Papers by Koichiro Yoshino
Teaching Text Agents to Learn Sequential Decision Making from Failure (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods to improve text-based reinforcement-learning agents' performance contain failed actions that reinforce incorrect behaviors and reduce task success rates. |
| Approach: | They propose a failed action-aware objective that suppresses negative impact of failed actions . they propose 'failed action-based' perturbation method that leverages unsuccessful trajectories to construct new successful ones . |
| Outcome: | The proposed method outperforms baselines and generalizes across environments. |
J-CRe3: A Japanese Conversation Dataset for Real-world Reference Resolution (2024.lrec-main)
Copied to clipboard
Nobuhiro Ueda, Hideko Habe, Akishige Yuguchi, Seiya Kawano, Yasutomo Kawanishi, Sadao Kurohashi, Koichiro Yoshino
| Challenge: | Existing studies have ground referential expressions in language to real-world objects for cooperative action generation. |
| Approach: | They propose a Japanese Conversation dataset for real-world reference resolution that ground referential expressions to visual information observed in egocentric views. |
| Outcome: | The proposed dataset contains egocentric video and dialogue audio of real-world conversations between two people acting as a master and assistant robot at home. |
Proactive User Information Acquisition via Chats on User-Favored Topics (2025.findings-emnlp)
Copied to clipboard
| Challenge: | PIA tasks require a system to acquire user information without making the user feel abrupt while engaging in a chat on a predefined topic. |
| Approach: | They propose a task to acquire user's answers to predefined questions without making the user feel abrupt while engaging in a chat on a predefined topic. |
| Outcome: | The proposed system outperforms LLMs prompted with task instructions in a dataset of 650 PIA chats and shows that it is reasonably accurate. |
Japanese Dialogue Corpus of Information Navigation and Attentive Listening Annotated with Extended ISO-24617-2 Dialogue Act Tags (L18-1)
Copied to clipboard
| Challenge: | Large-scale conventional dialogue corpora are mainly built for specified tasks with specially designed dialogue states. |
| Approach: | They propose to annotate large-scale dialogue data with an extended ISO-24617-2 dialogue act tag-set to model a natural conversation with machines. |
| Outcome: | The proposed corpus covers a wider range of dialogue tasks than existing task-oriented systems or text-chat systems. |
A Gaze-grounded Visual Question Answering Dataset for Clarifying Ambiguous Japanese Questions (2024.lrec-main)
Copied to clipboard
| Challenge: | Visual question answering (VQA) tasks are often based on directives, which can cause ambiguities in human utterances. |
| Approach: | They propose a method that clarifies ambiguous questions using gaze information . they propose combining gaze information with gaze information to improve accuracy . |
| Outcome: | The proposed method improves performance in some cases of a GazeVQA system on Gaze. |
Disambiguating Reference in Visually Grounded Dialogues through Joint Modeling of Textual and Multimodal Semantic Structures (2025.acl-long)
Copied to clipboard
| Challenge: | incorporating textual and multimodal reference resolution improves performance in visual-based reference resolution . Phrase grounding is a well-established task for understanding semantic relations between mentions and objects . ambiguities caused by pronouns and ellipses can arise in visually grounded dialogues . |
| Approach: | They propose a framework that unifies textual and multimodal reference resolution by mapping mention embeddings to object embeddements and selecting mentions or objects based on their similarity. |
| Outcome: | The proposed framework performs better in phrase grounding than other models for this task. |
Emotional Speech Corpus for Persuasive Dialogue System (2020.lrec-1)
Copied to clipboard
| Challenge: | Emotional expressions can be used to express the speaker’s emotion more directly than using only emotion expression in the text. |
| Approach: | They built a speech dialogue corpus in a persuasive scenario that uses emotional expressions to build a system with emotional expression. |
| Outcome: | The proposed system can express the speaker's emotion more directly than using only emotion expression in the text, and the results show that the collected emotional expressions with their speeches have higher emotional expressiveness for expressing the system's emotions to users. |
Dialogue Scenario Collection of Persuasive Dialogue with Emotional Expressions via Crowdsourcing (L18-1)
Copied to clipboard
| Challenge: | Existing methods for data collection and annotation are costly and prevent launching new dialogue systems. |
| Approach: | They asked crowd workers to create persuasive dialogue systems using emotional expressions . they annotated emotional states and users' acceptance for system persuasion . |
| Outcome: | The proposed system has sufficient agreement even without training, the researchers found . the experiment showed that the collected data are comparable to real-world dialogue recording methods . |
Improving Spoken Language Understanding by Wisdom of Crowds (2020.coling-main)
Copied to clipboard
| Challenge: | Existing systems that use statistical approaches to improve spoken language understanding (SLU) lack of training data is an important problem, especially for new system tasks. |
| Approach: | They propose to use crowdsourcing and knowledge community websites to augment the spoken language understanding system by collecting paraphrasing variations for new system tasks and augmented them using similar questions from a knowledge community website. |
| Outcome: | The proposed architecture augmented more than 120,000 samples to improve accuracies even with small seed data. |
Reflection-based Word Attribute Transfer (2020.acl-srw)
Copied to clipboard
| Challenge: | Existing word embeddings represent analogic relations to change attributes, such as gender, such that king is male. |
| Approach: | They propose a method for word attribute transfer based on reflection mappings without such an analogy operation. |
| Outcome: | The proposed method can transfer attributes of the given words without changing the words that do not have the target attributes. |
Analysis of Style-Shifting on Social Media: Using Neural Language Model Conditioned by Social Meanings (2023.findings-emnlp)
Copied to clipboard
Seiya Kawano, Shota Kanezaki, Angel Fernando Garcia Contreras, Akishige Yuguchi, Marie Katsurai, Koichiro Yoshino
| Challenge: | Using a personalized neural language model, we predict an individual’s conversational style based on surprisals predicted by a personal neural language modeling model. |
| Approach: | They propose a personalized neural language model that predicts changes in an individual’s conversational style based on surprisals predicted by a neural language modeling model. |
| Outcome: | The proposed model outperforms existing models in predicting conversational style-shifting in a test set and shows correlations between it and various conversation factors as well as human evaluation of style- shifting. |