Papers by Hideki Tanaka

10 papers
Centroid-Based Efficient Minimum Bayes Risk Decoding (2024.findings-acl)

Copied to clipboard

Challenge: Minimum Bayes risk (MBR) decoding requires quadratic time since it computes the expected score between a translation hypothesis and all reference translations.
Approach: They propose a centroid-based MBR decoding method that clusters the translations in the feature space and calculates the expected score using the centroids of each cluster.
Outcome: The proposed method outperforms vanilla MBR decoding in translation quality by up to 0.5 COMET in the WMT’22 EnJa, EnDe, EnZh, and WMT'23 Enja translation tasks.
Content-Equivalent Translated Parallel News Corpus and Extension of Domain Adaptation for NMT (2020.lrec-1)

Copied to clipboard

Challenge: Existing methods to train NMT systems with noisy data are not sufficient . a recent increase in foreigners visiting Japan has created a significant information gap .
Approach: They propose a Japanese-English parallel news corpus that is content-equivalent . they extend a domain-adaptation method to train NMT models with clean corpus .
Outcome: The proposed corpus improves translation quality and is more effective than existing methods.
Neural Machine Translation System using a Content-equivalently Translated Parallel Corpus for the Newswire Translation Tasks at WAT 2019 (D19-52)

Copied to clipboard

Challenge: In addition to the JIJI Corpus, we developed a corpus of 0.22M sentence pairs by manually, translating Japanese news sentences into English content- equivalently.
Approach: They propose to use JIJI Corpus and Equivalent-style sentences to translate Japanese news sentences into English content- equivalently.
Outcome: The proposed translation models achieved the best human evaluation scores in the newswire translation tasks at WAT 2019 . they used the JIJI Corpus, which was provided by the task organizer, and the Equivalent-style translation model to translate Japanese news sentences into English content- equivalently.
PrahokBART: A Pre-trained Sequence-to-Sequence Model for Khmer Natural Language Generation (2025.coling-main)

Copied to clipboard

Challenge: Pre-trained sequence-to-sequence models are typically pretrained on extensive raw text corpora and fine-tuned on task-specific data.
Approach: They introduce a pre-trained sequence-to-sequence model trained from scratch for Khmer using carefully curated Khmer and English corpora.
Outcome: The proposed model outperforms existing models on three generative tasks and is data-efficient and effective in enhancing performance across various natural language generation tasks.
FeatureBART: Feature Based Sequence-to-Sequence Pre-Training for Low-Resource NMT (2022.coling-1)

Copied to clipboard

Challenge: FeatureBART is a linguistically motivated sequence-to-sequence monolingual pre-training strategy . syntactic features such as lemma, part-of-speech and dependency labels are incorporated into the pre-trained model .
Approach: They propose a linguistically motivated sequence-to-sequence monolingual pre-training strategy that incorporates syntactic features into the framework.
Outcome: The proposed model improves translation quality in bilingual and multilingual settings over models that do not use features.
A Multilingual Multiway Evaluation Data Set for Structured Document Translation of Asian Languages (2022.findings-aacl)

Copied to clipboard

Challenge: a lack of evaluation data sets for structured content limits progress in machine translation . a common use case of machine translation is the translation of structured or formatted documents .
Approach: They propose a multilingual multiway evaluation data set for machine translation of structured documents of Asian languages Japanese, Korean and Chinese.
Outcome: The proposed data set is well suited for multilingual evaluation and contains richer annotation tag sets than existing data sets.
Registering Source Tokens to Target Language Spaces in Multilingual Neural Machine Translation (2025.acl-long)

Copied to clipboard

Challenge: Multilingual neural machine translation (MNMT) aims for arbitrary translations across multiple languages.
Approach: They propose a method that inserts a set of tokens specifying the target language into the input sequence between the source and target tokens.
Outcome: The proposed method outperforms existing models on a large-scale benchmark.
Subset Retrieval Nearest Neighbor Machine Translation (2023.acl-long)

Copied to clipboard

Challenge: k-nearest-neighbor machine translation (kNN-MT) is a new approach to improve NMT performance without additional training.
Approach: They propose a method that integrates example-search into the decoding algorithm to improve neighbor token retrieval.
Outcome: The proposed method achieves a speed-up of up to 132.2 times and an improvement in BLEU score of up 1.6 compared with kNN-MT in the WMT’19 translation task and the domain adaptation tasks in De-En and En-Ja.
Robust Neural Machine Translation for Abugidas by Glyph Perturbation (2024.eacl-short)

Copied to clipboard

Challenge: Neural machine translation systems are vulnerable when trained on limited data.
Approach: They propose to add noise to the training phase to increase robustness of NMT systems trained on limited data.
Outcome: The proposed training strategy overcomes noise and improves robustness for low-resource tasks for abugida glyphs.
NGLUEni: Benchmarking and Adapting Pretrained Language Models for Nguni Languages (2024.lrec-main)

Copied to clipboard

Challenge: Nguni languages have over 20 million home language speakers in South Africa . there has been considerable growth in the datasets for these languages, but no analysis of the performance of NLP models for these language has been reported across languages and tasks.
Approach: They compile publicly available datasets for natural language understanding and generation, spanning 6 tasks and 11 datasets.
Outcome: The proposed models outperform existing models and large-scale adapted models on cross-lingual transfer and machine translation.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations