端到端的口语理解（SLU）使用单个模型直接从音频中预测意图。它有望通过利用中间文本表示中丢失的声学信息来提高助手系统的性能，并防止自动语音识别（ASR）中的级联错误。此外，在部署助手系统时，拥有一个统一模型具有效率优势。但是，具有语义解析标签的公共音频数据集有限的数量阻碍了该领域的研究进展。在本文中，我们发布了以任务为导向的语义解析（Stop）数据集，该数据集是公开可用的最大，最复杂的SLU数据集。此外，我们定义了低资源拆分，以建立有限的标记数据时改善SLU的基准。此外，除了人类录制的音频外，我们还发布了TTS生成版本，以基于端到端SLU系统的低资源域适应性的性能。最初的实验表明，端到端SLU模型的性能比级联的同行差一些，我们希望这能鼓励未来的工作。

我们提出了一种基于审议的新型方法来端到端（E2E）口语理解（SLU），其中流媒体自动语音识别（ASR）模型会产生第一频繁的假设和第二通通的自然语言（NLU）（NLU） ）组件通过对ASR的文本和音频嵌入来生成语义解析。通过将E2E SLU制定为广义解码器，我们的系统能够支持复杂的组成语义结构。此外，ASR和NLU之间的参数共享使该系统特别适合资源受限的（内部设备）环境；我们提出的方法始终在TOPV2数据集的口头版本（Stop）的口语版本上始终优于强大管道NLU基线的0.60％至0.65％。我们证明了文本和音频功能的融合，再加上系统重写第一通道假设的能力，使我们的方法对ASR错误更加强大。最后，我们表明我们的方法可以显着减少从自然语音到合成语音训练时的降解，但是要使文本到语音（TTS）成为可行的解决方案，以扩大E2E SLU。

Implicit Neural Representations (INR) have recently shown to be powerful tool for high-quality video compression. However, existing works are limiting as they do not explicitly exploit the temporal redundancy in videos, leading to a long encoding time. Additionally, these methods have fixed architectures which do not scale to longer videos or higher resolutions. To address these issues, we propose NIRVANA, which treats videos as groups of frames and fits separate networks to each group performing patch-wise prediction. This design shares computation within each group, in the spatial and temporal dimensions, resulting in reduced encoding time of the video. The video representation is modeled autoregressively, with networks fit on a current group initialized using weights from the previous group's model. To further enhance efficiency, we perform quantization of the network parameters during training, requiring no post-hoc pruning or quantization. When compared with previous works on the benchmark UVG dataset, NIRVANA improves encoding quality from 37.36 to 37.70 (in terms of PSNR) and the encoding speed by 12X, while maintaining the same compression rate. In contrast to prior video INR works which struggle with larger resolution and longer videos, we show that our algorithm is highly flexible and scales naturally due to its patch-wise and autoregressive designs. Moreover, our method achieves variable bitrate compression by adapting to videos with varying inter-frame motion. NIRVANA achieves 6X decoding speed and scales well with more GPUs, making it practical for various deployment scenarios.

The ability to jointly learn from multiple modalities, such as text, audio, and visual data, is a defining feature of intelligent systems. While there have been promising advances in designing neural networks to harness multimodal data, the enormous success of data augmentation currently remains limited to single-modality tasks like image classification. Indeed, it is particularly difficult to augment each modality while preserving the overall semantic structure of the data; for example, a caption may no longer be a good description of an image after standard augmentations have been applied, such as translation. Moreover, it is challenging to specify reasonable transformations that are not tailored to a particular modality. In this paper, we introduce LeMDA, Learning Multimodal Data Augmentation, an easy-to-use method that automatically learns to jointly augment multimodal data in feature space, with no constraints on the identities of the modalities or the relationship between modalities. We show that LeMDA can (1) profoundly improve the performance of multimodal deep learning architectures, (2) apply to combinations of modalities that have not been previously considered, and (3) achieve state-of-the-art results on a wide range of applications comprised of image, text, and tabular data.

This work presents a physics-informed deep learning-based super-resolution framework to enhance the spatio-temporal resolution of the solution of time-dependent partial differential equations (PDE). Prior works on deep learning-based super-resolution models have shown promise in accelerating engineering design by reducing the computational expense of traditional numerical schemes. However, these models heavily rely on the availability of high-resolution (HR) labeled data needed during training. In this work, we propose a physics-informed deep learning-based framework to enhance the spatial and temporal resolution of coarse-scale (both in space and time) PDE solutions without requiring any HR data. The framework consists of two trainable modules independently super-resolving the PDE solution, first in spatial and then in temporal direction. The physics based losses are implemented in a novel way to ensure tight coupling between the spatio-temporally refined outputs at different times and improve framework accuracy. We analyze the capability of the developed framework by investigating its performance on an elastodynamics problem. It is observed that the proposed framework can successfully super-resolve (both in space and time) the low-resolution PDE solutions while satisfying physics-based constraints and yielding high accuracy. Furthermore, the analysis and obtained speed-up show that the proposed framework is well-suited for integration with traditional numerical methods to reduce computational complexity during engineering design.

Vision Transformers (ViTs) have gained significant popularity in recent years and have proliferated into many applications. However, it is not well explored how varied their behavior is under different learning paradigms. We compare ViTs trained through different methods of supervision, and show that they learn a diverse range of behaviors in terms of their attention, representations, and downstream performance. We also discover ViT behaviors that are consistent across supervision, including the emergence of Offset Local Attention Heads. These are self-attention heads that attend to a token adjacent to the current token with a fixed directional offset, a phenomenon that to the best of our knowledge has not been highlighted in any prior work. Our analysis shows that ViTs are highly flexible and learn to process local and global information in different orders depending on their training method. We find that contrastive self-supervised methods learn features that are competitive with explicitly supervised features, and they can even be superior for part-level tasks. We also find that the representations of reconstruction-based models show non-trivial similarity to contrastive self-supervised models. Finally, we show how the "best" layer for a given task varies by both supervision method and task, further demonstrating the differing order of information processing in ViTs.

Experimental sciences have come to depend heavily on our ability to organize, interpret and analyze high-dimensional datasets produced from observations of a large number of variables governed by natural processes. Natural laws, conservation principles, and dynamical structure introduce intricate inter-dependencies among these observed variables, which in turn yield geometric structure, with fewer degrees of freedom, on the dataset. We show how fine-scale features of this structure in data can be extracted from \emph{discrete} approximations to quantum mechanical processes given by data-driven graph Laplacians and localized wavepackets. This data-driven quantization procedure leads to a novel, yet natural uncertainty principle for data analysis induced by limited data. We illustrate the new approach with algorithms and several applications to real-world data, including the learning of patterns and anomalies in social distancing and mobility behavior during the COVID-19 pandemic.

This paper aims to provide an unsupervised modelling approach that allows for a more flexible representation of text embeddings. It jointly encodes the words and the paragraphs as individual matrices of arbitrary column dimension with unit Frobenius norm. The representation is also linguistically motivated with the introduction of a novel similarity metric. The proposed modelling and the novel similarity metric exploits the matrix structure of embeddings. We then go on to show that the same matrices can be reshaped into vectors of unit norm and transform our problem into an optimization problem over the spherical manifold. We exploit manifold optimization to efficiently train the matrix embeddings. We also quantitatively verify the quality of our text embeddings by showing that they demonstrate improved results in document classification, document clustering, and semantic textual similarity benchmark tests.

Often questions provided to open-domain question answering systems are ambiguous. Traditional QA systems that provide a single answer are incapable of answering ambiguous questions since the question may be interpreted in several ways and may have multiple distinct answers. In this paper, we address multi-answer retrieval which entails retrieving passages that can capture majority of the diverse answers to the question. We propose a re-ranking based approach using Determinantal point processes utilizing BERT as kernels. Our method jointly considers query-passage relevance and passage-passage correlation to retrieve passages that are both query-relevant and diverse. Results demonstrate that our re-ranking technique outperforms state-of-the-art method on the AmbigQA dataset.

Breaking down a document or a conversation into multiple contiguous segments based on its semantic structure is an important and challenging problem in NLP, which can assist many downstream tasks. However, current works on topic segmentation often focus on segmentation of structured texts. In this paper, we comprehensively analyze the generalization capabilities of state-of-the-art topic segmentation models on unstructured texts. We find that: (a) Current strategies of pre-training on a large corpus of structured text such as Wiki-727K do not help in transferability to unstructured texts. (b) Training from scratch with only a relatively small-sized dataset of the target unstructured domain improves the segmentation results by a significant margin.