Search Results for author: Kentaro Inui

Found 177 papers, 67 papers with code

Exploring Methods for Generating Feedback Comments for Writing Learning

1 code implementation EMNLP 2021 Kazuaki Hanawa, Ryo Nagata, Kentaro Inui

To shed light on these points, we investigate a wider range of methods for generating many feedback comments in this study.

Comment Generation Retrieval

IRAC: A Domain-Specific Annotated Corpus of Implicit Reasoning in Arguments

1 code implementation LREC 2022 Keshav Singh, Naoya Inoue, Farjana Sultana Mim, Shoichi Naito, Kentaro Inui

To solve this problem, we hypothesize that as human reasoning is guided by innate collection of domain-specific knowledge, it might be beneficial to create such a domain-specific corpus for machines.

Exploring Methodologies for Collecting High-Quality Implicit Reasoning in Arguments

1 code implementation EMNLP (ArgMining) 2021 Keshav Singh, Farjana Sultana Mim, Naoya Inoue, Shoichi Naito, Kentaro Inui

Annotation of implicit reasoning (i. e., warrant) in arguments is a critical resource to train models in gaining deeper understanding and correct interpretation of arguments.

Vocal Bursts Intensity Prediction

Emergence of Primacy and Recency Effect in Mamba: A Mechanistic Point of View

no code implementations18 Jun 2025 Muhammad Cendekia Airlangga, Hilal AlQuabeh, Munachiso S Nwadike, Kentaro Inui

We study memory in state-space language models using primacy and recency effects as behavioral tools to uncover how information is retained and forgotten over time.

Mamba

Spelling-out is not Straightforward: LLMs' Capability of Tokenization from Token to Characters

no code implementations12 Jun 2025 Tatsuya Hiraoka, Kentaro Inui

Large language models (LLMs) can spell out tokens character by character with high accuracy, yet they struggle with more complex character-level tasks, such as identifying compositional subcomponents within tokens.

On Entity Identification in Language Models

no code implementations3 Jun 2025 Masaki Sakata, Benjamin Heinzerling, Sho Yokoi, Takumi Ito, Kentaro Inui

We analyze the extent to which internal representations of language models (LMs) identify and distinguish mentions of named entities, focusing on the many-to-many correspondence between entities and their mentions.

Understanding Fact Recall in Language Models: Why Two-Stage Training Encourages Memorization but Mixed Training Teaches Knowledge

no code implementations22 May 2025 Ying Zhang, Benjamin Heinzerling, Dongyuan Li, Ryoma Ishigaki, Yuta Hitomi, Kentaro Inui

Fact recall, the ability of language models (LMs) to retrieve specific factual knowledge, remains a challenging task despite their impressive general capabilities.

Memorization

Mechanistic Insights into Grokking from the Embedding Layer

no code implementations21 May 2025 H. V. AlquBoj, Hilal AlQuabeh, Velibor Bojkovic, Munachiso Nwadike, Kentaro Inui

Grokking, a delayed generalization in neural networks after perfect training performance, has been observed in Transformers and MLPs, but the components driving it remain underexplored.

SPIRIT: Patching Speech Language Models against Jailbreak Attacks

no code implementations18 May 2025 Amirbek Djanibekov, Nurdaulet Mukhituly, Kentaro Inui, Hanan Aldarmaki, Nils Lukas

Speech Language Models (SLMs) enable natural interactions via spoken instructions, which more effectively capture user intent by detecting nuances in speech.

Tell Me Who Your Students Are: GPT Can Generate Valid Multiple-Choice Questions When Students' (Mis)Understanding Is Hinted

no code implementations9 May 2025 Machi Shimmei, Masaki Uto, Yuichiroh Matsubayashi, Kentaro Inui, Aditi Mallavarapu, Noboru Matsuda

To evaluate the validity of the generated MCQs, Item Response Theory (IRT) was applied to compare item characteristics between MCQs generated by AnaQuest, a baseline ChatGPT prompt, and human-crafted items.

Language Modeling Language Modelling +4

How LLMs Learn: Tracing Internal Representations with Sparse Autoencoders

1 code implementation9 Mar 2025 Tatsuro Inaba, Kentaro Inui, Yusuke Miyao, Yohei Oseki, Benjamin Heinzerling, Yu Takagi

Large Language Models (LLMs) demonstrate remarkable multilingual capabilities and broad knowledge.

Syntactic Learnability of Echo State Neural Language Models at Scale

no code implementations3 Mar 2025 Ryo Ueda, Tatsuki Kuribayashi, Shunsuke Kando, Kentaro Inui

What is a neural model with minimum architectural complexity that exhibits reasonable language learning capability?

Language Modeling Language Modelling

Rectifying Belief Space via Unlearning to Harness LLMs' Reasoning

no code implementations28 Feb 2025 Ayana Niwa, Masahiro Kaneko, Kentaro Inui

Large language models (LLMs) can exhibit advanced reasoning yet still generate incorrect answers.

Number Representations in LLMs: A Computational Parallel to Human Perception

1 code implementation22 Feb 2025 H. V. AlquBoj, Hilal AlQuabeh, Velibor Bojkovic, Tatsuya Hiraoka, Ahmed Oumar El-Shangiti, Munachiso Nwadike, Kentaro Inui

Humans are believed to perceive numbers on a logarithmic mental number line, where smaller values are represented with greater resolution than larger ones.

Dimensionality Reduction

Weight-based Analysis of Detokenization in Language Models: Understanding the First Stage of Inference Without Inference

no code implementations27 Jan 2025 Go Kamoda, Benjamin Heinzerling, Tatsuro Inaba, Keito Kudo, Keisuke Sakaguchi, Kentaro Inui

According to the stages-of-inference hypothesis, early layers of language models map their subword-tokenized input, which does not necessarily correspond to a linguistically meaningful segmentation, to more meaningful representations that form the model's ``inner vocabulary''.

RECALL: Library-Like Behavior In Language Models is Enhanced by Self-Referencing Causal Cycles

1 code implementation23 Jan 2025 Munachiso Nwadike, Zangir Iklassov, Toluwani Aremu, Tatsuya Hiraoka, Velibor Bojkovic, Benjamin Heinzerling, Hilal Alqaubeh, Martin Takáč, Kentaro Inui

We introduce the concept of the self-referencing causal cycle (abbreviated RECALL) - a mechanism that enables large language models (LLMs) to bypass the limitations of unidirectional causality, which underlies a phenomenon known as the reversal curse.

Think-to-Talk or Talk-to-Think? When LLMs Come Up with an Answer in Multi-Step Arithmetic Reasoning

no code implementations2 Dec 2024 Keito Kudo, Yoichi Aoki, Tatsuki Kuribayashi, Shusaku Sone, Masaya Taniguchi, Ana Brassard, Keisuke Sakaguchi, Kentaro Inui

This study investigates the internal reasoning process of language models during arithmetic multi-step reasoning, motivated by the question of when they internally form their answers during reasoning.

Arithmetic Reasoning

The Geometry of Numerical Reasoning: Language Models Compare Numeric Properties in Linear Subspaces

no code implementations17 Oct 2024 Ahmed Oumar El-Shangiti, Tatsuya Hiraoka, Hilal AlQuabeh, Benjamin Heinzerling, Kentaro Inui

This paper investigates whether large language models (LLMs) utilize numerical attributes encoded in a low-dimensional subspace of the embedding space when answering logical comparison questions (e. g., Was Cristiano born before Messi?).

Repetition Neurons: How Do Language Models Produce Repetitions?

no code implementations17 Oct 2024 Tatsuya Hiraoka, Kentaro Inui

This paper introduces repetition neurons, regarded as skill neurons responsible for the repetition problem in text generation tasks.

In-Context Learning Text Generation

Representational Analysis of Binding in Language Models

no code implementations9 Sep 2024 Qin Dai, Benjamin Heinzerling, Kentaro Inui

Moreover, we also discover the causal effect of OI on binding that when editing representations along the OI encoding direction, LMs tend to bind a given entity to other attributes accordingly.

Attribute Dimensionality Reduction

An Investigation of Warning Erroneous Chat Translations in Cross-lingual Communication

no code implementations28 Aug 2024 Yunmeng Li, Jun Suzuki, Makoto Morishita, Kaori Abe, Kentaro Inui

Machine translation models are still inappropriate for translating chats, despite the popularity of translation software and plug-in applications.

Machine Translation Translation

Reducing the Cost: Cross-Prompt Pre-Finetuning for Short Answer Scoring

1 code implementation26 Aug 2024 Hiroaki Funayama, Yuya Asazuma, Yuichiroh Matsubayashi, Tomoya Mizumoto, Kentaro Inui

Specifically, given that scoring rubrics and reference answers differ for each prompt, we utilize key phrases, or representative expressions that the answer should contain to increase scores, and train a SAS model to learn the relationship between key phrases and answers using already annotated prompts (i. e., cross-prompts).

First Heuristic Then Rational: Dynamic Use of Heuristics in Language Model Reasoning

1 code implementation23 Jun 2024 Yoichi Aoki, Keito Kudo, Tatsuki Kuribayashi, Shusaku Sone, Masaya Taniguchi, Keisuke Sakaguchi, Kentaro Inui

Multi-step reasoning instruction, such as chain-of-thought prompting, is widely adopted to explore better language models (LMs) performance.

Language Modeling Language Modelling

The Curse of Popularity: Popular Entities have Catastrophic Side Effects when Deleting Knowledge from Language Models

no code implementations10 Jun 2024 Ryosuke Takahashi, Go Kamoda, Benjamin Heinzerling, Keisuke Sakaguchi, Kentaro Inui

This study focuses on the knowledge stored in LMs and analyzes the relationship between the side effects of knowledge deletion and the entities related to the knowledge.

Knowledge Graphs World Knowledge

ACORN: Aspect-wise Commonsense Reasoning Explanation Evaluation

1 code implementation8 May 2024 Ana Brassard, Benjamin Heinzerling, Keito Kudo, Keisuke Sakaguchi, Kentaro Inui

However, their correlation with majority-voted human ratings varied across different quality aspects, indicating that they are not a complete replacement.

Monotonic Representation of Numeric Properties in Language Models

1 code implementation15 Mar 2024 Benjamin Heinzerling, Kentaro Inui

Language models (LMs) can express factual knowledge involving numeric properties such as Karl Popper was born in 1902.

Japanese-English Sentence Translation Exercises Dataset for Automatic Grading

no code implementations6 Mar 2024 Naoki Miura, Hiroaki Funayama, Seiya Kikuchi, Yuichiroh Matsubayashi, Yuya Iwase, Kentaro Inui

Using this dataset, we demonstrate the performance of baselines including finetuned BERT and GPT models with few-shot in-context learning.

Few-Shot Learning In-Context Learning +2

J-UniMorph: Japanese Morphological Annotation through the Universal Feature Schema

1 code implementation22 Feb 2024 Kosuke Matsuzaki, Masaya Taniguchi, Kentaro Inui, Keisuke Sakaguchi

We introduce a Japanese Morphology dataset, J-UniMorph, developed based on the UniMorph feature schema.

Test-time Augmentation for Factual Probing

1 code implementation26 Oct 2023 Go Kamoda, Benjamin Heinzerling, Keisuke Sakaguchi, Kentaro Inui

Factual probing is a method that uses prompts to test if a language model "knows" certain world knowledge facts.

Language Modeling Language Modelling +2

Contrastive Learning-based Sentence Encoders Implicitly Weight Informative Words

1 code implementation24 Oct 2023 Hiroto Kurita, Goro Kobayashi, Sho Yokoi, Kentaro Inui

The performance of sentence encoders can be significantly improved through the simple practice of fine-tuning using contrastive loss.

Contrastive Learning Sentence

Chat Translation Error Detection for Assisting Cross-lingual Communications

1 code implementation2 Aug 2023 Yunmeng Li, Jun Suzuki, Makoto Morishita, Kaori Abe, Ryoko Tokuhisa, Ana Brassard, Kentaro Inui

In this paper, we describe the development of a communication support system that detects erroneous translations to facilitate crosslingual communications due to the limitations of current machine chat translation methods.

Translation

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

no code implementations28 Jul 2023 Camélia Guerraoui, Paul Reisert, Naoya Inoue, Farjana Sultana Mim, Shoichi Naito, Jungmin Choi, Irfan Robbani, Wenzhi Wang, Kentaro Inui

The use of argumentation in education has been shown to improve critical thinking skills for end-users such as students, and computational models for argumentation have been developed to assist in this process.

Prompting for explanations improves Adversarial NLI. Is this true? {Yes} it is {true} because {it weakens superficial cues}

no code implementations EACL 2023 Pride Kavumba, Ana Brassard, Benjamin Heinzerling, Kentaro Inui

Explanation prompts ask language models to not only assign a particular label to a giveninput, such as true, entailment, or contradiction in the case of natural language inference but also to generate a free-text explanation that supports this label.

Adversarial Natural Language Inference Natural Language Inference

Tracing and Manipulating Intermediate Values in Neural Math Problem Solvers

1 code implementation17 Jan 2023 Yuta Matsumoto, Benjamin Heinzerling, Masashi Yoshikawa, Kentaro Inui

Previous research has shown that information about intermediate values of these inputs can be extracted from the activations of the models, but it is unclear where that information is encoded and whether that information is indeed used during inference.

Math

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

1 code implementation2 Nov 2022 Qin Dai, Benjamin Heinzerling, Kentaro Inui

They either do not allow any sharing between the text encoder and the KG encoder at all, or, in case of models with KG-to-text attention, only share information in one direction.

Knowledge Graphs Relation +1

Target-Guided Open-Domain Conversation Planning

1 code implementation COLING 2022 Yosuke Kishinami, Reina Akama, Shiki Sato, Ryoko Tokuhisa, Jun Suzuki, Kentaro Inui

Prior studies addressing target-oriented conversational tasks lack a crucial notion that has been intensively studied in the context of goal-oriented artificial intelligence agents, namely, planning.

Retrieval

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

1 code implementation SIGDIAL (ACL) 2022 Shiki Sato, Reina Akama, Hiroki Ouchi, Ryoko Tokuhisa, Jun Suzuki, Kentaro Inui

In this scenario, the quality of the n-best list considerably affects the occurrence of contradictions because the final response is chosen from this n-best list.

Response Generation

RealTime QA: What's the Answer Right Now?

1 code implementation NeurIPS 2023 Jungo Kasai, Keisuke Sakaguchi, Yoichi Takahashi, Ronan Le Bras, Akari Asai, Xinyan Yu, Dragomir Radev, Noah A. Smith, Yejin Choi, Kentaro Inui

We introduce REALTIME QA, a dynamic question answering (QA) platform that announces questions and evaluates systems on a regular basis (weekly in this version).

Information Retrieval Question Answering +1

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

no code implementations16 Jun 2022 Hiroaki Funayama, Tasuku Sato, Yuichiroh Matsubayashi, Tomoya Mizumoto, Jun Suzuki, Kentaro Inui

Towards guaranteeing high-quality predictions, we present the first study of exploring the use of human-in-the-loop framework for minimizing the grading cost while guaranteeing the grading quality by allowing a SAS model to share the grading task with a human grader.

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

1 code implementation23 May 2022 Masato Mita, Keisuke Sakaguchi, Masato Hagiwara, Tomoya Mizumoto, Jun Suzuki, Kentaro Inui

Natural language processing technology has rapidly improved automated grammatical error correction tasks, and the community begins to explore document-level revision as one of the next challenges.

Grammatical Error Correction Language Modelling +1

Context Limitations Make Neural Language Models More Human-Like

1 code implementation23 May 2022 Tatsuki Kuribayashi, Yohei Oseki, Ana Brassard, Kentaro Inui

Language models (LMs) have been used in cognitive modeling as well as engineering studies -- they compute information-theoretic complexity metrics that simulate humans' cognitive load during reading.

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

no code implementations LREC 2022 Farjana Sultana Mim, Naoya Inoue, Shoichi Naito, Keshav Singh, Kentaro Inui

Attacking is not always straightforward and often comprise complex rhetorical moves such that arguers might agree with a logic of an argument while attacking another logic.

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

1 code implementation LREC 2022 Shoichi Naito, Shintaro Sawada, Chihiro Nakagawa, Naoya Inoue, Kenshi Yamaguchi, Iori Shimizu, Farjana Sultana Mim, Keshav Singh, Kentaro Inui

In this paper, we define three criteria that a template set should satisfy: expressiveness, informativeness, and uniqueness, and verify the feasibility of creating a template set that satisfies these criteria as a first trial.

Diagnostic Informativeness +2

COPA-SSE: Semi-structured Explanations for Commonsense Reasoning

1 code implementation LREC 2022 Ana Brassard, Benjamin Heinzerling, Pride Kavumba, Kentaro Inui

We present Semi-Structured Explanations for COPA (COPA-SSE), a new crowdsourced dataset of 9, 747 semi-structured, English common sense explanations for Choice of Plausible Alternatives (COPA) questions.

Common Sense Reasoning Knowledge Graphs

Annotating Implicit Reasoning in Arguments with Causal Links

no code implementations26 Oct 2021 Keshav Singh, Naoya Inoue, Farjana Sultana Mim, Shoichi Naitoh, Kentaro Inui

Most of the existing work that focus on the identification of implicit knowledge in arguments generally represent implicit knowledge in the form of commonsense or factual knowledge.

Transformer-based Lexically Constrained Headline Generation

1 code implementation EMNLP 2021 Kosuke Yamada, Yuta Hitomi, Hideaki Tamori, Ryohei Sasano, Naoaki Okazaki, Kentaro Inui, Koichi Takeda

We also consider a new headline generation strategy that takes advantage of the controllable generation order of Transformer.

Headline Generation

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

1 code implementation EMNLP 2021 Naoya Inoue, Harsh Trivedi, Steven Sinha, Niranjan Balasubramanian, Kentaro Inui

Instead, we advocate for an abstractive approach, where we propose to generate a question-focused, abstractive summary of input paragraphs and then feed it to an RC system.

2k Multi-Hop Reading Comprehension

SHAPE: Shifted Absolute Position Embedding for Transformers

1 code implementation13 Sep 2021 Shun Kiyono, Sosuke Kobayashi, Jun Suzuki, Kentaro Inui

Position representation is crucial for building position-aware representations in Transformers.

Position

SyGNS: A Systematic Generalization Testbed Based on Natural Language Semantics

1 code implementation Findings (ACL) 2021 Hitomi Yanaka, Koji Mineshima, Kentaro Inui

We also find that the generalization performance to unseen combinations is better when the form of meaning representations is simpler.

Negation Systematic Generalization

Lower Perplexity is Not Always Human-Like

1 code implementation ACL 2021 Tatsuki Kuribayashi, Yohei Oseki, Takumi Ito, Ryo Yoshida, Masayuki Asahara, Kentaro Inui

Overall, our results suggest that a cross-lingual evaluation will be necessary to construct human-like computational models.

Language Modeling Language Modelling

Learning to Learn to be Right for the Right Reasons

no code implementations NAACL 2021 Pride Kavumba, Benjamin Heinzerling, Ana Brassard, Kentaro Inui

Here, we propose to explicitly learn a model that does well on both the easy test set with superficial cues and hard test set without superficial cues.

Meta-Learning

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

no code implementations16 Apr 2021 Keshav Singh, Paul Reisert, Naoya Inoue, Kentaro Inui

We construct a preliminary dataset of 6, 000 warrants annotated over 600 arguments for 3 debatable topics.

Natural Language Understanding

Pseudo Zero Pronoun Resolution Improves Zero Anaphora Resolution

1 code implementation EMNLP 2021 Ryuto Konno, Shun Kiyono, Yuichiroh Matsubayashi, Hiroki Ouchi, Kentaro Inui

Masked language models (MLMs) have contributed to drastic performance improvements with regard to zero anaphora resolution (ZAR).

Two Training Strategies for Improving Relation Extraction over Universal Graph

1 code implementation EACL 2021 Qin Dai, Naoya Inoue, Ryo Takahashi, Kentaro Inui

This paper explores how the Distantly Supervised Relation Extraction (DS-RE) can benefit from the use of a Universal Graph (UG), the combination of a Knowledge Graph (KG) and a large-scale text collection.

Relation Relation Extraction +1

Exploring Transitivity in Neural NLI Models through Veridicality

1 code implementation EACL 2021 Hitomi Yanaka, Koji Mineshima, Kentaro Inui

Despite the recent success of deep neural networks in natural language processing, the extent to which they can demonstrate human-like generalization capacities for natural language understanding remains unclear.

Natural Language Inference Natural Language Understanding

Efficient Estimation of Influence of a Training Instance

no code implementations EMNLP (sustainlp) 2020 Sosuke Kobayashi, Sho Yokoi, Jun Suzuki, Kentaro Inui

Understanding the influence of a training instance on a neural network model leads to improving interpretability.

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

no code implementations COLING 2020 Ryuto Konno, Yuichiroh Matsubayashi, Shun Kiyono, Hiroki Ouchi, Ryo Takahashi, Kentaro Inui

This study addresses two underexplored issues on CDA, that is, how to reduce the computational cost of data augmentation and how to ensure the quality of the generated data.

Data Augmentation Language Modeling +5

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

no code implementations13 Oct 2020 Farjana Sultana Mim, Naoya Inoue, Paul Reisert, Hiroki Ouchi, Kentaro Inui

Existing approaches for automated essay scoring and document representation learning typically rely on discourse parsers to incorporate discourse structure into text representation.

All Automated Essay Scoring +6

Langsmith: An Interactive Academic Text Revision System

no code implementations EMNLP 2020 Takumi Ito, Tatsuki Kuribayashi, Masatoshi Hidaka, Jun Suzuki, Kentaro Inui

Despite the current diversity and inclusion initiatives in the academic community, researchers with a non-native command of English still face significant obstacles when writing papers in English.

Diversity

Evaluation of Similarity-based Explanations

2 code implementations ICLR 2021 Kazuaki Hanawa, Sho Yokoi, Satoshi Hara, Kentaro Inui

In this study, we investigated relevance metrics that can provide reasonable explanations to users.

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

1 code implementation ACL 2020 Masahiro Kaneko, Masato Mita, Shun Kiyono, Jun Suzuki, Kentaro Inui

The answer to this question is not as straightforward as one might expect because the previous common methods for incorporating a MLM into an EncDec model have potential drawbacks when applied to GEC.

Decoder Grammatical Error Correction +2

Creating Corpora for Research in Feedback Comment Generation

no code implementations LREC 2020 Ryo Nagata, Kentaro Inui, Shin{'}ichiro Ishikawa

In this paper, we report on datasets that we created for research in feedback comment generation {---} a task of automatically generating feedback comments such as a hint or an explanatory note for writing learning.

Comment Generation

Word Rotator's Distance

1 code implementation EMNLP 2020 Sho Yokoi, Ryo Takahashi, Reina Akama, Jun Suzuki, Kentaro Inui

Accordingly, we propose a method that first decouples word vectors into their norm and direction, and then computes alignment-based similarity using earth mover's distance (i. e., optimal transport cost), which we refer to as word rotator's distance.

Semantic Similarity Semantic Textual Similarity +3

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

1 code implementation ACL 2020 Hitomi Yanaka, Koji Mineshima, Daisuke Bekki, Kentaro Inui

This indicates that the generalization ability of neural models is limited to cases where the syntactic structures are nearly the same as those in the training set.

Evaluating Dialogue Generation Systems via Response Selection

1 code implementation ACL 2020 Shiki Sato, Reina Akama, Hiroki Ouchi, Jun Suzuki, Kentaro Inui

Existing automatic evaluation metrics for open-domain dialogue response generation systems correlate poorly with human evaluation.

Dialogue Generation Response Generation

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

1 code implementation EMNLP 2020 Goro Kobayashi, Tatsuki Kuribayashi, Sho Yokoi, Kentaro Inui

Attention is a key component of Transformers, which have recently achieved considerable success in natural language processing.

Machine Translation Translation +1

Assessing the Benchmarking Capacity of Machine Reading Comprehension Datasets

no code implementations21 Nov 2019 Saku Sugawara, Pontus Stenetorp, Kentaro Inui, Akiko Aizawa

Existing analysis work in machine reading comprehension (MRC) is largely concerned with evaluating the capabilities of systems.

Benchmarking Machine Reading Comprehension +1

Inject Rubrics into Short Answer Grading System

no code implementations WS 2019 Tianqi Wang, Naoya Inoue, Hiroki Ouchi, Tomoya Mizumoto, Kentaro Inui

Most existing SAG systems predict scores based only on the answers, including the model used as base line in this paper, which gives the-state-of-the-art performance.

Improving Evidence Detection by Leveraging Warrants

no code implementations WS 2019 Keshav Singh, Paul Reisert, Naoya Inoue, Pride Kavumba, Kentaro Inui

Recognizing the implicit link between a claim and a piece of evidence (i. e. warrant) is the key to improving the performance of evidence detection.

R4C: A Benchmark for Evaluating RC Systems to Get the Right Answer for the Right Reason

no code implementations ACL 2020 Naoya Inoue, Pontus Stenetorp, Kentaro Inui

Recent studies have revealed that reading comprehension (RC) systems learn to exploit annotation artifacts and other biases in current datasets.

Multi-Hop Reading Comprehension

Riposte! A Large Corpus of Counter-Arguments

no code implementations8 Oct 2019 Paul Reisert, Benjamin Heinzerling, Naoya Inoue, Shun Kiyono, Kentaro Inui

Counter-arguments (CAs), one form of constructive feedback, have been proven to be useful for critical thinking skills.

An Empirical Study of Incorporating Pseudo Data into Grammatical Error Correction

1 code implementation IJCNLP 2019 Shun Kiyono, Jun Suzuki, Masato Mita, Tomoya Mizumoto, Kentaro Inui

The incorporation of pseudo data in the training of grammatical error correction models has been one of the main factors in improving the performance of such models.

Grammatical Error Correction

Analytic Score Prediction and Justification Identification in Automated Short Answer Scoring

no code implementations WS 2019 Tomoya Mizumoto, Hiroki Ouchi, Yoriko Isobe, Paul Reisert, Ryo Nagata, Satoshi Sekine, Kentaro Inui

This paper provides an analytical assessment of student short answer responses with a view to potential benefits in pedagogical contexts.

An Empirical Study of Span Representations in Argumentation Structure Parsing

no code implementations ACL 2019 Tatsuki Kuribayashi, Hiroki Ouchi, Naoya Inoue, Paul Reisert, Toshinori Miyoshi, Jun Suzuki, Kentaro Inui

For several natural language processing (NLP) tasks, span representation design is attracting considerable attention as a promising new technique; a common basis for an effective design has been established.

Can neural networks understand monotonicity reasoning?

1 code implementation WS 2019 Hitomi Yanaka, Koji Mineshima, Daisuke Bekki, Kentaro Inui, Satoshi Sekine, Lasha Abzianidze, Johan Bos

Monotonicity reasoning is one of the important reasoning skills for any intelligent natural language inference (NLI) model in that it requires the ability to capture the interaction between lexical and syntactic structures.

Data Augmentation Natural Language Inference

Subword-based Compact Reconstruction of Word Embeddings

1 code implementation NAACL 2019 Shota Sasaki, Jun Suzuki, Kentaro Inui

The idea of subword-based word embeddings has been proposed in the literature, mainly for solving the out-of-vocabulary (OOV) word problem observed in standard word-based word embeddings.

Word Embeddings

Annotating with Pros and Cons of Technologies in Computer Science Papers

1 code implementation WS 2019 Hono Shirai, Naoya Inoue, Jun Suzuki, Kentaro Inui

Specifically, we show how to adapt the targeted sentiment analysis task for pros/cons extraction in computer science papers and conduct an annotation study.

Sentiment Analysis

The Sally Smedley Hyperpartisan News Detector at SemEval-2019 Task 4

no code implementations SEMEVAL 2019 Kazuaki Hanawa, Shota Sasaki, Hiroki Ouchi, Jun Suzuki, Kentaro Inui

Our system achieved 80. 9{\%} accuracy on the test set for the formal run and got the 3rd place out of 42 teams.

A Large-Scale Multi-Length Headline Corpus for Analyzing Length-Constrained Headline Generation Model Evaluation

no code implementations WS 2019 Yuta Hitomi, Yuya Taguchi, Hideaki Tamori, Ko Kikuta, Jiro Nishitoba, Naoaki Okazaki, Kentaro Inui, Manabu Okumura

However, because there is no corpus of headlines of multiple lengths for a given article, previous research on controlling output length in headline generation has not discussed whether the system outputs could be adequately evaluated without multiple references of different lengths.

Articles Headline Generation

Feasible Annotation Scheme for Capturing Policy Argument Reasoning using Argument Templates

1 code implementation WS 2018 Paul Reisert, Naoya Inoue, Tatsuki Kuribayashi, Kentaro Inui

Most of the existing works on argument mining cast the problem of argumentative structure identification as classification tasks (e. g. attack-support relations, stance, explicit premise/claim).

Argument Mining Document Summarization +2

Mixture of Expert/Imitator Networks: Scalable Semi-supervised Learning Framework

no code implementations13 Oct 2018 Shun Kiyono, Jun Suzuki, Kentaro Inui

We also demonstrate that our method has the more data, better performance property with promising scalability to the amount of unlabeled data.

General Classification text-classification +1

Pointwise HSIC: A Linear-Time Kernelized Co-occurrence Norm for Sparse Linguistic Expressions

no code implementations EMNLP 2018 Sho Yokoi, Sosuke Kobayashi, Kenji Fukumizu, Jun Suzuki, Kentaro Inui

As well as deriving PMI from mutual information, we derive this new measure from the Hilbert--Schmidt independence criterion (HSIC); thus, we call the new measure the pointwise HSIC (PHSIC).

Machine Translation Sentence +2

What Makes Reading Comprehension Questions Easier?

1 code implementation EMNLP 2018 Saku Sugawara, Kentaro Inui, Satoshi Sekine, Akiko Aizawa

From this study, we observed that (i) the baseline performances for the hard subsets remarkably degrade compared to those of entire datasets, (ii) hard questions require knowledge inference and multiple-sentence reasoning in comparison with easy questions, and (iii) multiple-choice questions tend to require a broader range of reasoning skills than answer extraction and description questions.

Machine Reading Comprehension Multiple-choice +1

Predicting Stances from Social Media Posts using Factorization Machines

no code implementations COLING 2018 Akira Sasaki, Kazuaki Hanawa, Naoaki Okazaki, Kentaro Inui

This paper presents an approach to detect the stance of a user toward a topic based on their stances toward other topics and the social media posts of the user.

Decision Making Stance Detection

Distance-Free Modeling of Multi-Predicate Interactions in End-to-End Japanese Predicate-Argument Structure Analysis

no code implementations COLING 2018 Yuichiroh Matsubayashi, Kentaro Inui

Capturing interactions among multiple predicate-argument structures (PASs) is a crucial issue in the task of analyzing PAS in Japanese.

Cross-Lingual Learning-to-Rank with Shared Representations

no code implementations NAACL 2018 Shota Sasaki, Shuo Sun, Shigehiko Schamoni, Kevin Duh, Kentaro Inui

Cross-lingual information retrieval (CLIR) is a document retrieval task where the documents are written in a language different from that of the user{'}s query.

Cross-Lingual Information Retrieval Learning-To-Rank +2

Unsupervised Learning of Style-sensitive Word Vectors

no code implementations ACL 2018 Reina Akama, Kento Watanabe, Sho Yokoi, Sosuke Kobayashi, Kentaro Inui

This paper presents the first study aimed at capturing stylistic similarity between words in an unsupervised manner.

Word Embeddings

A Corpus of Deep Argumentative Structures as an Explanation to Argumentative Relations

no code implementations7 Dec 2017 Paul Reisert, Naoya Inoue, Naoaki Okazaki, Kentaro Inui

Our coverage result of 74. 6% indicates that argumentative relations can reasonably be explained by our small pattern set.

Reference-based Metrics can be Replaced with Reference-less Metrics in Evaluating Grammatical Error Correction Systems

no code implementations IJCNLP 2017 Hiroki Asano, Tomoya Mizumoto, Kentaro Inui

In grammatical error correction (GEC), automatically evaluating system outputs requires gold-standard references, which must be created manually and thus tend to be both expensive and limited in coverage.

Grammatical Error Correction Machine Translation

Revisiting the Design Issues of Local Models for Japanese Predicate-Argument Structure Analysis

no code implementations IJCNLP 2017 Yuichiroh Matsubayashi, Kentaro Inui

The research trend in Japanese predicate-argument structure (PAS) analysis is shifting from pointwise prediction models with local features to global models designed to search for globally optimal solutions.

A Neural Language Model for Dynamically Representing the Meanings of Unknown Words and Entities in a Discourse

1 code implementation IJCNLP 2017 Sosuke Kobayashi, Naoaki Okazaki, Kentaro Inui

This study addresses the problem of identifying the meaning of unknown words or entities in a discourse with respect to the word embedding approaches used in neural language models.

Language Modeling Language Modelling +1

Analyzing the Revision Logs of a Japanese Newspaper for Article Quality Assessment

no code implementations WS 2017 Hideaki Tamori, Yuta Hitomi, Naoaki Okazaki, Kentaro Inui

We address the issue of the quality of journalism and analyze daily article revision logs from a Japanese newspaper company.

Composing Distributed Representations of Relational Patterns

1 code implementation ACL 2016 Sho Takase, Naoaki Okazaki, Kentaro Inui

Learning distributed representations for relation instances is a central technique in downstream NLP applications.

General Classification Relation +1

Other Topics You May Also Agree or Disagree: Modeling Inter-Topic Preferences using Tweets and Matrix Factorization

no code implementations ACL 2017 Akira Sasaki, Kazuaki Hanawa, Naoaki Okazaki, Kentaro Inui

We present in this paper our approach for modeling inter-topic preferences of Twitter users: for example, those who agree with the Trans-Pacific Partnership (TPP) also agree with free trade.

Stance Detection

Modeling Context-sensitive Selectional Preference with Distributed Representations

no code implementations COLING 2016 Naoya Inoue, Yuichiroh Matsubayashi, Masayuki Ono, Naoaki Okazaki, Kentaro Inui

This paper proposes a novel problem setting of selectional preference (SP) between a predicate and its arguments, called as context-sensitive SP (CSP).

Semantic Role Labeling

Question-Answering with Logic Specific to Video Games

no code implementations LREC 2016 Corentin Dumont, Ran Tian, Kentaro Inui

We chose a popular game called {`}Minecraft{'}, and created a QA corpus with a knowledge database related to this game and the ontology of a meaning representation that will be used to structure this database.

Clustering Minecraft +1

An Attentive Neural Architecture for Fine-grained Entity Type Classification

no code implementations WS 2016 Sonse Shimaoka, Pontus Stenetorp, Kentaro Inui, Sebastian Riedel

In this work we propose a novel attention-based neural network model for the task of fine-grained entity type classification that unlike previously proposed models recursively composes representations of entity mention contexts.

Classification General Classification +1

The Mechanism of Additive Composition

no code implementations26 Nov 2015 Ran Tian, Naoaki Okazaki, Kentaro Inui

Additive composition (Foltz et al, 1998; Landauer and Dumais, 1997; Mitchell and Lapata, 2010) is a widely used method for computing meanings of phrases, which takes the average of vector representations of the constituent words.

Cannot find the paper you are looking for? You can Submit a new open access paper.