no code implementations • LREC 2022 • Fumikazu Sato, Naoki Yoshinaga, Masaru Kitsuregawa
In this study, to improve the accuracy of pronunciation prediction, we construct two large-scale Japanese corpora that annotate kanji characters with their pronunciations.
no code implementations • EMNLP (BlackboxNLP) 2021 • Daisuke Oba, Naoki Yoshinaga, Masashi Toyoda
Probing classifiers have been extensively used to inspect whether a model component captures specific linguistic phenomena.
1 code implementation • Findings (EMNLP) 2021 • Shoetsu Sato, Naoki Yoshinaga, Masashi Toyoda, Masaru Kitsuregawa
Our method chooses the most probable one from redundantly sampled latent variables for tying up the variable with a given response.
no code implementations • Findings (EMNLP) 2021 • Satoshi Akasaki, Naoki Yoshinaga, Masashi Toyoda
Experiments on the Twitter datasets confirm the effectiveness of our typing model and the context selector.
1 code implementation • 8 Mar 2024 • Xin Zhao, Naoki Yoshinaga, Daisuke Oba
Acquiring factual knowledge for language models (LMs) in low-resource languages poses a serious challenge, thus resorting to cross-lingual transfer in multilingual LMs (ML-LMs).
no code implementations • 4 Jan 2024 • Yuma Tsuta, Naoki Yoshinaga, Shoetsu Sato, Masashi Toyoda
Open-domain dialogue systems have started to engage in continuous conversations with humans.
1 code implementation • 1 Dec 2023 • Yueguan Wang, Naoki Yoshinaga
Despite the prevalence of pretrained language models in natural language understanding tasks, understanding lengthy text such as document is still challenging due to the data sparseness problem.
no code implementations • 14 Sep 2023 • Daisuke Oba, Naoki Yoshinaga, Masashi Toyoda
The meanings of words and phrases depend not only on where they are used (contexts) but also on who use them (writers).
no code implementations • 9 Jun 2023 • Keiji Shinzato, Naoki Yoshinaga, Yandi Xia, Wei-Te Chen
We finetune a pre-trained generative model, T5, to decode a set of attribute-value pairs as a target sequence from the given product text.
no code implementations • 30 May 2023 • Naoki Yoshinaga
Accurate neural models are much less efficient than non-neural models and are useless for processing billions of social media posts or handling user queries in real time with a limited budget.
no code implementations • 21 Dec 2022 • Zihan Wang, Naoki Yoshinaga
In this study, we therefore introduce the task of generating game commentaries from esports' data records.
no code implementations • 14 Oct 2022 • Kosuke Nishida, Naoki Yoshinaga, Kyosuke Nishida
Although named entity recognition (NER) helps us to extract domain-specific entities from text (e. g., artists in the music domain), it is costly to create a large amount of training data or a structured knowledge base to perform accurate NER in the target domain.
no code implementations • 13 Oct 2022 • Satoshi Akasaki, Naoki Yoshinaga, Masashi Toyoda
The major challenge is detecting uncertain contexts of disappearing entities from noisy microblog posts.
no code implementations • ACL 2022 • Keiji Shinzato, Naoki Yoshinaga, Yandi Xia, Wei-Te Chen
A key challenge in attribute value extraction (AVE) from e-commerce sites is how to handle a large number of attributes for diverse products.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Shoetsu Sato, Jin Sakuma, Naoki Yoshinaga, Masashi Toyoda, Masaru Kitsuregawa
Prior to fine-tuning, our method replaces the embedding layers of the NMT model by projecting general word embeddings induced from monolingual data in a target domain onto a source-domain embedding space.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Nobukazu Fukuda, Naoki Yoshinaga, Masaru Kitsuregawa
In this study, inspired by the processes for creating words from known words, we propose a robust method of estimating oov word embeddings by referring to pre-trained word embeddings for known words with similar surfaces to target oov words.
no code implementations • NAACL 2021 • Amane Sugiyama, Naoki Yoshinaga
Although many context-aware neural machine translation models have been proposed to incorporate contexts in translation, most of those models are trained end-to-end on parallel documents aligned in sentence-level.
no code implementations • ACL 2020 • Tsuta Yuma, Naoki Yoshinaga, Masashi Toyoda
Experimental results on massive Twitter data confirmed that υBLEU is comparable to ΔBLEU in terms of its correlation with human judgment and that the state of the art automatic evaluation method, RUBER, is improved by integrating υBLEU.
no code implementations • 30 Apr 2020 • Shoetsu Sato, Jin Sakuma, Naoki Yoshinaga, Masashi Toyoda, Masaru Kitsuregawa
Prior to fine-tuning, our method replaces the embedding layers of the NMT model by projecting general word embeddings induced from monolingual data in a target domain onto a source-domain embedding space.
no code implementations • WS 2019 • Amane Sugiyama, Naoki Yoshinaga
A single sentence does not always convey information that is enough to translate it into other languages.
no code implementations • CONLL 2019 • Masato Neishi, Naoki Yoshinaga
Although some approaches such as the attention mechanism have partially remedied the problem, we found that the current standard NMT model, Transformer, has difficulty in translating long sentences compared to the former standard, Recurrent Neural Network (RNN)-based model.
no code implementations • CONLL 2019 • Jin Sakuma, Naoki Yoshinaga
We present a method for applying a neural network trained on one (resource-rich) language for a given task to other (resource-poor) languages.
no code implementations • 8 Jul 2019 • Satoshi Akasaki, Naoki Yoshinaga, Masashi Toyoda
Keeping up to date on emerging entities that appear every day is indispensable for various applications, such as social-trend analysis and marketing research.
no code implementations • NAACL 2019 • Daisuke Oba, Naoki Yoshinaga, Shoetsu Sato, Satoshi Akasaki, Masashi Toyoda
In this study, we propose a method of modeling such personal biases in word meanings (hereafter, semantic variations) with personalized word embeddings obtained by solving a task on subjective text while regarding words used by different individuals as different words.
no code implementations • NAACL 2019 • Shonosuke Ishiwatari, Hiroaki Hayashi, Naoki Yoshinaga, Graham Neubig, Shoetsu Sato, Masashi Toyoda, Masaru Kitsuregawa
When reading a text, it is common to become stuck on unfamiliar words and phrases, such as polysemous words with novel senses, rarely used idioms, internet slang, or emerging entities.
1 code implementation • 1 Nov 2018 • Shonosuke Ishiwatari, Hiroaki Hayashi, Naoki Yoshinaga, Graham Neubig, Shoetsu Sato, Masashi Toyoda, Masaru Kitsuregawa
When reading a text, it is common to become stuck on unfamiliar words and phrases, such as polysemous words with novel senses, rarely used idioms, internet slang, or emerging entities.
1 code implementation • WS 2017 • Masato Neishi, Jin Sakuma, Satoshi Tohda, Shonosuke Ishiwatari, Naoki Yoshinaga, Masashi Toyoda
In this paper, we describe the team UT-IIS{'}s system and results for the WAT 2017 translation tasks.
no code implementations • ACL 2017 • Shonosuke Ishiwatari, JingTao Yao, Shujie Liu, Mu Li, Ming Zhou, Naoki Yoshinaga, Masaru Kitsuregawa, Weijia Jia
The chunk-level decoder models global dependencies while the word-level decoder decides the local word order in a chunk.
no code implementations • COLING 2016 • Tatsuya Iwanari, Kohei Ohara, Naoki Yoshinaga, Nobuhiro Kaji, Masashi Toyoda, Masaru Kitsuregawa
Kotonush, a system that clarifies people{'}s values on various concepts on the basis of what they write about on social media, is presented.