminating irrelevant concepts from the training set based on actionable insights from SOXAI can enhance a model's performance.
arXiv Detail & Related papers (2023-06-14T23:24:01Z) - A Study of Situational Reasoning for Traffic Understanding [63.45021731775964]
We devise three novel text-based tasks for situational reasoning in the traffic domain.
We adopt four knowledge-enhanced methods that have shown generalization capability across language reasoning tasks in prior work.
We provide in-depth analyses of model performance on data partitions and examine model predictions categorically.
arXiv Detail & Related papers (2023-06-05T01:01:12Z) - Improved Target-specific Stance Detection on Social Media Platforms by
Delving into Conversation Threads [12.007570049217398]
We propose a new task called conversational stance detection.
It infers the stance towards a given target (e.g., COVID-19 vaccination) when given a data instance and its corresponding conversation thread.
To infer the desired stances from both data instances and conversation threads, we propose a model called Branch-BERT that incorporates contextual information in conversation threads.
arXiv Detail & Related papers (2022-11-06T08:40:48Z) - Contextual information integration for stance detection via
cross-attention [59.662413798388485]
Stance detection deals with identifying an author's stance towards a target.
Most existing stance detection models are limited because they do not consider relevant contextual information.
We propose an approach to integrate contextual information as text.
arXiv Detail & Related papers (2022-11-03T15:04:29Z) - Rumor Detection with Self-supervised Learning on Texts and Social Graph [101.94546286960642]
We propose contrastive self-supervised learning on heterogeneous information sources, so as to reveal their relations and characterize rumors better.
We term this framework as Self-supervised Rumor Detection (SRD)
Extensive experiments on three real-world datasets validate the effectiveness of SRD for automatic rumor detection on social media.
arXiv Detail & Related papers (2022-04-19T12:10:03Z) - Adversarial Learning for Zero-Shot Stance Detection on Social Media [1.7702142798241087]
We propose a new model for zero-shot stance detection on Twitter that uses adversarial learning to generalize across topics.
Our model achieves state-of-the-art performance on a number of unseen test topics with minimal computational costs.
arXiv Detail & Related papers (2021-05-14T01:08:48Z) - Generalized Zero-shot Intent Detection via Commonsense Knowledge [5.398580049917152]
We propose RIDE: an intent detection model that leverages commonsense knowledge in an unsupervised fashion to overcome the issue of training data scarcity.
RIDE computes robust and generalizable relationship meta-features that capture deep semantic relationships between utterances and intent labels.
Our extensive experimental analysis on three widely-used intent detection benchmarks shows that relationship meta-features significantly increase the accuracy of detecting both seen and unseen intents.
arXiv Detail & Related papers (2021-02-04T23:36:41Z) - Knowledge-driven Data Construction for Zero-shot Evaluation in
Commonsense Question Answering [80.60605604261416]
We propose a novel neuro-symbolic framework for zero-shot question answering across commonsense tasks.
We vary the set of language models, training regimes, knowledge sources, and data generation strategies, and measure their impact across tasks.
We show that, while an individual knowledge graph is better suited for specific tasks, a global knowledge graph brings consistent gains across different tasks.
arXiv Detail & Related papers (2020-11-07T22:52:21Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.