A Paragraph-level Multi-task Learning Model for Scientific Fact-Verification
arXiv:2012.14500
Abstract
Even for domain experts, it is a non-trivial task to verify a scientific claim by providing supporting or refuting evidence rationales. The situation worsens as misinformation is proliferated on social media or news websites, manually or programmatically, at every moment. As a result, an automatic fact-verification tool becomes crucial for combating the spread of misinformation. In this work, we propose a novel, paragraph-level, multi-task learning model for the SciFact task by directly computing a sequence of contextualized sentence embeddings from a BERT model and jointly training the model on rationale selection and stance prediction.
arXiv comment5 pages; The AAAI-21 Workshop on Scientific Document Understanding
References in corpus (9)
- Distributed Representations of Words and Phrases and their Compositionality
- Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
- Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
- Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Features
- SemEval-2017 Task 8: RumourEval: Determining rumour veracity and support for rumours
- Seeing Things from a Different Angle: Discovering Diverse Perspectives about Claims
- TwoWingOS: A Two-Wing Optimization Strategy for Evidential Claim Verification
- Scientific Claim Verification with VERT5ERINI
- A Richly Annotated Corpus for Different Tasks in Automated Fact-Checking