Papers by Nobuhiro Kaji

4 papers
Conversation Initiation by Diverse News Contents Introduction (N19-1)

Copied to clipboard

Challenge: Existing conversation systems assume that the user always initiates conversation and focus on how to respond to the given user’s utterance.
Approach: They propose to generate initial utterance by summarizing and chatting about news articles to avoid boredom by relying on boilerplate utterrances like greetings.
Outcome: The proposed model outperforms baseline models and based on information retrieval based and generation based models.
Lattice Path Edit Distance: A Romanization-aware Edit Distance for Extracting Misspelling-Correction Pairs from Japanese Search Query Logs (2023.emnlp-industry)

Copied to clipboard

Challenge: Existing methods to extract misspelling-correction pairs from Japanese query logs are not effective due to the unique input methods.
Approach: They propose a romanization-aware edit distance that utilizes romanization lattices to efficiently consider all possible romanized forms of input strings.
Outcome: Empirical results show lattice path edit distance outperforms standard edit distance in Japanese . latticae path editing distance outpersforms existing methods even with romanization .
Search Query Embeddings via User-behavior-driven Contrastive Learning (2025.naacl-industry)

Copied to clipboard

Challenge: Existing approaches to embed search queries are limited due to shortness and surface-level variations.
Approach: They propose a user-behavior-driven contrastive learning approach which directly aligns query embeddings according to user intent.
Outcome: The proposed model outperforms state-of-the-art text embedding models on real-world QU tasks while minimizing lexical similarities.
Just One is Enough: An Existence-based Alignment Check for Robust Japanese Pronunciation Estimation (2025.emnlp-industry)

Copied to clipboard

Challenge: Existence-based alignment has been used to detect pronunciation errors in Japanese NLP, but finding reliable attention heads remains challenging.
Approach: They propose a method that detects and corrects pronunciation errors in Japanese by using beam search.
Outcome: The proposed method reduces hallucinations and omissions and improves pronunciation estimation by over 2.5%.

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