Related papers: A Sub-Character Architecture for Korean Language P…
The flourishing blossom of deep learning has witnessed the rapid development of Chinese character recognition. However, it remains a great challenge that the characters for testing may have different distributions from those of the training…
Hierarchical Multiscale LSTM (Chung et al., 2016a) is a state-of-the-art language model that learns interpretable structure from character-level input. Such models can provide fertile ground for (cognitive) computational linguistics…
Most existing Neural Machine Translation models use groups of characters or whole words as their unit of input and output. We propose a model with a hierarchical char2word encoder, that takes individual characters both as input and output.…
Segmentation of highly slanted and horizontally overlapped characters is a challenging research area that is still fresh. Several techniques are reported in the state of art, but produce low accuracy for the highly slanted characters…
In this paper, we propose an end-to-end Korean singing voice synthesis system from lyrics and a symbolic melody using the following three novel approaches: 1) phonetic enhancement masking, 2) local conditioning of text and pitch to the…
The limited availability of non-native speech datasets presents a major challenge in automatic speech recognition (ASR) to narrow the performance gap between native and non-native speakers. To address this, the focus of this study is on the…
The performance of automatic speech recognition (ASR) models can be greatly improved by proper beam-search decoding with external language model (LM). There has been an increasing interest in Korean speech recognition, but not many studies…
We present a Character-Word Long Short-Term Memory Language Model which both reduces the perplexity with respect to a baseline word-level language model and reduces the number of parameters of the model. Character information can reveal…
With the advent of Transformer, which was used in translation models in 2017, attention-based architectures began to attract attention. Furthermore, after the emergence of BERT, which strengthened the NLU-specific encoder part, which is a…
A new scheme to represent phonological changes during continuous speech recognition is suggested. A phonological tag coupled with its morphological tag is designed to represent the conditions of Korean phonological changes. A pairwise…
A Lite BERT (ALBERT) has been introduced to scale up deep bidirectional representation learning for natural languages. Due to the lack of pretrained ALBERT models for Korean language, the best available practice is the multilingual model or…
Handwritten character recognition (HCR) is a challenging problem for machine learning researchers. Unlike printed text data, handwritten character datasets have more variation due to human-introduced bias. With numerous unique character…
The Backpack is a Transformer alternative shown to improve interpretability in English language modeling by decomposing predictions into a weighted sum of token sense components. However, Backpacks' reliance on token-defined meaning raises…
Black-box probing models can reliably extract linguistic features like tense, number, and syntactic role from pretrained word representations. However, the manner in which these features are encoded in representations remains poorly…
In some contexts, well-formed natural language cannot be expected as input to information or communication systems. In these contexts, the use of grammar-independent input (sequences of uninflected semantic units like e.g.…
For readability and disambiguation of the written text, appropriate word segmentation is recommended for documentation, and it also holds for the digitized texts. If the language is agglutinative while far from scriptio continua, for…
Representation learning is the foundation of machine reading comprehension. In state-of-the-art models, deep learning methods broadly use word and character level representations. However, character is not naturally the minimal linguistic…
Korean is often referred to as a low-resource language in the research community. While this claim is partially true, it is also because the availability of resources is inadequately advertised and curated. This work curates and reviews a…
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…
Although LLMs have made significant progress in various languages, there are still concerns about their effectiveness with low-resource agglutinative languages compared to languages such as English. In this study, we focused on Korean, a…