Related papers: Graph-to-Text Generation with Dynamic Structure Pr…

Generating text from structured inputs, such as meaning representations or RDF triples, has often involved the use of specialized graph-encoding neural networks. However, recent applications of pretrained transformers to linearizations of…

We propose the Graph Context Encoder (GCE), a simple but efficient approach for graph representation learning based on graph feature masking and reconstruction. GCE models are trained to efficiently reconstruct input graphs similarly to a…

Generating texts which express complex ideas spanning multiple sentences requires a structured representation of their content (document plan), but these representations are prohibitively expensive to manually produce. In this work, we…

In recent years, the long-range attention mechanism of vision transformers has driven significant performance breakthroughs across various computer vision tasks. However, the traditional self-attention mechanism, which processes both…

Structure aware graph generation aims to generate graphs that satisfy given topological properties. It has applications in domains such as drug discovery, social network modeling, and knowledge graph construction. Unlike existing methods…

Graph-based clustering plays an important role in the clustering area. Recent studies about graph convolution neural networks have achieved impressive success on graph type data. However, in general clustering tasks, the graph structure of…

Graph Retrieval-Augmented Generation (GRAG or Graph RAG) architectures aim to enhance language understanding and generation by leveraging external knowledge. However, effectively capturing and integrating the rich semantic information…

When applying the Transformer architecture to source code, designing a good self-attention mechanism is critical as it affects how node relationship is extracted from the Abstract Syntax Trees (ASTs) of the source code. We present Code…

Graph Representation Learning (GRL) is an influential methodology, enabling a more profound understanding of graph-structured data and aiding graph clustering, a critical task across various domains. The recent incursion of attention…

Ever since neural models were adopted in data-to-text language generation, they have invariably been reliant on extrinsic components to improve their semantic accuracy, because the models normally do not exhibit the ability to generate text…

The emerging graph Transformers have achieved impressive performance for graph representation learning over graph neural networks (GNNs). In this work, we regard the self-attention mechanism, the core module of graph Transformers, as a…

Auto-encoders have emerged as a successful framework for unsupervised learning. However, conventional auto-encoders are incapable of utilizing explicit relations in structured data. To take advantage of relations in graph-structured data,…

Scene Text Recognition (STR), the task of recognizing text against complex image backgrounds, is an active area of research. Current state-of-the-art (SOTA) methods still struggle to recognize text written in arbitrary shapes. In this…

A video-grounded dialogue system referred to as the Structured Co-reference Graph Attention (SCGA) is presented for decoding the answer sequence to a question regarding a given video while keeping track of the dialogue context. Although…

Discourse representation tree structure (DRTS) parsing is a novel semantic parsing task which has been concerned most recently. State-of-the-art performance can be achieved by a neural sequence-to-sequence model, treating the tree…

In this paper, we introduce VACA, a novel class of variational graph autoencoders for causal inference in the absence of hidden confounders, when only observational data and the causal graph are available. Without making any parametric…

Generative networks have made it possible to generate meaningful signals such as images and texts from simple noise. Recently, generative methods based on GAN and VAE were developed for graphs and graph signals. However, the mathematical…

There has been a recent surge in transformer-based architectures for learning on graphs, mainly motivated by attention as an effective learning mechanism and the desire to supersede handcrafted operators characteristic of message passing…

Text-to-CAD code generation is a long-horizon task that translates textual instructions into long sequences of interdependent operations. Existing methods typically decode text directly into executable code (e.g., bpy) without explicitly…

State-of-the-art audio captioning methods typically use the encoder-decoder structure with pretrained audio neural networks (PANNs) as encoders for feature extraction. However, the convolution operation used in PANNs is limited in capturing…