相关论文: Semantic Compression for Word and Sentence Embeddi…

In deep time series forecasting, the Fourier Transform (FT) is extensively employed for frequency representation learning. However, it often struggles in capturing multi-scale, time-sensitive patterns. Although the Wavelet Transform (WT)…

Transformer-based approaches have been successfully used to obtain state-of-the-art accuracy on natural language processing (NLP) tasks with semi-structured tables. These model architectures are typically deep, resulting in slow training…

Contextualized word representations are able to give different representations for the same word in different contexts, and they have been shown to be effective in downstream natural language processing tasks, such as question answering,…

WaveNet is a state-of-the-art text-to-speech vocoder that remains challenging to deploy due to its autoregressive loop. In this work we focus on ways to accelerate the original WaveNet architecture directly, as opposed to modifying the…

This paper reformulates Transformer/Attention mechanisms in Large Language Models (LLMs) through measure theory and frequency analysis, theoretically demonstrating that hallucination is an inevitable structural limitation. The embedding…

Word representations are created using analogy context-based statistics and lexical relations on words. Word representations are inputs for the learning models in Natural Language Understanding (NLU) tasks. However, to understand language,…

For most of the state-of-the-art speech enhancement techniques, a spectrogram is usually preferred than the respective time-domain raw data since it reveals more compact presentation together with conspicuous temporal information over a…

Vector representations of sentences, trained on massive text corpora, are widely used as generic sentence embeddings across a variety of NLP problems. The learned representations are generally assumed to be continuous and real-valued,…

Manually labelling large collections of text data is a time-consuming, expensive, and laborious task, but one that is necessary to support machine learning based on text datasets. Active learning has been shown to be an effective way to…

We first present our work in machine translation, during which we used aligned sentences to train a neural network to embed n-grams of different languages into an $d$-dimensional space, such that n-grams that are the translation of each…

End-to-end neural machine translation has overtaken statistical machine translation in terms of translation quality for some language pairs, specially those with large amounts of parallel data. Besides this palpable improvement, neural…

With the growth of digital networks such as the Internet, digital media have been explosively developed in e-commerce and online services. This causes problems such as illegal copy and fake ownership. Watermarking is proposed as one of the…

The Internet has turned the entire world into a small village;this is because it has made it possible to share millions of images and videos. However, sending and receiving a huge amount of data is considered to be a main challenge. To…

Efficient representation of text documents is an important building block in many NLP tasks. Research on long text categorization has shown that simple weighted averaging of word vectors for sentence representation often outperforms more…

In this paper, we propose a novel speech enhancement (SE) method by exploiting the discrete wavelet transform (DWT). This new method reduces the amount of fast time-varying portion, viz. the DWT-wise detail component, in the spectrogram of…

Dialogue act recognition is an important component of a large number of natural language processing pipelines. Many research works have been carried out in this area, but relatively few investigate deep neural networks and word embeddings.…

Despite the well-developed cut-edge representation learning for language, most language representation models usually focus on specific level of linguistic unit, which cause great inconvenience when being confronted with handling multiple…

In recent years BERT shows apparent advantages and great potential in natural language processing tasks. However, both training and applying BERT requires intensive time and resources for computing contextual language representations, which…

Sentence embeddings can be decoded to give approximations of the original texts used to create them. We explore this effect in the context of text simplification, demonstrating that reconstructed text embeddings preserve complexity levels.…

Sentence embeddings are central to modern NLP and AI systems, yet little is known about their internal structure. While we can compare these embeddings using measures such as cosine similarity, the contributing features are not…