English
Related papers

Related papers: ZEN: Pre-training Chinese Text Encoder Enhanced by…

200 papers

Grapheme-to-phoneme (G2P) conversion serves as an essential component in Chinese Mandarin text-to-speech (TTS) system, where polyphone disambiguation is the core issue. In this paper, we propose an end-to-end framework to predict the…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-03 Dongyang Dai , Zhiyong Wu , Shiyin Kang , Xixin Wu , Jia Jia , Dan Su , Dong Yu , Helen Meng

Encoder-only Transformers have advanced along three axes -- architecture, data, and systems -- yielding Pareto gains in accuracy, speed, and memory efficiency. Yet these improvements have not fully transferred to Chinese, where tokenization…

Computation and Language · Computer Science 2025-10-15 Zeyu Zhao , Ningtao Wang , Xing Fu , Yu Cheng

Although existing neural network approaches have achieved great success on Chinese spelling correction, there is still room to improve. The model is required to avoid over-correction and to distinguish a correct token from its phonological…

Computation and Language · Computer Science 2023-03-21 Rui Sun , Xiuyu Wu , Yunfang Wu

Chinese short text matching is a fundamental task in natural language processing. Existing approaches usually take Chinese characters or words as input tokens. They have two limitations: 1) Some Chinese words are polysemous, and semantic…

Computation and Language · Computer Science 2021-02-26 Boer Lyu , Lu Chen , Su Zhu , Kai Yu

Most Chinese pre-trained models take character as the basic unit and learn representation according to character's external contexts, ignoring the semantics expressed in the word, which is the smallest meaningful utterance in Chinese.…

Computation and Language · Computer Science 2020-04-30 Yanzeng Li , Bowen Yu , Mengge Xue , Tingwen Liu

Recently, knowledge-enhanced pre-trained language models (KEPLMs) improve context-aware representations via learning from structured relations in knowledge graphs, and/or linguistic knowledge from syntactic or dependency analysis. Unlike…

Computation and Language · Computer Science 2022-10-13 Taolin Zhang , Junwei Dong , Jianing Wang , Chengyu Wang , Ang Wang , Yinghui Liu , Jun Huang , Yong Li , Xiaofeng He

The front-end module in a typical Mandarin text-to-speech system (TTS) is composed of a long pipeline of text processing components, which requires extensive efforts to build and is prone to large accumulative model size and cascade errors.…

Sound · Computer Science 2021-01-01 Yang Zhang , Liqun Deng , Yasheng Wang

Pre-trained Transformer language models (LM) have become go-to text representation encoders. Prior research fine-tunes deep LMs to encode text sequences such as sentences and passages into single dense vector representations for efficient…

Computation and Language · Computer Science 2021-09-22 Luyu Gao , Jamie Callan

Given the advantage and recent success of English character-level and subword-unit models in several NLP tasks, we consider the equivalent modeling problem for Chinese. Chinese script is logographic and many Chinese logograms are composed…

Computation and Language · Computer Science 2018-09-11 Falcon Z. Dai , Zheng Cai

Commonly-used transformer language models depend on a tokenization schema which sets an unchangeable subword vocabulary prior to pre-training, destined to be applied to all downstream tasks regardless of domain shift, novel word formations,…

Computation and Language · Computer Science 2021-08-03 Yuval Pinter , Amanda Stent , Mark Dredze , Jacob Eisenstein

This paper introduces PnG BERT, a new encoder model for neural TTS. This model is augmented from the original BERT model, by taking both phoneme and grapheme representations of text as input, as well as the word-level alignment between…

Computation and Language · Computer Science 2021-06-08 Ye Jia , Heiga Zen , Jonathan Shen , Yu Zhang , Yonghui Wu

Bidirectional Encoder Representations from Transformers (BERT) represents the latest incarnation of pretrained language models which have recently advanced a wide range of natural language processing tasks. In this paper, we showcase how…

Computation and Language · Computer Science 2019-09-06 Yang Liu , Mirella Lapata

Chinese text recognition is more challenging than Latin text due to the large amount of fine-grained Chinese characters and the great imbalance over classes, which causes a serious overfitting problem. We propose to apply Maximum Entropy…

Computer Vision and Pattern Recognition · Computer Science 2020-07-10 Changxu Cheng , Wuheng Xu , Xiang Bai , Bin Feng , Wenyu Liu

Unlike alphabetic languages, Chinese spelling and pronunciation are different. Both characters and pinyin take an important role in Chinese language understanding. In Chinese NLP tasks, we almost adopt characters or words as model input,…

Computation and Language · Computer Science 2023-10-10 Baojun Wang , Kun Xu , Lifeng Shang

Chinese word segmentation and dependency parsing are two fundamental tasks for Chinese natural language processing. The dependency parsing is defined on word-level. Therefore word segmentation is the precondition of dependency parsing,…

Computation and Language · Computer Science 2019-12-19 Hang Yan , Xipeng Qiu , Xuanjing Huang

To understand the algorithm that supports the human brain's language representation, previous research has attempted to predict neural responses to linguistic stimuli using embeddings generated by artificial neural networks (ANNs), a…

Computation and Language · Computer Science 2023-10-10 Jingyuan Sun , Xiaohan Zhang , Marie-Francine Moens

The pre-trained language model is trained on large-scale unlabeled text and can achieve state-of-the-art results in many different downstream tasks. However, the current pre-trained language model is mainly concentrated in the Chinese and…

Computation and Language · Computer Science 2022-05-17 Yuan Sun , Sisi Liu , Junjie Deng , Xiaobing Zhao

Sentence embeddings are commonly used in text clustering and semantic retrieval tasks. State-of-the-art sentence representation methods are based on artificial neural networks fine-tuned on large collections of manually labeled sentence…

Computation and Language · Computer Science 2022-07-27 Sławomir Dadas

Chinese named entity recognition (CNER) is an important task in Chinese natural language processing field. However, CNER is very challenging since Chinese entity names are highly context-dependent. In addition, Chinese texts lack delimiters…

Computation and Language · Computer Science 2019-05-07 Fangzhao Wu , Junxin Liu , Chuhan Wu , Yongfeng Huang , Xing Xie

Neural machine translation (NMT) heavily relies on word-level modelling to learn semantic representations of input sentences. However, for languages without natural word delimiters (e.g., Chinese) where input sentences have to be tokenized…

Computation and Language · Computer Science 2016-12-12 Jinsong Su , Zhixing Tan , Deyi Xiong , Rongrong Ji , Xiaodong Shi , Yang Liu