Factkb: Generalizable factuality evaluation using language models enhanced with factual knowledge
Evaluating the factual consistency of automatically generated summaries is essential for the
progress and adoption of reliable summarization systems. Despite recent advances, existing …
progress and adoption of reliable summarization systems. Despite recent advances, existing …
Interpretable multimodal misinformation detection with logic reasoning
Multimodal misinformation on online social platforms is becoming a critical concern due to
increasing credibility and easier dissemination brought by multimedia content, compared to …
increasing credibility and easier dissemination brought by multimedia content, compared to …
Document-level event argument extraction with a chain reasoning paradigm
Document-level event argument extraction aims to identify event arguments beyond
sentence level, where a significant challenge is to model long-range dependencies …
sentence level, where a significant challenge is to model long-range dependencies …
Self-supervised logic induction for explainable fuzzy temporal commonsense reasoning
Understanding temporal commonsense concepts, such as times of occurrence and
durations is crucial for event-centric language understanding. Reasoning about such …
durations is crucial for event-centric language understanding. Reasoning about such …
It is not about what you say, it is about how you say it: A surprisingly simple approach for improving reading comprehension
Natural language processing has seen rapid progress over the past decade. Due to the
speed of developments, some practices get established without proper evaluation …
speed of developments, some practices get established without proper evaluation …
Logical reasoning over natural language as knowledge representation: A survey
Logical reasoning is central to human cognition and intelligence. It includes deductive,
inductive, and abductive reasoning. Past research of logical reasoning within AI uses formal …
inductive, and abductive reasoning. Past research of logical reasoning within AI uses formal …
Adversarial Entity Graph Convolutional Networks for multi-hop inference question answering
Y Du, R Yan, Y Hou, Y Pei, H Han - Expert Systems with Applications, 2024 - Elsevier
Multi-hop reasoning is critical for natural language understanding but poses challenges for
current models, requiring models capable of aggregating and reasoning across multiple …
current models, requiring models capable of aggregating and reasoning across multiple …
Neural ranking with weak supervision for open-domain question answering: A survey
Neural ranking (NR) has become a key component for open-domain question-answering in
order to access external knowledge. However, training a good NR model requires …
order to access external knowledge. However, training a good NR model requires …
A legal multi-choice question answering model based on bert and attention
G Chen, X Luo, J Zhu - International Conference on Knowledge Science …, 2023 - Springer
Legal question answering is one of the critical topics in the field of legal intelligence, and the
judicial examination is a multi-choice question-answering task. However, previous scoring …
judicial examination is a multi-choice question-answering task. However, previous scoring …
Enhanced question understanding for multi-type legal question answering
Abstract Multi-type Legal Question Answering (MLQA) aims to automatically respond to legal
questions presented in natural language. Current MLQA models generally include a text …
questions presented in natural language. Current MLQA models generally include a text …