Related papers: Encoding Syntactic Knowledge in Transformer Encode…

Transformers are increasingly dominating multi-modal reasoning tasks, such as visual question answering, achieving state-of-the-art results thanks to their ability to contextualize information using the self-attention and co-attention…

The goal of spoken language understanding (SLU) systems is to determine the meaning of the input speech signal, unlike speech recognition which aims to produce verbatim transcripts. Advances in end-to-end (E2E) speech modeling have made it…

In recent years, pre-trained Transformers have dominated the majority of NLP benchmark tasks. Many variants of pre-trained Transformers have kept breaking out, and most focus on designing different pre-training objectives or variants of…

We present models for encoding sentences into embedding vectors that specifically target transfer learning to other NLP tasks. The models are efficient and result in accurate performance on diverse transfer tasks. Two variants of the…

Image inpainting has made significant advances in recent years. However, it is still challenging to recover corrupted images with both vivid textures and reasonable structures. Some specific methods only tackle regular textures while losing…

Intent classification is crucial for conversational agents (chatbots), and deep learning models perform well in this area. However, little research has been done on the explainability of intent classification due to the absence of suitable…

Driver intention prediction seeks to anticipate drivers' actions by analyzing their behaviors with respect to surrounding traffic environments. Existing approaches primarily focus on late-fusion techniques, and neglect the importance of…

There has been a recent surge of interest in automating software engineering tasks using deep learning. This paper addresses the problem of code generation, where the goal is to generate target code given source code in a different language…

While existing text-to-speech (TTS) models exhibit high expressiveness, fine-grained control over composite instructions remains challenging due to the structural mismatch between discrete textual intents and continuous acoustic…

This work proposes an attention-based sequence-to-sequence model for handwritten word recognition and explores transfer learning for data-efficient training of HTR systems. To overcome training data scarcity, this work leverages models…

We present Token-UNet, adopting the TokenLearner and TokenFuser modules to encase Transformers into UNets. While Transformers have enabled global interactions among input elements in medical imaging, current computational challenges hinder…

In this paper, we proposed a sentence encoding-based model for recognizing text entailment. In our approach, the encoding of sentence is a two-stage process. Firstly, average pooling was used over word-level bidirectional LSTM (biLSTM) to…

The Transformer architecture has gained growing attention in graph representation learning recently, as it naturally overcomes several limitations of graph neural networks (GNNs) by avoiding their strict structural inductive biases and…

To achieve deep natural language understanding, syntactic constituent parsing plays a crucial role and is widely required by many artificial intelligence systems for processing both text and speech. A recent approach involves using standard…

Recently, the Transformer model that is based solely on attention mechanisms, has advanced the state-of-the-art on various machine translation tasks. However, recent studies reveal that the lack of recurrence hinders its further improvement…

Effective license plate recognition systems are required to be resilient to constant change, as new license plates are released into traffic daily. While Transformer-based networks excel in their recognition at first sight, we observe…

In this paper, we propose an encoder-decoder neural architecture (called Channelformer) to achieve improved channel estimation for orthogonal frequency-division multiplexing (OFDM) waveforms in downlink scenarios. The self-attention…

Autoregressive decoder-only transformers have become key components for scalable sequence processing and generation models. However, the transformer's self-attention mechanism requires transferring prior token projections from the main…

A key challenge of dialog systems research is to effectively and efficiently adapt to new domains. A scalable paradigm for adaptation necessitates the development of generalizable models that perform well in few-shot settings. In this…

Recently, self-attention models such as Transformers have given competitive results compared to recurrent neural network systems in speech recognition. The key factor for the outstanding performance of self-attention models is their ability…