相关论文: Snowman: A Million-scale Chinese Commonsense Knowl…

Generative commonsense reasoning which aims to empower machines to generate sentences with the capacity of reasoning over a set of concepts is a critical bottleneck for text generation. Even the state-of-the-art pre-trained language…

Knowledge graph (KG) is an abstraction that can be extracted from text corpora and used for in-depth reasoning. Prior work has leveraged KGs to fine-tune language models (LMs), enabling domain-specific superintelligence. In this work, we…

Recent research suggests that neural machine translation (MT) in the news domain has reached human-level performance, but for other professional domains, it is far below the level. In this paper, we conduct a fine-grained systematic human…

Knowledge graphs (KGs), which could provide essential relational information between entities, have been widely utilized in various knowledge-driven applications. Since the overall human knowledge is innumerable that still grows explosively…

In any system that uses structured knowledge graph (KG) data as its underlying knowledge representation, KG-to-text generation is a useful tool for turning parts of the graph data into text that can be understood by humans. Recent work has…

Commonsense knowledge about everyday concepts is an important asset for AI applications, such as question answering and chatbots. Recently, we have seen an increasing interest in the construction of structured commonsense knowledge bases…

Large Language Models (LLMs) possess human-level cognitive and decision-making capabilities, making them a key technology for 6G. However, applying LLMs to the communication domain faces three major challenges: 1) Inadequate communication…

Pretrained language models have excelled at many NLP tasks recently; however, their social intelligence is still unsatisfactory. To enable this, machines need to have a more general understanding of our complicated world and develop the…

Commonsense knowledge is essential for advancing natural language processing (NLP) by enabling models to engage in human-like reasoning, which requires a deeper understanding of context and often involves making inferences based on implicit…

Analyzing ethnic or religious bias is important for improving fairness, accountability, and transparency of natural language processing models. However, many techniques rely on human-compiled lists of bias terms, which are expensive to…

Knowledge graphs store a large number of factual triples while they are still incomplete, inevitably. The previous knowledge graph completion (KGC) models predict missing links between entities merely relying on fact-view data, ignoring the…

The construction of Generalized Knowledge Graph (GKG), including knowledge graph, event knowledge graph and commonsense knowledge graph, is fundamental for various natural language processing tasks. Current studies typically construct these…

This paper shows how to construct knowledge graphs (KGs) from pre-trained language models (e.g., BERT, GPT-2/3), without human supervision. Popular KGs (e.g, Wikidata, NELL) are built in either a supervised or semi-supervised manner,…

Researchers have pursued neurosymbolic artificial intelligence (AI) applications for nearly three decades. A marriage of the neural and symbolic components can lead to rapid advancements in AI. Yet, the field has not realized this promise…

Commonsense knowledge is essential for many AI applications, including those in natural language processing, visual processing, and planning. Consequently, many sources that include commonsense knowledge have been designed and constructed…

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…

Knowledge Graphs (KGs) are extensively used across different domains and in several applications. Often, these KGs are very large in size. Such KGs become unwieldy for tasks such as question answering and visualization. Summarization of KGs…

Language models (LMs) trained on large amounts of data have shown impressive performance on many NLP tasks under the zero-shot and few-shot setup. Here we aim to better understand the extent to which such models learn commonsense knowledge…

Pre-trained Language Models (PLMs) have proven to be beneficial for various downstream NLP tasks. Recently, GPT-3, with 175 billion parameters and 570GB training data, drew a lot of attention due to the capacity of few-shot (even zero-shot)…

Recent interest in building foundation models for KGs has highlighted a fundamental challenge: knowledge-graph data is relatively scarce. The best-known KGs are primarily human-labeled, created by pattern-matching, or extracted using early…