Papers by Noriki Nishida

14 papers
Neural Networks in a Product of Hyperbolic Spaces (2022.naacl-srw)

Copied to clipboard

Challenge: Recent advances in the use of hyperbolic spaces have been reported in natural language processing and graph embedding.
Approach: They propose to extend hyperbolic neural networks to a product of hyperbolical spaces by using a single hyperbolically spaced hyperbole.
Outcome: The proposed method improves graph node classification accuracy on tree-like datasets.
RNSum: A Large-Scale Dataset for Automatic Release Note Generation via Commit Logs Summarization (2022.acl-long)

Copied to clipboard

Challenge: a release note is a technical document that describes the latest changes to a software product.
Approach: They propose to extract and then abstract release notes from GitHub repositories using a transformer-based network like BART.
Outcome: The proposed methods generate less noisy release notes at higher coverage than baselines.
Do Multimodal Large Language Models Truly See What We Point At? Investigating Indexical, Iconic, and Symbolic Gesture Comprehension (2025.acl-short)

Copied to clipboard

Challenge: In recent years, multimodal large language models (MLLMs) excel at integrating textual, auditory, and visual information, but their ability to accurately interpret gestures remains underexplored.
Approach: They annotated five gesture type labels to 925 gesture instances from the Miraikan SC Corpus and analyzed gesture descriptions generated by state-of-the-art MLLMs, including GPT-4o.
Outcome: The proposed models lack real-world referential understanding and are inconsistent in interpreting indexical gestures.
Recent Trends in Personalized Dialogue Generation: A Review of Datasets, Methodologies, and Evaluations (2024.lrec-main)

Copied to clipboard

Challenge: Personalization is a multifaceted process that requires multiple definitions and varies between individuals.
Approach: They propose to systemically survey the recent landscape of personalized dialogue generation including the datasets employed, methodologies developed, and evaluation metrics applied.
Outcome: The proposed model can generate fluent and coherent responses to human queries in a language-based conversational agent.
Dissecting GraphRAG: A Modular Analysis of Knowledge Structuring for Factoid Question Answering (2026.tacl-1)

Copied to clipboard

Challenge: GraphRAG integrates structured knowledge graphs into question answering . high-quality triple extraction is critical, but lacks granularity and topical coherence . large language models suffer from inherent limitations in their internalized knowledge .
Approach: They evaluate module-level design choices in GraphRAG for retrieval-augmented generation . they find that triple extraction is critical for accurate and comprehensive retrieval .
Outcome: The proposed framework outperforms other retrieval-augmented generation frameworks in accuracy and efficiency.
Zero-Shot Entailment Learning for Ontology-Based Biomedical Annotation Without Explicit Mentions (2025.coling-main)

Copied to clipboard

Challenge: Automated biomedical annotation presents significant challenges when entities are not explicitly mentioned in the text.
Approach: They propose an entailment-based zero-shot text classification approach to annotate biomedical text passages using the Homeostasis Imbalance Process (HOIP) ontology.
Outcome: The proposed method performs well when processes are not explicitly mentioned . it is time-consuming and expensive to annotate biomedical texts with a specific ontology .
MA-COIR: Leveraging Semantic Search Index and Generative Models for Ontology-Driven Biomedical Concept Recognition (2025.acl-srw)

Copied to clipboard

Challenge: Existing concepts recognition methods that rely on explicit mention identification fail to capture complex concepts not explicitly stated in the text.
Approach: They propose a framework that reformulates concept recognition as an indexing-recognition task.
Outcome: The proposed framework reduces computational requirements and improves recognition efficiency in low-resource settings.
Out-of-Domain Discourse Dependency Parsing via Bootstrapping: An Empirical Analysis on Its Effectiveness and Limitation (2022.tacl-1)

Copied to clipboard

Challenge: Discourse parsing accuracy degrades significantly on out-of-domain text.
Approach: They propose to use bootstrapping methods to adapt modern discourse dependency parsers to out-of-domain text without additional human supervision.
Outcome: The proposed methods are significantly and consistently effective for unsupervised domain adaptation of discourse dependency parsing, but the low coverage of accurately predicted pseudo labels is a bottleneck for further improvement.
Applicability Condition Extraction for Therapeutic Drug-Disease Relations (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for identifying conditions under which a drug can be effective are limited . et al., j. n. d., al. c., and dr. m. s., 2005, are not able to identify context-specific conditions for therapeutic drug–disease relations.
Approach: They propose to annotate triples of drugs, diseases, and applicability conditions from biomedical literature.
Outcome: The proposed method outperforms baselines across evaluation settings.
Unsupervised Discourse Constituency Parsing Using Viterbi EM (2020.tacl-1)

Copied to clipboard

Challenge: Existing studies on unsupervised discourse parsing have shown that it is expensive, time-consuming, and sometimes highly ambiguous.
Approach: They propose an unsupervised parsing algorithm using Viterbi EM with a margin-based criterion and initialization methods for Viterbia training of discourse constituents based on prior knowledge of text structures.
Outcome: The proposed method outperforms fully supervised parsers in terms of performance and learning of discourse constituents.
J-Shuwa: A Large-Scale Web-Collected Japanese Sign Language-Japanese Parallel Corpus (2026.findings-acl)

Copied to clipboard

Challenge: Japanese Sign Language (JSL) is a low-resource sign language that has received limited attention in the AI community due to the lack of large-scale, publicly available parallel corpora.
Approach: They propose a large-scale JSL-Japanese parallel corpus constructed from YouTube videos with hard-coded subtitles and closed captions.
Outcome: The proposed model is effective for training models and can be used for future research across a wide range of tasks.
A Visually-grounded First-person Dialogue Dataset with Verbal and Non-verbal Responses (2020.emnlp-main)

Copied to clipboard

Challenge: In visual-grounded dialogue systems, first-person visual information about where the other speakers are and what they are paying attention to is crucial to understand their intentions.
Approach: They propose a visually-grounded first-person dialogue (VFD) dataset with verbal and non-verbal responses.
Outcome: The proposed dataset provides verbal and non-verbal responses for first-person visual information and recent neural network models.
Better Generalizing to Unseen Concepts: An Evaluation Framework and An LLM-Based Auto-Labeled Pipeline for Biomedical Concept Recognition (2026.eacl-long)

Copied to clipboard

Challenge: Existing methods for recognizing ontology concepts are limited by the number of annotations available.
Approach: They propose an evaluation framework built on hierarchical concept indices and novel metrics to measure generalization.
Outcome: The proposed evaluation framework is built on hierarchical concept indices and novel metrics to measure generalization.
Post Persona Alignment for Multi-Session Dialogue Generation (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for multi-session persona-based dialogue generation typically retrieve persona information before response generation, which can constrain diversity and result in generic outputs.
Approach: They propose a two-stage framework that reverses the process of retrieving persona information before response generation.
Outcome: Experiments on multi-session persona-based dialogue data show that the proposed framework outperforms existing methods in consistency, diversity, and persona relevance.

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