相关论文: Punctuation-aware treebank tree binarization

Prompt tuning has achieved great success in transferring the knowledge from large pretrained vision-language models into downstream tasks, and has dominated the performance on visual grounding (VG). However, almost all existing prompt…

For the task of subdecimeter aerial imagery segmentation, fine-grained semantic segmentation results are usually difficult to obtain because of complex remote sensing content and optical conditions. Recently, convolutional neural networks…

Many operations on sensory data -- comparison, memory, retrieval, and reasoning -- are naturally expressed over discrete symbolic structures. In language this interface is given by tokens; in audio, it must be learned. Existing audio…

We propose two fast neural combinatory models for constituency parsing: binary and multi-branching. Our models decompose the bottom-up parsing process into 1) classification of tags, labels, and binary orientations or chunks and 2) vector…

In this work, we unify several existing decoding strategies for punctuation prediction in one framework and introduce a novel strategy which utilises multiple predictions at each word across different windows. We show that significant…

Generative retrieval (GR) ranks documents by autoregressively generating document identifiers. Because many GR methods rely on trie-constrained beam search, they are vulnerable to early pruning of relevant prefixes under finite-beam…

Learning per-point semantic features from the hierarchical feature pyramid is essential for point cloud semantic segmentation. However, most previous methods suffered from ambiguous region features or failed to refine per-point features…

We present a new paradigm for fine-tuning large-scale visionlanguage pre-trained models on downstream task, dubbed Prompt Regularization (ProReg). Different from traditional fine-tuning which easily overfits to the downstream task data,…

The high-frequency issuance and short-cycle speculation of meme tokens in decentralized finance (DeFi) have significantly amplified rug-pull risk. Existing approaches still struggle to provide stable early warning under scarce anomalies,…

A typical information extraction pipeline consists of token- or span-level classification models coupled with a series of pre- and post-processing scripts. In a production pipeline, requirements often change, with classes being added and…

The growth in the complexity of Convolutional Neural Networks (CNNs) is increasing interest in partitioning a network across multiple accelerators during training and pipelining the backpropagation computations over the accelerators.…

Bagging and boosting, two effective machine learning techniques, are applied to natural language parsing. Experiments using these techniques with a trainable statistical parser are described. The best resulting system provides roughly as…

Predicting structured outputs such as semantic segmentation relies on expensive per-pixel annotations to learn supervised models like convolutional neural networks. However, models trained on one data domain may not generalize well to other…

Unsupervised Domain Adaptation (UDA) leverages a labeled source domain to solve tasks in an unlabeled target domain. While Transformer-based methods have shown promise in UDA, their application is limited to plain Transformers, excluding…

We introduce a tree-structured attention neural network for sentences and small phrases and apply it to the problem of sentiment classification. Our model expands the current recursive models by incorporating structural information around a…

We propose a novel high-performance and interpretable canonical deep tabular data learning architecture, TabNet. TabNet uses sequential attention to choose which features to reason from at each decision step, enabling interpretability and…

The prevailing approach for training and evaluating paraphrase identification models is constructed as a binary classification problem: the model is given a pair of sentences, and is judged by how accurately it classifies pairs as either…

Neural network have achieved remarkable successes in many scientific fields. However, the interpretability of the neural network model is still a major bottlenecks to deploy such technique into our daily life. The challenge can dive into…

Scientific time series often encode predictive geometric structure, including connectivity, cycles, shell-like geometry, directional changes, and nonlinear neighborhoods, that standard dot-product attention does not explicitly represent. We…

The purpose of binary segmentation models is to determine which pixels belong to an object of interest (e.g., which pixels in an image are part of roads). The models assign a logit score (i.e., probability) to each pixel and these are…