Related papers: Type-Constrained Representation Learning in Knowle…

Large Language Models (LLMs) have shown remarkable capabilities in processing various data structures, including graphs. While previous research has focused on developing textual encoding methods for graph representation, the emergence of…

Large language models (LLMs) have garnered significant attention for their superior performance in many knowledge-driven applications on the world wide web.These models are designed to train hundreds of millions or more parameters on large…

With the development of deep learning technology, large language models have achieved remarkable results in many natural language processing tasks. However, these models still have certain limitations in handling complex reasoning tasks and…

Concept Bottleneck Models (CBMs) provide explicit interpretations for deep neural networks through concepts and allow intervention with concepts to adjust final predictions. Existing CBMs assume concepts are conditionally independent given…

Text-Attributed Graphs (TAGs) are graphs of connected textual documents. Graph models can efficiently learn TAGs, but their training heavily relies on human-annotated labels, which are scarce or even unavailable in many applications. Large…

As larger deep learning models are hard to interpret, there has been a recent focus on generating explanations of these black-box models. In contrast, we may have apriori explanations of how models should behave. In this paper, we formalize…

Semantic networks, such as the knowledge graph, can represent the knowledge leveraging the graph structure. Although the knowledge graph shows promising values in natural language processing, it suffers from incompleteness. This paper…

Syntactic structures used to play a vital role in natural language processing (NLP), but since the deep learning revolution, NLP has been gradually dominated by neural models that do not consider syntactic structures in their design. One…

In the domain of semi-supervised learning, the current approaches insufficiently exploit the potential of considering inter-instance relationships among (un)labeled data. In this work, we address this limitation by providing an approach for…

Pre-training language models (LMs) on large-scale unlabeled text data makes the model much easier to achieve exceptional downstream performance than their counterparts directly trained on the downstream tasks. In this work, we study what…

Previous works show that Pre-trained Language Models (PLMs) can capture factual knowledge. However, some analyses reveal that PLMs fail to perform it robustly, e.g., being sensitive to the changes of prompts when extracting factual…

Temporal Knowledge Graphs have emerged as a powerful way of not only modeling static relationships between entities but also the dynamics of how relations evolve over time. As these informational structures can be used to store information…

Knowledge enhanced pre-trained language models (K-PLMs) are shown to be effective for many public tasks in the literature but few of them have been successfully applied in practice. To address this problem, we propose K-AID, a systematic…

Pre-trained language models (LMs) are used for knowledge intensive tasks like question answering, but their knowledge gets continuously outdated as the world changes. Prior work has studied targeted updates to LMs, injecting individual…

Table foundation models bring high hopes to data science: pre-trained on tabular data to embark knowledge or priors, they should facilitate downstream tasks on tables. One specific challenge is that of data semantics: numerical entries take…

Recent advances in employing neural networks on graph domains helped push the state of the art in link prediction tasks, particularly in recommendation services. However, the use of temporal contextual information, often modeled as dynamic…

Knowledge embeddings (KE) represent a knowledge graph (KG) by embedding entities and relations into continuous vector spaces. Existing methods are mainly structure-based or description-based. Structure-based methods learn representations…

We investigate whether the hidden states of large language models (LLMs) can be used to estimate and impute economic and financial statistics. Focusing on county-level (e.g. unemployment) and firm-level (e.g. total assets) variables, we…

The knowledge-grounded dialogue task aims to generate responses that convey information from given knowledge documents. However, it is a challenge for the current sequence-based model to acquire knowledge from complex documents and…

A key obstacle in automated analytics and meta-learning is the inability to recognize when different datasets contain measurements of the same variable. Because provided attribute labels are often uninformative in practice, this task may be…