Related papers: Investigating an Effective Character-level Embeddi…
Large language models (LLMs) have shown remarkable potential for problem solving, with open source models achieving increasingly impressive performance on benchmarks measuring areas from logical reasoning to mathematical ability. Ensembling…
Previous work combines word-level and character-level representations using concatenation or scalar weighting, which is suboptimal for high-level tasks like reading comprehension. We present a fine-grained gating mechanism to dynamically…
The CUTE benchmark showed that LLMs struggle with character understanding in English. We extend it to more languages with diverse scripts and writing systems, introducing EXECUTE. Our simplified framework allows easy expansion to any…
Korean-Chinese is a low resource language pair, but Korean and Chinese have a lot in common in terms of vocabulary. Sino-Korean words, which can be converted into corresponding Chinese characters, account for more than fifty of the entire…
Incorporating linguistic knowledge can improve scene text recognition, but it is questionable whether the same holds for scene text spotting, which typically involves text detection and recognition. This paper proposes a method that…
Sequence labeling architectures use word embeddings for capturing similarity, but suffer when handling previously unseen or rare words. We investigate character-level extensions to such models and propose a novel architecture for combining…
Learning to construct text representations in end-to-end systems can be difficult, as natural languages are highly compositional and task-specific annotated datasets are often limited in size. Methods for directly supervising language…
Many efforts have been devoted to develop alternative methods to traditional vector quantization in image domain such as sparse coding and soft-assignment. These approaches can be split into a dictionary learning phase and a feature…
Document classification tasks were primarily tackled at word level. Recent research that works with character-level inputs shows several benefits over word-level approaches such as natural incorporation of morphemes and better handling of…
Words can be represented by composing the representations of subword units such as word segments, characters, and/or character n-grams. While such representations are effective and may capture the morphological regularities of words, they…
We combine character-level and contextual language model representations to improve performance on Discourse Representation Structure parsing. Character representations can easily be added in a sequence-to-sequence model in either one…
Short text classification (STC) remains a challenging task due to the scarcity of contextual information and labeled data. However, existing approaches have pre-dominantly focused on English because most benchmark datasets for the STC are…
Common Large Language model (LLM) evaluations rely on demonstration examples to steer models' responses to the desired style. While the number of examples used has been studied and standardized, the choice of how to format examples is less…
The choice of modeling units is crucial for automatic speech recognition (ASR) tasks. In mandarin scenarios, the Chinese characters represent meaning but are not directly related to the pronunciation. Thus only considering the writing of…
Character-based neural models have recently proven very useful for many NLP tasks. However, there is a gap of sophistication between methods for learning representations of sentences and words. While most character models for learning…
Wav2vec 2.0 is an end-to-end framework of self-supervised learning for speech representation that is successful in automatic speech recognition (ASR), but most of the work on the topic has been developed with a single language: English.…
We propose spoken sentence embeddings which capture both acoustic and linguistic content. While existing works operate at the character, phoneme, or word level, our method learns long-term dependencies by modeling speech at the sentence…
In this article, how word embeddings can be used as features in Chinese sentiment classification is presented. Firstly, a Chinese opinion corpus is built with a million comments from hotel review websites. Then the word embeddings which…
Despite the rapid development of large language models (LLMs) for the Korean language, there remains an obvious lack of benchmark datasets that test the requisite Korean cultural and linguistic knowledge. Because many existing Korean…
This paper examines the Code-Switching (CS) phenomenon where two languages intertwine within a single utterance. There exists a noticeable need for research on the CS between English and Korean. We highlight that the current Equivalence…