Related papers: Fine-Grained Modeling of Narrative Context: A Cohe…
Generalized text representations are the foundation of many natural language understanding tasks. To fully utilize the different corpus, it is inevitable that models need to understand the relevance among them. However, many methods ignore…
Knowledge graph embedding, which projects symbolic entities and relations into continuous vector spaces, is gaining increasing attention. Previous methods allow a single static embedding for each entity or relation, ignoring their intrinsic…
Natural Questions is a new challenging machine reading comprehension benchmark with two-grained answers, which are a long answer (typically a paragraph) and a short answer (one or more entities inside the long answer). Despite the…
We study question answering over a dynamic textual environment. Although neural network models achieve impressive accuracy via learning from input-output examples, they rarely leverage various types of knowledge and are generally not…
Document-level relation extraction is a complex human process that requires logical inference to extract relationships between named entities in text. Existing approaches use graph-based neural models with words as nodes and edges as…
Conversational machine comprehension (MC) has proven significantly more challenging compared to traditional MC since it requires better utilization of conversation history. However, most existing approaches do not effectively capture…
Inductive link prediction -- where entities during training and inference stages can be different -- has shown great potential for completing evolving knowledge graphs in an entity-independent manner. Many popular methods mainly focus on…
Understanding narrative text requires capturing characters' motivations, goals, and mental states. This paper proposes an Entity-based Narrative Graph (ENG) to model the internal-states of characters in a story. We explicitly model…
The paper studies sequential reasoning over graph-structured data, which stands as a fundamental task in various trending fields like automated math problem solving and neural graph algorithm learning, attracting a lot of research interest.…
Joint entity and relation extraction plays a pivotal role in various applications, notably in the construction of knowledge graphs. Despite recent progress, existing approaches often fall short in two key aspects: richness of representation…
Frame semantic parsing is a semantic analysis task based on FrameNet which has received great attention recently. The task usually involves three subtasks sequentially: (1) target identification, (2) frame classification and (3) semantic…
Graph Neural Networks (GNNs) have gained great popularity in tackling various analytical tasks on graph-structured data (i.e., networks). Typical GNNs and their variants follow a message-passing manner that obtains network representations…
In-context learning is the ability of a pretrained model to adapt to novel and diverse downstream tasks by conditioning on prompt examples, without optimizing any parameters. While large language models have demonstrated this ability, how…
Existing approaches to image captioning usually generate the sentence word-by-word from left to right, with the constraint of conditioned on local context including the given image and history generated words. There have been many studies…
Our world is shaped by events of various complexity. This includes both small-scale local events like local farmer markets and large complex events like political and military conflicts. The latter are typically not observed directly but…
Learning in the space-time domain remains a very challenging problem in machine learning and computer vision. Current computational models for understanding spatio-temporal visual data are heavily rooted in the classical single-image based…
This paper addresses the problems of missing reasoning chains and insufficient entity-level semantic understanding in large language models when dealing with tasks that require structured knowledge. It proposes a fine-tuning algorithm…
Graph-based convolutional model such as non-local block has shown to be effective for strengthening the context modeling ability in convolutional neural networks (CNNs). However, its pixel-wise computational overhead is prohibitive which…
Conditional image modeling based on textual descriptions is a relatively new domain in unsupervised learning. Previous approaches use a latent variable model and generative adversarial networks. While the formers are approximated by using…
Recently, graph neural networks (GNNs) have been widely used for document classification. However, most existing methods are based on static word co-occurrence graphs without sentence-level information, which poses three challenges:(1) word…