Related papers: Incorporating Sememes into Chinese Definition Mode…

In recent years, several influential computational models and metrics have been proposed to predict how humans comprehend and process sentence. One particularly promising approach is contextual semantic similarity. Inspired by the attention…

Measuring sentence similarity is a key research area nowadays as it allows machines to better understand human languages. In this paper, we proposed a Cross-Attention Siamese Network (CATsNet) to carry out the task of learning the semantic…

The choice of modeling units is critical to automatic speech recognition (ASR) tasks. Conventional ASR systems typically choose context-dependent states (CD-states) or context-dependent phonemes (CD-phonemes) as their modeling units.…

Sememes are minimum semantic units of concepts in human languages, such that each word sense is composed of one or multiple sememes. Words are usually manually annotated with their sememes by linguists, and form linguistic common-sense…

Neural network has become the dominant method for Chinese word segmentation. Most existing models cast the task as sequence labeling, using BiLSTM-CRF for representing the input and making output predictions. Recently, attention-based…

Learning and generating Chinese poems is a charming yet challenging task. Traditional approaches involve various language modeling and machine translation techniques, however, they perform not as well when generating poems with complex…

Chinese word segmentation (CWS) is the basic of Chinese natural language processing (NLP). The quality of word segmentation will directly affect the rest of NLP tasks. Recently, with the artificial intelligence tide rising again, Long…

We introduce an attention-based Bi-LSTM for Chinese implicit discourse relations and demonstrate that modeling argument pairs as a joint sequence can outperform word order-agnostic approaches. Our model benefits from a partial sampling…

Sequence-to-sequence attention-based models have recently shown very promising results on automatic speech recognition (ASR) tasks, which integrate an acoustic, pronunciation and language model into a single neural network. In these models,…

Interpretability and explainability of neural networks is continuously increasing in importance, especially within safety-critical domains and to provide the social right to explanation. Concept based explanations align well with how humans…

Recently, Chinese word segmentation (CWS) methods using neural networks have made impressive progress. Most of them regard the CWS as a sequence labeling problem which construct models based on local features rather than considering global…

Intent classification has been widely researched on English data with deep learning approaches that are based on neural networks and word embeddings. The challenge for Chinese intent classification stems from the fact that, unlike English…

Recently, much Chinese text error correction work has focused on Chinese Spelling Check (CSC) and Chinese Grammatical Error Diagnosis (CGED). In contrast, little attention has been paid to the complicated problem of Chinese Semantic Error…

In this paper, we present Chinese lexical fusion recognition, a new task which could be regarded as one kind of coreference recognition. First, we introduce the task in detail, showing the relationship with coreference recognition and…

Recently, textual information has been proved to play a positive role in recommendation systems. However, most of the existing methods only focus on representation learning of textual information in ratings, while potential selection bias…

This paper introduces the Contextual Evaluation Model (CEM), a novel method for knowledge representation and manipulation. The CEM differs from existing models in that it integrates facts, patterns and sequences into a single contextual…

This paper studies Chinese Spelling Correction (CSC), which aims to detect and correct the potential spelling errors in a given sentence. Current state-of-the-art methods regard CSC as a sequence tagging task and fine-tune BERT-based models…

Attention mechanism has gained great success in vision recognition. Many works are devoted to improving the effectiveness of attention mechanism, which finely design the structure of the attention operator. These works need lots of…

Whole word masking (WWM), which masks all subwords corresponding to a word at once, makes a better English BERT model. For the Chinese language, however, there is no subword because each token is an atomic character. The meaning of a word…

To automatically correct handwritten assignments, the traditional approach is to use an OCR model to recognize characters and compare them to answers. The OCR model easily gets confused on recognizing handwritten Chinese characters, and the…