Related papers: Adversarial Multi-Criteria Learning for Chinese Wo…
As machine learning systems become more widely used, especially for safety critical applications, there is a growing need to ensure that these systems behave as intended, even in the face of adversarial examples. Adversarial examples are…
Benefiting from the strong ability of the pre-trained model, the research on Chinese Word Segmentation (CWS) has made great progress in recent years. However, due to massive computation, large and complex models are incapable of empowering…
Until recently, Chinese texts could not be studied using co-word analysis because the words are not separated by spaces in Chinese (and Japanese). A word can be composed of one or more characters. The online availability of programs that…
Generative adversarial networks (GANs) have succeeded in inducing cross-lingual word embeddings -- maps of matching words across languages -- without supervision. Despite these successes, GANs' performance for the difficult case of distant…
While significant progress has been made in the image captioning task, video description is still in its infancy due to the complex nature of video data. Generating multi-sentence descriptions for long videos is even more challenging. Among…
Cross-lingual Summarization (CLS) aims at producing a summary in the target language for an article in the source language. Traditional solutions employ a two-step approach, i.e. translate then summarize or summarize then translate.…
Based on network analysis of hierarchical structural relations among Chinese characters, we develop an efficient learning strategy of Chinese characters. We regard a more efficient learning method if one learns the same number of useful…
As natural language processing (NLP) for gender bias becomes a significant interdisciplinary topic, the prevalent data-driven techniques such as large-scale language models suffer from data inadequacy and biased corpus, especially for…
In recent years, a great many methods of learning from multi-view data by considering the diversity of different views have been proposed. These views may be obtained from multiple sources or different feature subsets. In trying to organize…
We investigate the performance on phoneme categorization and phoneme and word segmentation of several self-supervised learning (SSL) methods based on Contrastive Predictive Coding (CPC). Our experiments show that with the existing…
Most of the Chinese pre-trained models adopt characters as basic units for downstream tasks. However, these models ignore the information carried by words and thus lead to the loss of some important semantics. In this paper, we propose a…
This paper presents a novel method that allows a machine learning algorithm following the transformation-based learning paradigm \cite{brill95:tagging} to be applied to multiple classification tasks by training jointly and simultaneously on…
The evolution of language follows the rule of gradual change. Grammar, vocabulary, and lexical semantic shifts take place over time, resulting in a diachronic linguistic gap. As such, a considerable amount of texts are written in languages…
Automated medical image analysis has a significant value in diagnosis and treatment of lesions. Brain tumors segmentation has a special importance and difficulty due to the difference in appearances and shapes of the different tumor regions…
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…
This study presents a Long Short-Term Memory (LSTM) neural network approach to Japanese word segmentation (JWS). Previous studies on Chinese word segmentation (CWS) succeeded in using recurrent neural networks such as LSTM and gated…
Text classification is a very classic NLP task, but it has two prominent shortcomings: On the one hand, text classification is deeply domain-dependent. That is, a classifier trained on the corpus of one domain may not perform so well in…
Acoustic Word Embeddings (AWEs) improve the efficiency of speech retrieval tasks such as Spoken Term Detection (STD) and Keyword Spotting (KWS). However, existing approaches suffer from limitations, including unimodal supervision, disjoint…
The goal of this paper is to learn cross-domain representations for slot filling task in spoken language understanding (SLU). Most of the recently published SLU models are domain-specific ones that work on individual task domains.…
Lexical analysis is believed to be a crucial step towards natural language understanding and has been widely studied. Recent years, end-to-end lexical analysis models with recurrent neural networks have gained increasing attention. In this…