Related papers: Character Feature Engineering for Japanese Word Se…

Discriminative segmental models offer a way to incorporate flexible feature functions into speech recognition. However, their appeal has been limited by their computational requirements, due to the large number of possible segments to…

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…

Motivated by the increasing popularity of transformers in computer vision, in recent times there has been a rapid development of novel architectures. While in-domain performance follows a constant, upward trend, properties like robustness…

Current language models (LMs) use a fixed, static subword tokenizer. This default choice typically results in degraded efficiency and language capabilities, especially in languages other than English. To address this issue, we challenge the…

Data representation is a fundamental task in machine learning. The representation of data affects the performance of the whole machine learning system. In a long history, the representation of data is done by feature engineering, and…

Language models typically tokenize raw text into sequences of subword identifiers from a predefined vocabulary, a process inherently sensitive to typographical errors, length variations, and largely oblivious to the internal structure of…

This paper presents a joint model for performing unsupervised morphological analysis on words, and learning a character-level composition function from morphemes to word embeddings. Our model splits individual words into segments, and…

Semantic segmentation is a vital problem in computer vision. Recently, a common solution to semantic segmentation is the end-to-end convolution neural network, which is much more accurate than traditional methods.Recently, the decoders…

In domain classification for spoken dialog systems, correct detection of out-of-domain (OOD) utterances is crucial because it reduces confusion and unnecessary interaction costs between users and the systems. Previous work usually utilizes…

Why do some languages like Czech permit free word order, while others like English do not? We address this question by pretraining transformer language models on a spectrum of synthetic word-order variants of natural languages. We observe…

In real-time speech recognition applications, the latency is an important issue. We have developed a character-level incremental speech recognition (ISR) system that responds quickly even during the speech, where the hypotheses are…

Acoustics-to-word models are end-to-end speech recognizers that use words as targets without relying on pronunciation dictionaries or graphemes. These models are notoriously difficult to train due to the lack of linguistic knowledge. It is…

The problem of identifying voice commands has always been a challenge due to the presence of noise and variability in speed, pitch, etc. We will compare the efficacies of several neural network architectures for the speech recognition…

When translating Japanese nouns into English, we face the problem of articles and numbers which the Japanese language does not have, but which are necessary for the English composition. To solve this difficult problem we classified the…

While pretrained language models have exhibited impressive generalization capabilities, they still behave unpredictably under certain domain shifts. In particular, a model may learn a reasoning process on in-domain training data that does…

We tackle the problem of multi-class relational sequence learning using relevant patterns discovered from a set of labelled sequences. To deal with this problem, firstly each relational sequence is mapped into a feature vector using the…

Recent advancements in large language models (LLMs) have shown promise in feature engineering for tabular data, but concerns about their reliability persist, especially due to variability in generated outputs. We introduce a multi-level…

Image-based sequence recognition has been a long-standing research topic in computer vision. In this paper, we investigate the problem of scene text recognition, which is among the most important and challenging tasks in image-based…

This paper presents methods for building speech recognizers tailored for Japanese speaking assessment tasks. Specifically, we build a speech recognizer that outputs phonemic labels with accent markers. Although Japanese is resource-rich,…

Ranking functions in information retrieval are often used in search engines to recommend the relevant answers to the query. This paper makes use of this notion of information retrieval and applies onto the problem domain of cognate…