Papers by Gaku Morio
Disentangling the Effects of Unlearning in Measuring Parametric Faithfulness of Chain-of-Thought (2026.acl-srw)
Copied to clipboard
Ryo Mitsuhashi, Gaku Morio, Ayana Niwa, Masahiro Kaneko, Kentaro Inui, Terufumi Morishita, Yuta Koreeda, Yasuhiro Sogawa
| Challenge: | Chain-of-Thought (CoT) has been debated as a model's faithfulness to internal reasoning process. |
| Approach: | They propose to use unlearning to measure parametric faithfulness of models by adjusting for unintended artifacts of unlearning. |
| Outcome: | The proposed metric accounts for the unintended artifacts of unlearning and shows that it is non-negligible. |
How does the task complexity of masked pretraining objectives affect downstream performance? (2023.findings-acl)
Copied to clipboard
| Challenge: | Masked language modeling (MLM) is a widely used self-supervised pretraining objective. |
| Approach: | They propose to use a mask-based objective to predict a token that is replaced with a masked token given its context. |
| Outcome: | The proposed objectives show that they should have half the complexity needed to perform comparably to MLM. |
JFLD: A Japanese Benchmark for Deductive Reasoning Based on Formal Logic (2024.lrec-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have proficiently solved a broad range of tasks with their rich knowledge but struggle with logical reasoning. |
| Approach: | They propose a deductive reasoning benchmark for Japanese that assesses logical reasoning abilities isolated from knowledge and various reasoning rules. |
| Outcome: | The proposed benchmarks assess whether LLMs can generate logical steps to (dis)prove a given hypothesis based on a set of facts. |
Towards Better Non-Tree Argument Mining: Proposition-Level Biaffine Parsing with Task-Specific Parameterization (2020.acl-main)
Copied to clipboard
| Challenge: | Argument mining studies have advanced the ability to predict argument structures, but the technology for capturing non-tree-structured arguments is still in its infancy. |
| Approach: | They propose a neural model that can predict proposition types and edges between propositions. |
| Outcome: | The proposed model improves edge prediction performance compared to baseline models. |
Predicting Narratives of Climate Obstruction in Social Media Advertising (2024.findings-acl)
Copied to clipboard
| Challenge: | Social media advertising allows entities to construct narratives that align with their commercial interests and sway public perception. |
| Approach: | They propose to classify climate-related narratives into seven categories based on existing definitions and data. |
| Outcome: | The proposed method outperforms other methods and can reduce human annotation costs. |
End-to-end Argument Mining with Cross-corpora Multi-task Learning (2022.tacl-1)
Copied to clipboard
| Challenge: | Argument(ation) mining is a task of identifying argument structure from text . lack of training data makes it difficult to train models based on limited data sets. |
| Approach: | They propose an end-to-end cross-corpus argument mining method that uses auxiliary argument mining corpora to train models. |
| Outcome: | The proposed method outperforms models trained on a single corpus on arguments on arguments in argument mining tasks. |
Project-then-Transfer: Effective Two-stage Cross-lingual Transfer for Semantic Dependency Parsing (2021.eacl-main)
Copied to clipboard
| Challenge: | Several remarkable contributions have been made in syntactic dependency parsing, especially on universal dependencies. |
| Approach: | They propose to capture cross-linguality by combing annotation projection and model transfer of pre-trained language models. |
| Outcome: | The proposed model parser almost achieved the approximated upper bound. |
Corpus for Modeling User Interactions in Online Persuasive Discussions (2020.lrec-1)
Copied to clipboard
| Challenge: | Several studies have focused on the identification and classification of argumentative components and the argumentative relations between the components. |
| Approach: | They propose an annotation scheme and corpus that captures user-generated inner-post arguments and inter-post relations between users in ChangeMyView. |
| Outcome: | The proposed annotation scheme captures user-generated inner-post arguments and inter-post relations in ChangeMyView, a persuasive forum. |
Annotating and Analyzing Semantic Role of Elementary Units and Relations in Online Persuasive Arguments (P19-2)
Copied to clipboard
| Challenge: | Existing studies on the features of persuasiveness focus on lexical features and argumentative features. |
| Approach: | They propose an annotation scheme that captures the semantic role of arguments in a popular online persuasion forum, ChangeMyView. |
| Outcome: | The proposed scheme captures the semantic role of arguments in a popular online persuasion forum, so-called ChangeMyView. |
Revealing and Predicting Online Persuasion Strategy with Elementary Units (D19-1)
Copied to clipboard
| Challenge: | Existing studies have examined persuasive discourses with regard to dynamics or lexical features. |
| Approach: | They propose to annotate five types of EUs in a persuasive forum and propose a baseline neural model that identifies the EU boundary and type. |
| Outcome: | The proposed model reveals that EUs definitively characterize online persuasive strategies. |