Sho Takase | DeepAI

AI Chat

Featured Co-authors

Kentaro Inui
78 publications
Jun Suzuki
42 publications
Naoaki Okazaki
42 publications
Masahiro Kaneko
29 publications
Masaaki Nagata
17 publications
Sosuke Kobayashi
15 publications
Shun Kiyono
14 publications
Tatsuya Hiraoka
6 publications
Mengsay Loem
3 publications
Kei Uchiumi
2 publications
Ayana Niwa
2 publications

∙ 05/29/2023

Exploring Effectiveness of GPT-3 in Grammatical Error Correction: A Study on Performance and Controllability in Prompt-Based Methods

Large-scale pre-trained language models such as GPT-3 have shown remarka...

0 Mengsay Loem, et al. ∙

∙ 08/26/2022

Nearest Neighbor Non-autoregressive Text Generation

Non-autoregressive (NAR) models can generate sentences with less computa...

0 Ayana Niwa, et al. ∙

∙ 07/27/2022

Are Neighbors Enough? Multi-Head Neural n-gram can be Alternative to Self-attention

Impressive performance of Transformer has been attributed to self-attent...

16 Mengsay Loem, et al. ∙

∙ 06/01/2022

On Layer Normalizations and Residual Connections in Transformers

In the perspective of a layer normalization (LN) position, the architect...

21 Sho Takase, et al. ∙

∙ 03/25/2022

Single Model Ensemble for Subword Regularized Models in Low-Resource Machine Translation

Subword regularizations use multiple subword segmentations during traini...

0 Sho Takase, et al. ∙

∙ 03/14/2022

Interpretability for Language Learners Using Example-Based Grammatical Error Correction

Grammatical Error Correction (GEC) should not focus only on high accurac...

6 Masahiro Kaneko, et al. ∙

∙ 01/14/2022

ExtraPhrase: Efficient Data Augmentation for Abstractive Summarization

Neural models trained with large amount of parallel data have achieved i...

0 Mengsay Loem, et al. ∙

∙ 05/26/2021

Joint Optimization of Tokenization and Downstream Model

Since traditional tokenizers are isolated from a downstream task and mod...

0 Tatsuya Hiraoka, et al. ∙

∙ 04/13/2021

Lessons on Parameter Sharing across Layers in Transformers

We propose a parameter sharing method for Transformers (Vaswani et al., ...

0 Sho Takase, et al. ∙

∙ 04/05/2021

Rethinking Perturbations in Encoder-Decoders for Fast Training

We often use perturbations to regularize neural models. For neural encod...

0 Sho Takase, et al. ∙

∙ 10/15/2020

Multi-Task Learning for Cross-Lingual Abstractive Summarization

We present a multi-task learning framework for cross-lingual abstractive...

0 Sho Takase, et al. ∙

∙ 05/02/2020

Improving Truthfulness of Headline Generation

Most studies on abstractive summarization re-port ROUGE scores between s...

0 Kazuki Matsumaru, et al. ∙

∙ 04/25/2020

All Word Embeddings from One Embedding

In neural network-based models for natural language processing (NLP), th...

0 Sho Takase, et al. ∙

∙ 06/13/2019

Character n-gram Embeddings to Improve RNN Language Models

This paper proposes a novel Recurrent Neural Network (RNN) language mode...

0 Sho Takase, et al. ∙

∙ 04/16/2019

Positional Encoding to Control Output Sequence Length

Neural encoder-decoder models have been successful in natural language g...

0 Sho Takase, et al. ∙

∙ 08/30/2018

Direct Output Connection for a High-Rank Language Model

This paper proposes a state-of-the-art recurrent neural network (RNN) la...

0 Sho Takase, et al. ∙

∙ 12/22/2017

Source-side Prediction for Neural Headline Generation

The encoder-decoder model is widely used in natural language generation ...

0 Shun Kiyono, et al. ∙

∙ 09/26/2017

Input-to-Output Gate to Improve RNN Language Models

This paper proposes a reinforcing method that refines the output layers ...

0 Sho Takase, et al. ∙

∙ 07/23/2017

Composing Distributed Representations of Relational Patterns

Learning distributed representations for relation instances is a central...

0 Sho Takase, et al. ∙

Are you a researcher?
Expose your work
to one of the largest
A.I. communities in the world