Related papers: Recursive Non-Autoregressive Graph-to-Graph Transf…

Different languages might have different word orders. In this paper, we investigate cross-lingual transfer and posit that an order-agnostic model will perform better when transferring to distant foreign languages. To test our hypothesis, we…

Objects in a scene are not always related. The execution efficiency of the one-stage scene graph generation approaches are quite high, which infer the effective relation between entity pairs using sparse proposal sets and a few queries.…

AMR-to-text generation is a problem recently introduced to the NLP community, in which the goal is to generate sentences from Abstract Meaning Representation (AMR) graphs. Sequence-to-sequence models can be used to this end by converting…

Graph Transformers (GTs) have significantly advanced the field of graph representation learning by overcoming the limitations of message-passing graph neural networks (GNNs) and demonstrating promising performance and expressive power.…

Motivation: Drug repurposing is a viable solution for reducing the time and cost associated with drug development. However, thus far, the proposed drug repurposing approaches still need to meet expectations. Therefore, it is crucial to…

So far, a very large amount of work in Natural Language Processing (NLP) rely on trees as the core mathematical structure to represent linguistic informations (e.g. in Chomsky's work). However, some linguistic phenomena do not cope properly…

Graph Neural Networks (GNNs) are effective tools for graph representation learning. Most GNNs rely on a recursive neighborhood aggregation scheme, named message passing, thereby their theoretical expressive power is limited to the…

Tensor ring (TR) decomposition is a powerful tool for exploiting the low-rank nature of multiway data and has demonstrated great potential in a variety of important applications. In this paper, nonnegative tensor ring (NTR) decomposition…

Cross-modal retrieval is gaining increasing efficacy and interest from the research community, thanks to large-scale training, novel architectural and learning designs, and its application in LLMs and multimodal LLMs. In this paper, we move…

Truncated Backpropagation Through Time (truncated BPTT) is a widespread method for learning recurrent computational graphs. Truncated BPTT keeps the computational benefits of Backpropagation Through Time (BPTT) while relieving the need for…

The introduction of pre-trained transformer-based contextualized word embeddings has led to considerable improvements in the accuracy of graph-based parsers for frameworks such as Universal Dependencies (UD). However, previous works differ…

Transformer architectures have exhibited remarkable performance in image super-resolution (SR). Since the quadratic computational complexity of the self-attention (SA) in Transformer, existing methods tend to adopt SA in a local region to…

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…

Automatic construction of relevant Knowledge Bases (KBs) from text, and generation of semantically meaningful text from KBs are both long-standing goals in Machine Learning. In this paper, we present ReGen, a bidirectional generation of…

Anatomical trees play an important role in clinical diagnosis and treatment planning. Yet, accurately representing these structures poses significant challenges owing to their intricate and varied topology and geometry. Most existing…

Unconstrained handwritten text recognition is a major step in most document analysis tasks. This is generally processed by deep recurrent neural networks and more specifically with the use of Long Short-Term Memory cells. The main drawbacks…

Traffic forecasting is a fundamental problem in intelligent transportation systems. Existing traffic predictors are limited by their expressive power to model the complex spatial-temporal dependencies in traffic data, mainly due to the…

Graph Convolutional Representation (GCR) has achieved impressive performance for graph data representation. However, existing GCR is generally defined on the input fixed graph which may restrict the representation capacity and also be…

This study presents a novel model for invertible sentence embeddings using a residual recurrent network trained on an unsupervised encoding task. Rather than the probabilistic outputs common to neural machine translation models, our…

Sequential recommendation (SR) is to accurately recommend a list of items for a user based on her current accessed ones. While new-coming users continuously arrive in the real world, one crucial task is to have inductive SR that can produce…