Related papers: KG-BART: Knowledge Graph-Augmented BART for Genera…
Reasoning is a critical ability towards complete visual understanding. To develop machine with cognition-level visual understanding and reasoning abilities, the visual commonsense reasoning (VCR) task has been introduced. In VCR, given a…
Commonsense question answering (QA) requires a model to grasp commonsense and factual knowledge to answer questions about world events. Many prior methods couple language modeling with knowledge graphs (KG). However, although a KG contains…
Existing KG-augmented models for commonsense question answering primarily focus on designing elaborate Graph Neural Networks (GNNs) to model knowledge graphs (KGs). However, they ignore (i) the effectively fusing and reasoning over question…
Multi-paragraph reasoning is indispensable for open-domain question answering (OpenQA), which receives less attention in the current OpenQA systems. In this work, we propose a knowledge-enhanced graph neural network (KGNN), which performs…
Humans use natural language to compose common concepts from their environment into plausible, day-to-day scene descriptions. However, such generative commonsense reasoning (GCSR) skills are lacking in state-of-the-art text generation…
Knowledge Graphs (KGs) have proven essential in information processing and reasoning applications because they link related entities and give context-rich information, supporting efficient information retrieval and knowledge discovery;…
We investigate the use of multimodal information contained in images as an effective method for enhancing the commonsense of Transformer models for text generation. We perform experiments using BART and T5 on concept-to-text generation,…
Generative commonsense reasoning requires machines to generate sentences describing an everyday scenario given several concepts, which has attracted much attention recently. However, existing models cannot perform as well as humans, since…
While large language models (LLMs) have made considerable advancements in understanding and generating unstructured text, their application in structured data remains underexplored. Particularly, using LLMs for complex reasoning tasks on…
Commonsense explanation generation aims to empower the machine's sense-making capability by generating plausible explanations to statements against commonsense. While this task is easy to human, the machine still struggles to generate…
Multi-hop question generation (MQG) aims to generate complex questions which require reasoning over multiple pieces of information of the input passage. Most existing work on MQG has focused on exploring graph-based networks to equip the…
Generative commonsense reasoning (GCR) in natural language is to reason about the commonsense while generating coherent text. Recent years have seen a surge of interest in improving the generation quality of commonsense reasoning tasks.…
Commonsense knowledge is paramount to enable intelligent systems. Typically, it is characterized as being implicit and ambiguous, hindering thereby the automation of its acquisition. To address these challenges, this paper presents…
We present the first comprehensive study on automatic knowledge base construction for two prevalent commonsense knowledge graphs: ATOMIC (Sap et al., 2019) and ConceptNet (Speer et al., 2017). Contrary to many conventional KBs that store…
The context-aware emotional reasoning ability of AI systems, especially in conversations, is of vital importance in applications such as online opinion mining from social media and empathetic dialogue systems. Due to the implicit nature of…
Large language models (LLMs) typically improve performance by either retrieving semantically similar information, or enhancing reasoning abilities through structured prompts like chain-of-thought. While both strategies are considered…
Prior work has shown that the ordering in which concepts are shown to a commonsense generator plays an important role, affecting the quality of the generated sentence. However, it remains a challenge to determine the optimal ordering of a…
The knowledge graph (KG) stores a large amount of structural knowledge, while it is not easy for direct human understanding. Knowledge graph-to-text (KG-to-text) generation aims to generate easy-to-understand sentences from the KG, and at…
Answering complex questions about textual narratives requires reasoning over both stated context and the world knowledge that underlies it. However, pretrained language models (LM), the foundation of most modern QA systems, do not robustly…
Scene graphs are powerful representations that parse images into their abstract semantic elements, i.e., objects and their interactions, which facilitates visual comprehension and explainable reasoning. On the other hand, commonsense…