b'Kentaro Inui'

research

∙ 08/02/2023

Chat Translation Error Detection for Assisting Cross-lingual Communications

In this paper, we describe the development of a communication support sy...

0 Yunmeng Li, et al. ∙

research

∙ 07/28/2023

Teach Me How to Improve My Argumentation Skills: A Survey on Feedback in Argumentation

The use of argumentation in education has been shown to improve critical...

0 Camélia Guerraoui, et al. ∙

research

∙ 05/29/2023

Transformer Language Models Handle Word Frequency in Prediction Head

Prediction head is a crucial component of Transformer language models. D...

0 Goro Kobayashi, et al. ∙

research

∙ 02/16/2023

Empirical Investigation of Neural Symbolic Reasoning Strategies

Neural reasoning accuracy improves when generating intermediate reasonin...

0 Yoichi Aoki, et al. ∙

research

∙ 02/15/2023

Do Deep Neural Networks Capture Compositionality in Arithmetic Reasoning?

Compositionality is a pivotal property of symbolic reasoning. However, h...

0 Keito Kudo, et al. ∙

research

∙ 02/01/2023

Feed-Forward Blocks Control Contextualization in Masked Language Models

Understanding the inner workings of neural network models is a crucial s...

0 Goro Kobayashi, et al. ∙

research

∙ 01/17/2023

Tracing and Manipulating Intermediate Values in Neural Math Problem Solvers

How language models process complex input that requires multiple steps o...

0 Yuta Matsumoto, et al. ∙

research

∙ 11/02/2022

Cross-stitching Text and Knowledge Graph Encoders for Distantly Supervised Relation Extraction

Bi-encoder architectures for distantly-supervised relation extraction ar...

0 Qin Dai, et al. ∙

research

∙ 09/20/2022

Target-Guided Open-Domain Conversation Planning

Prior studies addressing target-oriented conversational tasks lack a cru...

0 Yosuke Kishinami, et al. ∙

research

∙ 08/04/2022

N-best Response-based Analysis of Contradiction-awareness in Neural Response Generation Models

Avoiding the generation of responses that contradict the preceding conte...

0 Shiki Sato, et al. ∙

research

∙ 06/16/2022

Balancing Cost and Quality: An Exploration of Human-in-the-loop Frameworks for Automated Short Answer Scoring

Short answer scoring (SAS) is the task of grading short text written by ...

0 Hiroaki Funayama, et al. ∙

research

∙ 05/24/2022

Diverse Lottery Tickets Boost Ensemble from a Single Pretrained Model

Ensembling is a popular method used to improve performance as a last res...

20 Sosuke Kobayashi, et al. ∙

research

∙ 05/23/2022

Towards Automated Document Revision: Grammatical Error Correction, Fluency Edits, and Beyond

Natural language processing technology has rapidly improved automated gr...

0 Masato Mita, et al. ∙

research

∙ 05/23/2022

Context Limitations Make Neural Language Models More Human-Like

Do modern natural language processing (NLP) models exhibit human-like la...

3 Tatsuki Kuribayashi, et al. ∙

research

∙ 04/04/2022

LPAttack: A Feasible Annotation Scheme for Capturing Logic Pattern of Attacks in Arguments

In argumentative discourse, persuasion is often achieved by refuting or ...

12 Farjana Sultana Mim, et al. ∙

research

∙ 01/18/2022

COPA-SSE: Semi-structured Explanations for Commonsense Reasoning

We present Semi-Structured Explanations for COPA (COPA-SSE), a new crowd...

20 Ana Brassard, et al. ∙

research

∙ 01/18/2022

TYPIC: A Corpus of Template-Based Diagnostic Comments on Argumentation

Providing feedback on the argumentation of learner is essential for deve...

3 Shoichi Naito, et al. ∙

research

∙ 10/26/2021

Annotating Implicit Reasoning in Arguments with Causal Links

Most of the existing work that focus on the identification of implicit k...

5 Keshav Singh, et al. ∙

research

∙ 09/28/2021

Instance-Based Neural Dependency Parsing

Interpretable rationales for model predictions are crucial in practical ...

0 Hiroki Ouchi, et al. ∙

research

∙ 09/15/2021

Incorporating Residual and Normalization Layers into Analysis of Masked Language Models

Transformer architecture has become ubiquitous in the natural language p...

12 Goro Kobayashi, et al. ∙

research

∙ 09/15/2021

Transformer-based Lexically Constrained Headline Generation

This paper explores a variant of automatic headline generation methods, ...

0 Kosuke Yamada, et al. ∙

research

∙ 09/14/2021

Summarize-then-Answer: Generating Concise Explanations for Multi-hop Reading Comprehension

How can we generate concise explanations for multi-hop Reading Comprehen...

0 Naoya Inoue, et al. ∙

research

∙ 09/13/2021

SHAPE: Shifted Absolute Position Embedding for Transformers

Position representation is crucial for building position-aware represent...

8 Shun Kiyono, et al. ∙

research

∙ 06/02/2021

Lower Perplexity is Not Always Human-Like

In computational psycholinguistics, various language models have been ev...

0 Tatsuki Kuribayashi, et al. ∙

research

∙ 06/02/2021

SyGNS: A Systematic Generalization Testbed Based on Natural Language Semantics

Recently, deep neural networks (DNNs) have achieved great success in sem...

0 Hitomi Yanaka, et al. ∙

research

∙ 04/23/2021

Learning to Learn to be Right for the Right Reasons

Improving model generalization on held-out data is one of the core objec...

0 Pride Kavumba, et al. ∙

research

∙ 04/16/2021

A Comparative Study on Collecting High-Quality Implicit Reasonings at a Large-scale

Explicating implicit reasoning (i.e. warrants) in arguments is a long-st...

15 Keshav Singh, et al. ∙

research

∙ 04/15/2021

Pseudo Zero Pronoun Resolution Improves Zero Anaphora Resolution

The use of pretrained masked language models (MLMs) has drastically impr...

0 Ryuto Konno, et al. ∙

research

∙ 02/12/2021

Two Training Strategies for Improving Relation Extraction over Universal Graph

This paper explores how the Distantly Supervised Relation Extraction (DS...

0 Qin Dai, et al. ∙

research

∙ 01/26/2021

Exploring Transitivity in Neural NLI Models through Veridicality

Despite the recent success of deep neural networks in natural language p...

0 Hitomi Yanaka, et al. ∙

research

∙ 12/08/2020

Efficient Estimation of Influence of a Training Instance

Understanding the influence of a training instance on a neural network m...

10 Sosuke Kobayashi, et al. ∙

research

∙ 11/04/2020

PheMT: A Phenomenon-wise Dataset for Machine Translation Robustness on User-Generated Contents

Neural Machine Translation (NMT) has shown drastic improvement in its qu...

0 Ryo Fujii, et al. ∙

research

∙ 11/03/2020

Modeling Event Salience in Narratives via Barthes' Cardinal Functions

Events in a narrative differ in salience: some are more important to the...

0 Takaki Otake, et al. ∙

research

∙ 11/02/2020

An Empirical Study of Contextual Data Augmentation for Japanese Zero Anaphora Resolution

One critical issue of zero anaphora resolution (ZAR) is the scarcity of ...

0 Ryuto Konno, et al. ∙

research

∙ 10/13/2020

Corruption Is Not All Bad: Incorporating Discourse Structure into Pre-training via Corruption for Essay Scoring

Existing approaches for automated essay scoring and document representat...

0 Farjana Sultana Mim, et al. ∙

research

∙ 10/09/2020

Langsmith: An Interactive Academic Text Revision System

Despite the current diversity and inclusion initiatives in the academic ...

0 Takumi Ito, 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

∙ 08/20/2020

Language Models as Knowledge Bases: On Entity Representations, Storage Capacity, and Paraphrased Queries

Pretrained language models have been suggested as a possible alternative...

0 Benjamin Heinzerling, et al. ∙

research

∙ 07/28/2020

A System for Worldwide COVID-19 Information Aggregation

The global pandemic of COVID-19 has made the public pay close attention ...

0 Akiko Aizawa, et al. ∙

research

∙ 06/08/2020

Evaluation Criteria for Instance-based Explanation

Explaining predictions made by complex machine learning models helps use...

0 Kazuaki Hanawa, et al. ∙

research

∙ 06/02/2020

Embeddings of Label Components for Sequence Labeling: A Case Study of Fine-grained Named Entity Recognition

In general, the labels used in sequence labeling consist of different ty...

0 Takuma Kato, 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

∙ 05/02/2020

Language Models as an Alternative Evaluator of Word Order Hypotheses: A Case Study in Japanese

We examine a methodology using neural language models (LMs) for analyzin...

0 Tatsuki Kuribayashi, et al. ∙

research

∙ 04/30/2020

Word Rotator's Distance: Decomposing Vectors Gives Better Representations

One key principle for assessing semantic similarity between texts is to ...

0 Sho Yokoi, et al. ∙

research

∙ 04/30/2020

Do Neural Models Learn Systematicity of Monotonicity Inference in Natural Language?

Despite the success of language models using neural networks, it remains...

0 Hitomi Yanaka, et al. ∙

research

∙ 04/29/2020

Instance-Based Learning of Span Representations: A Case Study through Named Entity Recognition

Interpretable rationales for model predictions play a critical role in p...

0 Hiroki Ouchi, et al. ∙

research

∙ 04/29/2020

Evaluating Dialogue Generation Systems via Response Selection

Existing automatic evaluation metrics for open-domain dialogue response ...

0 Shiki Sato, et al. ∙

research

∙ 04/29/2020

Utterance Pair Scoring for Noisy Dialogue Data Filtering

Filtering noisy training data is one of the key approaches to improving ...

0 Reina Akama, et al. ∙

research

∙ 04/21/2020

Attention Module is Not Only a Weight: Analyzing Transformers with Vector Norms

Because attention modules are core components of Transformer-based model...

0 Goro Kobayashi, et al. ∙

research

∙ 11/21/2019

Assessing the Benchmarking Capacity of Machine Reading Comprehension Datasets

Existing analysis work in machine reading comprehension (MRC) is largely...

0 Saku Sugawara, et al. ∙

Kentaro Inui

Featured Co-authors