Masahiro Kaneko

research

∙ 09/20/2023

Controlled Generation with Prompt Insertion for Natural Language Explanations in Grammatical Error Correction

In Grammatical Error Correction (GEC), it is crucial to ensure the user'...

0 Masahiro Kaneko, et al. ∙

research

∙ 09/18/2023

Evaluating Gender Bias of Pre-trained Language Models in Natural Language Inference by Considering All Labels

Discriminatory social biases, including gender biases, have been found i...

0 Panatchakorn Anantaprayoon, et al. ∙

research

∙ 09/16/2023

The Impact of Debiasing on the Performance of Language Models in Downstream Tasks is Underestimated

Pre-trained language models trained on large-scale data have learned ser...

0 Masahiro Kaneko, et al. ∙

research

∙ 09/13/2023

In-Contextual Bias Suppression for Large Language Models

Despite their impressive performance in a wide range of NLP tasks, Large...

0 Daisuke Oba, et al. ∙

research

∙ 07/21/2023

OUTFOX: LLM-generated Essay Detection through In-context Learning with Adversarially Generated Examples

Large Language Models (LLMs) have achieved human-level fluency in text g...

0 Ryuto Koike, et al. ∙

research

∙ 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. ∙

research

∙ 05/19/2023

Reducing Sequence Length by Predicting Edit Operations with Large Language Models

Large Language Models (LLMs) have demonstrated remarkable performance in...

0 Masahiro Kaneko, et al. ∙

research

∙ 05/19/2023

Solving NLP Problems through Human-System Collaboration: A Discussion-based Approach

Humans work together to solve common problems by having discussions, exp...

0 Masahiro Kaneko, et al. ∙

research

∙ 01/28/2023

Comparing Intrinsic Gender Bias Evaluation Measures without using Human Annotated Examples

Numerous types of social biases have been identified in pre-trained lang...

0 Masahiro Kaneko, et al. ∙

research

∙ 10/06/2022

Debiasing isn't enough! – On the Effectiveness of Debiasing MLMs and their Social Biases in Downstream Tasks

We study the relationship between task-agnostic intrinsic and task-speci...

4 Masahiro Kaneko, et al. ∙

research

∙ 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. ∙

research

∙ 05/19/2022

Gender Bias in Meta-Embeddings

Combining multiple source embeddings to create meta-embeddings is consid...

6 Masahiro Kaneko, et al. ∙

research

∙ 03/14/2022

Sense Embeddings are also Biased–Evaluating Social Biases in Static and Contextualised Sense Embeddings

Sense embedding learning methods learn different embeddings for the diff...

9 Yi Zhou, et al. ∙

research

∙ 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. ∙

research

∙ 01/17/2022

Proficiency Matters Quality Estimation in Grammatical Error Correction

This study investigates how supervised quality estimation (QE) models of...

0 Yujin Takahashi, et al. ∙

research

∙ 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. ∙

research

∙ 04/17/2021

Sentence Concatenation Approach to Data Augmentation for Neural Machine Translation

Neural machine translation (NMT) has recently gained widespread attentio...

0 Seiichiro Kondo, et al. ∙

research

∙ 04/16/2021

Comparison of Grammatical Error Correction Using Back-Translation Models

Grammatical error correction (GEC) suffers from a lack of sufficient par...

0 Aomi Koyama, et al. ∙

research

∙ 04/15/2021

Unmasking the Mask – Evaluating Social Biases in Masked Language Models

Masked Language Models (MLMs) have shown superior performances in numero...

0 Masahiro Kaneko, et al. ∙

research

∙ 04/15/2021

Simultaneous Multi-Pivot Neural Machine Translation

Parallel corpora are indispensable for training neural machine translati...

0 Raj Dabre, et al. ∙

research

∙ 01/23/2021

Dictionary-based Debiasing of Pre-trained Word Embeddings

Word embeddings trained on large corpora have shown to encode high level...

0 Masahiro Kaneko, et al. ∙

research

∙ 01/23/2021

Debiasing Pre-trained Contextualised Embeddings

In comparison to the numerous debiasing methods proposed for the static ...

0 Masahiro Kaneko, et al. ∙

research

∙ 10/25/2020

Autoencoding Improves Pre-trained Word Embeddings

Prior work investigating the geometry of pre-trained word embeddings hav...

0 Masahiro Kaneko, et al. ∙

research

∙ 10/07/2020

A Self-Refinement Strategy for Noise Reduction in Grammatical Error Correction

Existing approaches for grammatical error correction (GEC) largely rely ...

0 Masato Mita, et al. ∙

research

∙ 05/03/2020

Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction

This paper investigates how to effectively incorporate a pre-trained mas...

0 Masahiro Kaneko, et al. ∙

research

∙ 04/07/2020

Towards Multimodal Simultaneous Neural Machine Translation

Simultaneous translation involves translating a sentence before the spea...

0 Aizhan Imankulova, et al. ∙

research

∙ 06/03/2019

Gender-preserving Debiasing for Pre-trained Word Embeddings

Word embeddings learnt from massive text collections have demonstrated s...

0 Masahiro Kaneko, et al. ∙

research

∙ 04/15/2019

Multi-Head Multi-Layer Attention to Deep Language Representations for Grammatical Error Detection

It is known that a deep neural network model pre-trained with large-scal...

0 Masahiro Kaneko, et al. ∙

research

∙ 04/05/2019

Cross-Corpora Evaluation and Analysis of Grammatical Error Correction Models --- Is Single-Corpus Evaluation Enough?

This study explores the necessity of performing cross-corpora evaluation...

0 Masato Mita, et al. ∙

Masahiro Kaneko

Featured Co-authors