Papers by Ryuichiro Higashinaka

20 papers
Generating Responses that Reflect Meta Information in User-Generated Question Answer Pairs (2020.lrec-1)

Copied to clipboard

Challenge: Existing approaches to realize consistent personalities require expensive data collection.
Approach: They propose to collect question-answer pairs for particular characters from online users . meta information such as emotion and intimacy was also collected .
Outcome: The proposed method can be used to train neural conversational models with high quality questions and meta information.
Optimal Summaries for Enabling a Smooth Handover in Chat-Oriented Dialogue (2022.aacl-srw)

Copied to clipboard

Challenge: In dialogue systems, it is difficult to provide fully autonomous dialogue . to ensure a good dialogue experience, human operators sometimes need to intervene .
Approach: They conducted large-scale experiments on chat dialogues to determine which type of summary is most useful for handover . abstractive summary plus one utterance immediately before handover and extractive summary consisting of five utterrances immediately before the handover were found to be the most useful .
Outcome: The best summaries were abstractive summary plus one utterance before handover and extractive summary consisting of five utterrances before hand over.
Dialogue Collection for Recording the Process of Building Common Ground in a Collaborative Task (2022.lrec-1)

Copied to clipboard

Challenge: Existing studies on the process of building common ground have not been well conducted.
Approach: They propose a method for recording the process of building common ground through a dialogue by using the intermediate result of a task.
Outcome: The proposed method can record the building common ground process by using the intermediate result of a task and can be estimated quite accurately.
Creating Large-Scale Argumentation Structures for Dialogue Systems (L18-1)

Copied to clipboard

Challenge: Argumentation is a process of reaching consensus through premises and rebuttals and is important for making decisions and exchanging views.
Approach: They propose to create argumentation structures in ten languages using argumentation databases . they also examine differences between the two languages to determine their effectiveness .
Outcome: The proposed arguments can be applied to argumentative dialogue systems and can be used as training data.
Data Collection for Empirically Determining the Necessary Information for Smooth Handover in Dialogue (2022.lrec-1)

Copied to clipboard

Challenge: Despite advances in deep learning, dialogue systems struggle to achieve fully autonomous transactions with users.
Approach: They conducted an experiment in which two operators switched periodically while performing chat, consultation, and sales tasks in dialogue.
Outcome: The results show that adjacency pairs are useful for recording conversation history . key-value pairs are also useful when there are underlying tasks, such as consultation and sales .
Analysis of Dialogue in Human-Human Collaboration in Minecraft (2022.lrec-1)

Copied to clipboard

Challenge: Recent studies have focused on developing dialogue systems that enable collaborative work, but few studies have centered on creative collaborative work.
Approach: They collected 500 dialogues of human-human collaboration in Minecraft as a basis for developing a dialogue system that enables creative collaborative work.
Outcome: The proposed system can be used to create a collaborative garden in Minecraft and collect text chats, action logs, and subjective evaluations.
I Remember You!: SUI Corpus for Remembering and Utilizing Users’ Information in Chat-oriented Dialogue Systems (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods for remembering and utilizing information on users in system utterances do not always fit the context of the dialogue.
Approach: They propose to use user information to fill in utterance templates but the utterrances do not always fit the context.
Outcome: The proposed system can remember and utilize user information on users in dialogues while keeping appropriateness for the context.
Investigating person-specific errors in chat-oriented dialogue systems (2022.acl-short)

Copied to clipboard

Challenge: Errors in general chatbots and chatbot that follow a rough persona have been studied . but those in chatbot based on real people have not been thoroughly investigated .
Approach: They analyze dialogue data of a generation-based chatbot trained from dialogue data . they find errors in attributes and relations can be divided into two levels: self and other .
Outcome: The results show that errors in chatbots can be divided into two types . the correspondence with an existing taxonomy of errors was also investigated .
Predicting Nods by using Dialogue Acts in Dialogue (L18-1)

Copied to clipboard

Challenge: Existing studies have generated nods from the final morphemes at the end of an utterance.
Approach: They propose to generate head nods from Japanese dialogues using morphemes . they compile a corpus of 24 dialogues including utterance and nod information .
Outcome: The proposed model outperforms a model using morpheme information in the Japanese language and shows that dialog acts can predict nods.
Combining Argumentation Structure and Language Model for Generating Natural Argumentative Dialogue (2022.aacl-short)

Copied to clipboard

Challenge: Argumentative dialogue is important process where speakers discuss a specific theme for consensus building or decision making.
Approach: They propose a method to generate argumentative dialogues by combining argumentation structure and language model.
Outcome: The proposed method significantly improves the naturalness of arguments without losing consistency.
Collection and Analysis of Travel Agency Task Dialogues with Age-Diverse Speakers (2022.lrec-1)

Copied to clipboard

Challenge: Using deep neural networks, task-oriented dialogue systems can be used to generate an appropriate response to users' inputs.
Approach: They collected a multimodal dialogue corpus with a wide range of speaker ages and set up a dialogue task based on travel . results suggest adult speakers have more independent opinions, older speakers express opinions more frequently compared with other age groups, and operators expressed a smile more frequently to minor speakers.
Outcome: The results show that adult speakers have more independent opinions, the older speakers express their opinions more frequently compared with other age groups, and the operators expressed a smile more frequently to the minor speakers.
Enhancing Task-oriented Dialogue Systems with Generative Post-processing Networks (2023.emnlp-main)

Copied to clipboard

Challenge: Recent work proposes a method to optimize pipelined dialogue systems by fine-tuning modules directly.
Approach: They propose a new post-processing component for natural language generation (NLG) they use dialogue act contribution to evaluate contribution of GenPPN-generated utterances .
Outcome: The proposed method improves the performance of task-oriented dialogue systems by modifying arbitrary modules including non-differentiable ones.
Investigating the Impact of Incremental Processing and Voice Activity Projection on Spoken Dialogue Systems (2025.coling-main)

Copied to clipboard

Challenge: a large language model (LLM) is gaining attention for its ability to model human-like turn-taking in human conversations.
Approach: They developed a turn-taking model that can be trained in unsupervised manner using spoken dialogue data between two speakers.
Outcome: The proposed model can be trained in unsupervised manner using spoken dialogue data between two speakers.
JMultiWOZ: A Large-Scale Japanese Multi-Domain Task-Oriented Dialogue Dataset (2024.lrec-main)

Copied to clipboard

Challenge: Existing datasets for task-oriented dialogue systems in English are limited compared to Japanese.
Approach: They evaluated the dialogue state tracking and response generation capabilities of Japanese language datasets using multi-domain task-oriented dialogues.
Outcome: The proposed dataset provides a benchmark that is on par with MultiWOZ2.2 and the latest large language model (LLM)-based methods.
Adaptive Natural Language Generation for Task-oriented Dialogue via Reinforcement Learning (2022.coling-1)

Copied to clipboard

Challenge: In task-oriented dialogue systems, the role of the natural language generation component is to convert a system's intentions, called dialogue acts (DAs), into natural language utterances and to convey DAs accurately to users.
Approach: They propose a method for Adaptive Natural language generation for Task-Oriented dialogue via Reinforcement learning that incorporates a natural language understanding module into the objective function of RL.
Outcome: The proposed method generates adaptive utterances against speech recognition errors and the different vocabulary levels of users in a multi-world task-oriented dialogue system.
Dialogue Corpus Construction Considering Modality and Social Relationships in Building Common Ground (2022.lrec-1)

Copied to clipboard

Challenge: Several studies have examined the process of building common ground in text chat, but none have investigated the process in depth.
Approach: They constructed a dialogue corpus to investigate the process of building common ground with a particular focus on the modality of dialogue and the social relationship between workers.
Outcome: The results suggest that adding the modality or developing the relationship between workers speeds up the building of common ground.
A Speculative and Tentative Common Ground Handling for Efficient Composition of Uncertain Dialogue (2022.lrec-1)

Copied to clipboard

Challenge: a study explores how the grounding process is composed and adapts to human cognitive processes . common ground is a set of information shared among participants that serves as a precondition for understanding individual utterances .
Approach: a study investigates how the grounding process is composed by participants . it suggests that common ground may not necessarily be formed bottom-up through analytic expressions .
Outcome: a new approach to human-like dialogue may be more suitable for natural human communication, the authors say . they show that common ground is mutually accepted among participants through holistic expressions .
Multi-task and Multi-lingual Joint Learning of Neural Lexical Utterance Classification based on Partially-shared Modeling (C18-1)

Copied to clipboard

Challenge: Existing studies on multitask and multilingual joint learning focus on cross-task or cross-lingual knowledge transfer.
Approach: They propose to divide state-of-the-art neural lexical utterance classification into language-specific components that can be shared between different tasks and different languages.
Outcome: The proposed method is able to support multi-task and multi-lingual learning using Japanese and English data sets with three different lexical utterance classification tasks.
Collecting and Analyzing Dialogues in a Tagline Co-Writing Task (2024.lrec-main)

Copied to clipboard

Challenge: Currently, most studies on dialogue systems focus on problemsolving dialogues and relatively little research has been done on systems that can engage in creative collaboration with users.
Approach: They designed a tagline co-writing task in which two people collaborate to create taglines via text chat and collected dialogue logs, editing logs and questionnaire results.
Outcome: The proposed task involved a tagline co-writing task in which two people collaborate to create taglines via text chat, and collected dialogue logs, editing logs and questionnaire results.
Adversarial Training for Multi-task and Multi-lingual Joint Modeling of Utterance Intent Classification (D18-1)

Copied to clipboard

Challenge: In multi-task and multi-lingual joint modeling, common knowledge can be efficiently utilized among multiple tasks or multiple languages.
Approach: They propose to introduce language-specific adversarial networks and task-specific language adversarials to purge the task or language dependencies of shared networks.
Outcome: The proposed method is demonstrated using Japanese and English data sets for three different utterance intent classification tasks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations