← Authors

Sho Takase

28 papers · 2013–2025 · 7 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (7) 🐣 Hot Topic Early Bird πŸ—ΊοΈ Taxonomy Completionist (48) 🌈 Renaissance Researcher (5) πŸŒ‰ Interdisciplinary Bridge 🐝 Cross-Pollinator (9) 🧭 Keyword Pioneer πŸƒ Academic Marathon (12) 🌟 Keyword Trendsetter Combo (3) 🀝 Dynamic Duo (14) 🌱 Topic Pioneer 🧬 Topic Evolution ⚑ Prolific Year (5) πŸ’Ž Century Club (28) πŸš€ Conference Pioneer πŸ—ƒοΈ Keyword Collector (88) πŸ”₯ Unstoppable (8) πŸ“ˆ Trend Setter

Conferences

ACL (13) EMNLP (6) IJCNLP (3) NAACL (3) AAAI (1) ICML (1) NIPS (1)

Top co-authors

Naoaki Okazaki (14) Masaaki Nagata (8) Jun Suzuki (8) Shun Kiyono (6) Tatsuya Hiraoka (5) Atsushi Keyaki (4) Kei Uchiumi (4) Kentaro Inui (3) Tsutomu Hirao (3) Masahiro Kaneko (3)

Research topics

Education (1)

Keywords

neural machine translation (4) language model (4) recurrent neural network (3) encoder-decoder model (3) machine translation (3) data augmentation (3) anagram generation (2) grammatical error correction (2) depth-first search (2) text summarization (2) combinatorial constraint (2) natural language generation (2) neural language model (2) subword regularization (2) model ensemble (2) text classification (2) headline generation (2) word embedding (2) abstractive summarization (2) large language model (2)

Papers

Scaling Laws for Upcycling Mixture-of-Experts Language Models ICML 2025
Large Vocabulary Size Improves Large Language Models ACL 2025
B2T Connection: Serving Stability and Performance in Deep Transformers ACL 2023
Lessons on Parameter Sharing across Layers in Transformers ACL 2023
Exploring Effectiveness of GPT-3 in Grammatical Error Correction: A Study on Performance and Controllability in Prompt-Based Methods ACL 2023
Dynamic Structured Neural Topic Model with Self-Attention Mechanism ACL 2023
ExtraPhrase: Efficient Data Augmentation for Abstractive Summarization NAACL 2022
Interpretability for Language Learners Using Example-Based Grammatical Error Correction ACL 2022
Single Model Ensemble for Subword Regularized Models in Low-Resource Machine Translation ACL 2022
Word-level Perturbation Considering Word Length and Compositional Subwords ACL 2022
NT5 at WMT 2022 General Translation Task EMNLP 2022
Joint Optimization of Tokenization and Downstream Model IJCNLP 2021
Joint Optimization of Tokenization and Downstream Model ACL 2021
Rethinking Perturbations in Encoder-Decoders for Fast Training NAACL 2021
Optimizing Word Segmentation for Downstream Task EMNLP 2020
Improving Truthfulness of Headline Generation ACL 2020
All Word Embeddings from One Embedding NIPS 2020
Character n-Gram Embeddings to Improve RNN Language Models AAAI 2019
Generating Natural Anagrams: Towards Language Generation Under Hard Combinatorial Constraints IJCNLP 2019
Positional Encoding to Control Output Sequence Length NAACL 2019
Generating Natural Anagrams: Towards Language Generation Under Hard Combinatorial Constraints EMNLP 2019
Unsupervised Token-wise Alignment to Improve Interpretation of Encoder-Decoder Models EMNLP 2018
An Empirical Study of Building a Strong Baseline for Constituency Parsing ACL 2018
Direct Output Connection for a High-Rank Language Model EMNLP 2018
Input-to-Output Gate to Improve RNN Language Models IJCNLP 2017
Composing Distributed Representations of Relational Patterns ACL 2016
Neural Headline Generation on Abstract Meaning Representation EMNLP 2016
Detecting Chronic Critics Based on Sentiment Polarity and User’s Behavior in Social Media ACL 2013