相关论文: Exploring Faithful Rationale for Multi-hop Fact Ve…

The success of deep learning models on multi-hop fact verification has prompted researchers to understand the behavior behind their veracity. One possible way is erasure search: obtaining the rationale by entirely removing a subset of input…

The growing complexity of factual claims in real-world scenarios presents significant challenges for automated fact verification systems, particularly in accurately aggregating and reasoning over multi-hop evidence. Existing approaches…

Multi-hop reading comprehension across multiple documents attracts much attention recently. In this paper, we propose a novel approach to tackle this multi-hop reading comprehension problem. Inspired by human reasoning processing, we…

Explainable multi-hop question answering (QA) not only predicts answers but also identifies rationales, i. e. subsets of input sentences used to derive the answers. This problem has been extensively studied under the supervised setting,…

This paper studies faithful explanations for Graph Neural Networks (GNNs). First, we provide a new and general method for formally characterizing the faithfulness of explanations for GNNs. It applies to existing explanation methods,…

In recent years, there has been a surge of interests in interpretable graph reasoning methods. However, these models often suffer from limited performance when working on sparse and incomplete graphs, due to the lack of evidential paths…

Multi-hop reading comprehension focuses on one type of factoid question, where a system needs to properly integrate multiple pieces of evidence to correctly answer a question. Previous work approximates global evidence with local…

Graph neural networks (GNNs) excel in graph representation learning by integrating graph structure and node features. Existing GNNs, unfortunately, fail to account for the uncertainty of class probabilities that vary with the depth of the…

Automated fact-checking aims to assess the truthfulness of textual claims based on relevant evidence. However, verifying complex claims that require multi-hop reasoning remains a significant challenge. We propose GraphCheck, a novel…

Multi-hop reading comprehension (MHRC) requires not only to predict the correct answer span in the given passage, but also to provide a chain of supporting evidences for reasoning interpretability. It is natural to model such a process into…

This paper proposes an iterative inference algorithm for multi-hop explanation regeneration, that retrieves relevant factual evidence in the form of text snippets, given a natural language question and its answer. Combining multiple sources…

Graph Convolutional Networks (GCNs) have made significant advances in semi-supervised learning, especially for classification tasks. However, existing GCN based methods have two main drawbacks. First, to increase the receptive field and…

Graph convolutional network (GCN) has become popular in various natural language processing (NLP) tasks with its superiority in long-term and non-consecutive word interactions. However, existing single-hop graph reasoning in GCN may miss…

Fact verification aims to automatically probe the veracity of a claim based on several pieces of evidence. Existing works are always engaging in accuracy improvement, let alone explainability, a critical capability of fact verification…

Automatic multi-hop fact verification task has gained significant attention in recent years. Despite impressive results, these well-designed models perform poorly on out-of-domain data. One possible solution is to augment the training data…

Recent work has proposed multi-hop models and datasets for studying complex natural language reasoning. One notable task requiring multi-hop reasoning is fact checking, where a set of connected evidence pieces leads to the final verdict of…

This paper presents an end-to-end system for fact extraction and verification using textual and tabular evidence, the performance of which we demonstrate on the FEVEROUS dataset. We experiment with both a multi-task learning paradigm to…

Massive deployment of Graph Neural Networks (GNNs) in high-stake applications generates a strong demand for explanations that are robust to noise and align well with human intuition. Most existing methods generate explanations by…

Question Answering for complex questions is often modeled as a graph construction or traversal task, where a solver must build or traverse a graph of facts that answer and explain a given question. This "multi-hop" inference has been shown…

Fact checking aims to predict claim veracity by reasoning over multiple evidence pieces. It usually involves evidence retrieval and veracity reasoning. In this paper, we focus on the latter, reasoning over unstructured text and structured…