Papers by Junya Takayama

6 papers
Text Classification with Negative Supervision (2020.acl-main)

Copied to clipboard

Challenge: Existing models for text representations have shown state-of-the-art performance on text classification tasks, however, the discrepancy between semantic similarity of texts and labelling standards affects classifiers.
Approach: They propose a simple multitask learning model that uses negative supervision to generate distinct representations for texts with different labels.
Outcome: The proposed model outperforms state-of-the-art models on classification tasks in three different languages.
Persona-Consistent Dialogue Generation via Pseudo Preference Tuning (2025.coling-main)

Copied to clipboard

Challenge: Existing methods for improving persona consistency in dialogues require external resources.
Approach: They propose a method for enhancing persona consistency in dialogue response generation using direct preference optimization using persona data.
Outcome: The proposed method produces more consistent and natural responses than previous methods.
DIRECT: Direct and Indirect Responses in Conversational Text Corpus (2021.findings-emnlp)

Copied to clipboard

Challenge: Neural conversation models have been able to generate fluent responses through training on a dialogue corpus, but they lack the ability to reveal the implied intentions of users.
Approach: They propose to train neural conversation models on a dialogue corpus that provides pragmatic paraphrases to advance techniques for natural language understanding in dialogue systems.
Outcome: The proposed corpus provides 71,498 pairs of indirect–direct utterance pairs accompanied by a multi-turn dialogue history extracted from the MultiWoZ dataset.
Dialogue-Act Prediction of Future Responses Based on Conversation History (P19-2)

Copied to clipboard

Challenge: Sequence-to-sequence models are a common approach to develop chatbots, but they are prone to a black-box response generation process.
Approach: They propose a method to predict a DA of the next response based on the history of previous utterances and their DAs.
Outcome: The proposed model achieves 10.8% higher F1-score and 3.0% higher accuracy on DA prediction compared to baseline using only a single utterance .
Distinct Label Representations for Few-Shot Text Classification (2021.acl-short)

Copied to clipboard

Challenge: Existing methods for few-shot text classification ignore the semantic relevance of labels and are difficult to train because of the lack of training examples.
Approach: They propose a method that generates distinct label representations that embed information specific to each label.
Outcome: The proposed method significantly improves few-shot text classification across models and datasets.
Consistent Response Generation with Controlled Specificity (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to generate fluent responses generate inconsistent responses . we use a sequence-to-sequence model to generate specific responses based on a co-occurrence degree .
Approach: They propose a method to control the specificity of responses while maintaining the consistency with the utterances.
Outcome: The proposed method produces highly consistent responses in open-domain dialogues . it can generate fluent responses while maintaining the consistency with the utterances compared to the conventional model .

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