Related papers: SG-Net: Syntax Guided Transformer for Language Rep…

Networks have become considerably large, complex and dynamic. The configuration, operation, monitoring, and troubleshooting of networks is a cumbersome and time-consuming task for the network administrators as they must deal with the…

Attention-based sequence-to-sequence modeling provides a powerful and elegant solution for applications that need to map one sequence to a different sequence. Its success heavily relies on the availability of large amounts of training data.…

The Transformer model is widely used in natural language processing for sentence representation. However, the previous Transformer-based models focus on function words that have limited meaning in most cases and could merely extract…

Spoken Language Understanding (SLU), including intent detection and slot filling, is a core component in human-computer interaction. The natural attributes of the relationship among the two subtasks make higher requirements on fine-grained…

We introduce a dialogue policy based on a transformer architecture, where the self-attention mechanism operates over the sequence of dialogue turns. Recent work has used hierarchical recurrent neural networks to encode multiple utterances…

We propose a novel Transformer encoder-based architecture with syntactical knowledge encoded for intent detection and slot filling. Specifically, we encode syntactic knowledge into the Transformer encoder by jointly training it to predict…

We study the problem of using (partial) constituency parse trees as syntactic guidance for controlled text generation. Existing approaches to this problem use recurrent structures, which not only suffer from the long-term dependency problem…

Exploiting rich linguistic information in raw text is crucial for expressive text-to-speech (TTS). As large scale pre-trained text representation develops, bidirectional encoder representations from Transformers (BERT) has been proven to…

Thanks to the latest deep learning algorithms, silent speech interfaces (SSI) are now able to synthesize intelligible speech from articulatory movement data under certain conditions. However, the resulting models are rather…

Self-attention, an architectural motif designed to model long-range interactions in sequential data, has driven numerous recent breakthroughs in natural language processing and beyond. This work provides a theoretical analysis of the…

In this paper we present an end-to-end speech recognition model with Transformer encoders that can be used in a streaming speech recognition system. Transformer computation blocks based on self-attention are used to encode both audio and…

Recently, non-recurrent architectures (convolutional, self-attentional) have outperformed RNNs in neural machine translation. CNNs and self-attentional networks can connect distant words via shorter network paths than RNNs, and it has been…

Agents that can follow language instructions are expected to be useful in a variety of situations such as navigation. However, training neural network-based agents requires numerous paired trajectories and languages. This paper proposes…

Syntactic information contains structures and rules about how text sentences are arranged. Incorporating syntax into text modeling methods can potentially benefit both representation learning and generation. Variational autoencoders (VAEs)…

Self-attention is a method of encoding sequences of vectors by relating these vectors to each-other based on pairwise similarities. These models have recently shown promising results for modeling discrete sequences, but they are non-trivial…

Modern speech enhancement (SE) networks typically implement noise suppression through time-frequency masking, latent representation masking, or discriminative signal prediction. In contrast, some recent works explore SE via generative…

As modern networks grow in scale and complexity, manual configuration becomes increasingly inefficient and prone to human error. While intent-driven self-configuration using large language models has shown significant promise, such models…

While the general idea of self-supervised learning is identical across modalities, the actual algorithms and objectives differ widely because they were developed with a single modality in mind. To get us closer to general self-supervised…

Although end-to-end neural text-to-speech (TTS) methods (such as Tacotron2) are proposed and achieve state-of-the-art performance, they still suffer from two problems: 1) low efficiency during training and inference; 2) hard to model long…

The study of the attention mechanism has sparked interest in many fields, such as language modeling and machine translation. Although its patterns have been exploited to perform different tasks, from neural network understanding to textual…