no code implementations • COLING 2022 • Yuto Kuroda, Tomoyuki Kajiwara, Yuki Arase, Takashi Ninomiya
We propose a method to distill language-agnostic meaning embeddings from multilingual sentence encoders for unsupervised quality estimation of machine translation.
no code implementations • RANLP 2021 • Yuki Yano, Akihiro Tamura, Takashi Ninomiya, Hiroaki Obayashi
This study proposes an utterance position-aware approach for a neural network-based dialogue act recognition (DAR) model, which incorporates positional encoding for utterance’s absolute or relative position.
no code implementations • WAT 2022 • Yuki Nakatani, Tomoyuki Kajiwara, Takashi Ninomiya
In text generation tasks such as machine translation, models are generally trained using cross-entropy loss.
1 code implementation • sdp (COLING) 2022 • Hiroki Yamauchi, Tomoyuki Kajiwara, Marie Katsurai, Ikki Ohmukai, Takashi Ninomiya
We release a pretrained Japanese masked language model for an academic domain.
1 code implementation • LREC 2022 • Haruya Suzuki, Yuto Miyauchi, Kazuki Akiyama, Tomoyuki Kajiwara, Takashi Ninomiya, Noriko Takemura, Yuta Nakashima, Hajime Nagahara
We annotate 35, 000 SNS posts with both the writer’s subjective sentiment polarity labels and the reader’s objective ones to construct a Japanese sentiment analysis dataset.
1 code implementation • LREC 2022 • Kazuki Tani, Ryoya Yuasa, Kazuki Takikawa, Akihiro Tamura, Tomoyuki Kajiwara, Takashi Ninomiya, Tsuneo Kato
Therefore, we create a benchmark test dataset for Japanese-to-English MLCC-MT from the Newsela corpus by introducing an automatic filtering of data with inappropriate sentence-level complexity, manual check for parallel target language sentences with different complexity levels, and manual translation.
no code implementations • 9 Nov 2023 • Yuto Kuroda, Atsushi Fujita, Tomoyuki Kajiwara, Takashi Ninomiya
In this paper, we extensively investigate the usefulness of synthetic TQE data and pre-trained multilingual encoders in unsupervised sentence-level TQE, both of which have been proven effective in the supervised training scenarios.
no code implementations • ACL 2021 • Hiroyuki Deguchi, Akihiro Tamura, Takashi Ninomiya
This paper proposes a novel attention mechanism for Transformer Neural Machine Translation, {``}Synchronous Syntactic Attention,{''} inspired by synchronous dependency grammars.
no code implementations • NAACL 2021 • Kazuki Akiyama, Akihiro Tamura, Takashi Ninomiya
This paper proposes a new abstractive document summarization model, hierarchical BART (Hie-BART), which captures hierarchical structures of a document (i. e., sentence-word structures) in the BART model.
Ranked #7 on Document Summarization on CNN / Daily Mail
no code implementations • 28 Dec 2020 • Keisuke Shirai, Kazuma Hashimoto, Akiko Eriguchi, Takashi Ninomiya, Shinsuke Mori
In this paper, we propose to suppress an arbitrary type of errors by training the text generation model in a reinforcement learning framework, where we use a trainable reward function that is capable of discriminating between references and sentences containing the targeted type of errors.
no code implementations • COLING 2020 • Tetsuro Nishihara, Akihiro Tamura, Takashi Ninomiya, Yutaro Omote, Hideki Nakayama
This paper proposed a supervised visual attention mechanism for multimodal neural machine translation (MNMT), trained with constraints based on manual alignments between words in a sentence and their corresponding regions of an image.
no code implementations • COLING 2020 • Hiroyuki Deguchi, Masao Utiyama, Akihiro Tamura, Takashi Ninomiya, Eiichiro Sumita
This paper proposed a new subword segmentation method for neural machine translation, {``}Bilingual Subword Segmentation,{''} which tokenizes sentences to minimize the difference between the number of subword units in a sentence and that of its translation.
no code implementations • Asian Chapter of the Association for Computational Linguistics 2020 • Yutaro Omote, Kyoumoto Matsushita, Tomoya Iwakura, Akihiro Tamura, Takashi Ninomiya
Instead of handcrafted rules, we propose Transformer-based models that predict SMILES strings from chemical compound names.
no code implementations • LREC 2020 • Hideki Nakayama, Akihiro Tamura, Takashi Ninomiya
To verify our dataset, we performed phrase localization experiments in both languages and investigated the effectiveness of our Japanese annotations as well as multilingual learning realized by our dataset.
no code implementations • IJCNLP 2019 • Taiki Watanabe, Akihiro Tamura, Takashi Ninomiya, Takuya Makino, Tomoya Iwakura
We propose a method to improve named entity recognition (NER) for chemical compounds using multi-task learning by jointly training a chemical NER model and a chemical com- pound paraphrase model.
no code implementations • RANLP 2019 • Yutaro Omote, Akihiro Tamura, Takashi Ninomiya
This paper proposes a new Transformer neural machine translation model that incorporates syntactic distances between two source words into the relative position representations of the self-attention mechanism.
no code implementations • RANLP 2019 • Hiroyuki Deguchi, Akihiro Tamura, Takashi Ninomiya
In this paper, we propose a new Transformer neural machine translation (NMT) model that incorporates dependency relations into self-attention on both source and target sides, dependency-based self-attention.
no code implementations • COLING 2018 • Arata Ugawa, Akihiro Tamura, Takashi Ninomiya, Hiroya Takamura, Manabu Okumura
To alleviate these problems, the encoder of the proposed model encodes the input word on the basis of its NE tag at each time step, which could reduce the ambiguity of the input word.
no code implementations • IJCNLP 2017 • Taiki Watanabe, Akihiro Tamura, Takashi Ninomiya
This paper proposes a new attention mechanism for neural machine translation (NMT) based on convolutional neural networks (CNNs), which is inspired by the CKY algorithm.