Papers by Naoki Yoshinaga

26 papers
Speculative Sampling in Variational Autoencoders for Dialogue Response Generation (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing studies have tried to improve variational models but they fail to learn proper mappings.
Approach: They propose to use a variable-based sampling technique to find the most probable one from redundantly sampled latent variables to tie up the variable with a given response.
Outcome: The proposed method is effective in response generation with massive dialogue data constructed from Twitter posts.
Vocabulary Adaptation for Domain Adaptation in Neural Machine Translation (2020.findings-emnlp)

Copied to clipboard

Challenge: Neural network methods exhibit strong performance only in a few resource-rich domains.
Approach: They propose a method that fine-tunes embedding layers of a pre-trained NMT model to the target domain.
Outcome: The proposed method improves fine-tuning performance in En-Ja and De-En translation by 3.86 and 3.28 BLEU points.
Robust Backed-off Estimation of Out-of-Vocabulary Embeddings (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to solving out-of-vocabulary (OOV) words use subwords to represent oov words with a bag of subword.
Approach: They propose a method to estimate oov word embeddings by referring to pre-trained word embeds for known words with similar surfaces to target ov words.
Outcome: The proposed method improves word similarity tasks and biomedical tasks even with weak baselines.
Query-Focused Individual Simulation with Progressive Persona Completion (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to simulating individual responses from persona information assume rich persona profiles, which are often unavailable in practice.
Approach: They propose a query-focused individual simulation where relevant persona information is identified and requested on demand for each query.
Outcome: Experiments on two dialogue datasets show that the proposed method achieves comparable performance to approaches that rely on rich persona information extracted from dialogue history.
CLICKER: Cross-Lingual Knowledge Editing via In-Context Learning with Adaptive Stepwise Reasoning (2026.findings-eacl)

Copied to clipboard

Challenge: Existing knowledge editing methods are static and fail to propagate edits across languages.
Approach: They propose a KE method that dynamically retrieves only knowledge relevant to a given query and edits it to maintain cross-lingual consistency.
Outcome: The proposed method outperforms static KE methods on a multilingual dataset with semantically similar but irrelevant prompts.
A-TASC: Asian TED-Based Automatic Subtitling Corpus (2025.acl-long)

Copied to clipboard

Challenge: Existing AS corpora and primary metric SubER focus on European languages.
Approach: They propose an Asian TED-based automatic subtitling corpus derived from English TED Talks and a modification of SubER to enable reliable evaluation of subtitle quality for languages without explicit word boundaries.
Outcome: The proposed corpus is based on TED Talks audio segments, transcripts, and subtitles in Chinese, Japanese, Korean, and Vietnamese.
Tracing the Roots of Facts in Multilingual Language Models: Independent, Shared, and Transferred Knowledge (2024.eacl-long)

Copied to clipboard

Challenge: Using low-resource languages, multilingual language models (ML-LMs) have been developed to transfer factual knowledge across languages.
Approach: They ask how ML-LMs acquire and represent factual knowledge . they use a multilingual factual information probing dataset to investigate ML .
Outcome: The findings highlight the challenge of maintaining consistency factual knowledge across languages.
Fine-grained Typing of Emerging Entities in Microblogs (2021.findings-emnlp)

Copied to clipboard

Challenge: Graus et al., 2018) defined emerging entities as those that appear in contexts that emphasize their novelty, and attempted to discover emerging entities from microblogs.
Approach: They propose a task that assigns a fine-grained type to each emerging entity when a burst of posts containing that entity is first observed in a microblog.
Outcome: The proposed model can type 'homographic' emerging entities without relying on prior knowledge of the target entity.
Is He Extroverted? Identifying Missing Relevant Personas for Faithful User Simulation (2026.eacl-srw)

Copied to clipboard

Challenge: Existing user simulation approaches focus on generating user-like responses in dialogue without verifying whether critical personas are supplied.
Approach: They propose a task of identifying persona dimensions that are relevant but missing in simulating a user's reply for a given dialogue context.
Outcome: The proposed model identifies persona dimensions that are relevant but missing in simulating a user’s response for a given dialogue context.
Building Large-Scale Japanese Pronunciation-Annotated Corpora for Reading Heteronymous Logograms (2022.lrec-1)

Copied to clipboard

Challenge: Especially in Japanese, there are many common heteronyms expressed by logograms (Chinese characters or kanji) that have totally different pronunciations.
Approach: They construct large-scale Japanese corpora that annotate kanji characters with their pronunciations to improve the accuracy of pronunciation prediction models.
Outcome: The proposed models achieve an average accuracy of 0.939 for 203 common heteronyms and a 0.938 for 93 heters.
Context-aware Decoder for Neural Machine Translation using a Target-side Document-Level Language Model (2021.naacl-main)

Copied to clipboard

Challenge: Neural machine translation models that incorporate inter-sentential contexts can be trained only in document-level parallel data with sentential alignments.
Approach: They propose a method to perform context-aware decoding with any pre-trained translation model . their method uses sentence-level parallel data and target-side document-level monolingual data .
Outcome: The proposed method performs context-aware decoding on English to Russian translation using BLEU and contrastive tests.
Does Named Entity Recognition Truly Not Scale Up to Real-world Product Attribute Extraction? (2023.emnlp-industry)

Copied to clipboard

Challenge: scalability of attribute-value extraction (AVE) task is key for a large number of products . a question-answering (QA)-based approach is better for AVE, but requires a larger number of classes to be scalable.
Approach: They propose a question-answering-based approach that additionally inputs the target attribute as a query to extract its values.
Outcome: The proposed approach outperforms a classical approach on real-word e-commerce datasets in accuracy and speed.
Back to Patterns: Efficient Japanese Morphological Analysis with Feature-Sequence Trie (2023.acl-short)

Copied to clipboard

Challenge: Accurate neural models are less efficient than non-neural models and are useless for processing billions of social media posts and handling user queries.
Approach: They propose to make fast pattern-based NLP methods as accurate as possible . they propose a morphological analyzer for Japanese that induces reliable patterns .
Outcome: The proposed method induces reliable patterns from a morphological dictionary and annotated data in Japanese.
What Matters in Memorizing and Recalling Facts? Multifaceted Benchmarks for Knowledge Probing in Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Language models often exhibit factual hallucination issue, exhibiting factual factual knowledge-grounded sentences.
Approach: They introduce a knowledge probing benchmark to evaluate the knowledge recall ability of pre-trained language models from diverse perspectives.
Outcome: The proposed benchmark evaluates the knowledge recall ability of encoder- and decoder-based pre-trained language models from diverse perspectives.
Simple and Effective Knowledge-Driven Query Expansion for QA-Based Product Attribute Extraction (2022.acl-short)

Copied to clipboard

Challenge: Existing approaches to extract value from product data for a large number of attributes are not effective for rare and ambiguous attributes.
Approach: They propose to use attributes as knowledge to expand AVE queries by retrieving possible answers from training data.
Outcome: The proposed model improves on a cleaned version of AliExpress dataset for rare and ambiguous attributes, especially for rare attributes.
Commentary Generation from Data Records of Multiplayer Strategy Esports Game (2024.naacl-srw)

Copied to clipboard

Challenge: Esports play logs are expensive for human experts to provide individual games with play-by-play commentaries.
Approach: They first build large-scale esports data-to-text datasets that pair structured data and commentaries from a popular eSports game, League of Legends.
Outcome: The proposed model can generate game commentaries from esports’ data records while examining the impact of the pre-trained language models.
Self-Adaptive Named Entity Recognition by Retrieving Unstructured Knowledge (2023.eacl-main)

Copied to clipboard

Challenge: Named entity recognition (NER) is costly because of lack of training data and domain experts.
Approach: They propose a self-adaptive neural model that retrieves external knowledge from unstructured text to learn the usages of entities that have not been learned well.
Outcome: The proposed model outperforms strong baselines on cross-neuro-ner datasets by 2.35 points in F1 metric.
A Unified Generative Approach to Product Attribute-Value Identification (2023.findings-acl)

Copied to clipboard

Challenge: Product attribute value identification (PAVI) is a core task in the e-commerce industry.
Approach: They propose a generative approach to product attribute-value identification (PAVI) they use product text to decode a set of attribute- value pairs as a target sequence from the given product text.
Outcome: The proposed approach outperforms extraction- and classification-based methods on large-scale real-world datasets.
Modeling Personal Biases in Language Use by Inducing Personalized Word Embeddings (N19-1)

Copied to clipboard

Challenge: Existing studies have attempted to personalize models to improve performance on NLP tasks such as sentiment analysis but they did not estimate subjective input.
Approach: They propose a method of modeling personal biases in word meanings with personalized word embeddings by solving a task on subjective text while regarding words used by different individuals as different words.
Outcome: The proposed method improves sentiment analysis and target task with reviews retrieved from RateBeer.
Neuron Empirical Gradient: Discovering and Quantifying Neurons’ Global Linear Controllability (2025.acl-long)

Copied to clipboard

Challenge: Existing studies have shown that feed-forward neurons in pre-trained language models (PLMs) can encode factual knowledge, but current methods are costly and lack the link between activations and outputs.
Approach: They propose to compute a global linear relationship between neuron activations and outputs using a knowledge probing dataset.
Outcome: The proposed method exploits the neural empirical gradient to capture changes in neuron activations and model outputs.
Tracing Multilingual Knowledge Acquisition Dynamics in Domain Adaptation: A Case Study of Biomedical Adaptation (2026.eacl-long)

Copied to clipboard

Challenge: Multilingual domain adaptation (ML-DA) enables large language models to acquire domain knowledge across languages.
Approach: They propose an adaptive evaluation method that constructs multiple-choice QA datasets from the same bilingual domain corpus used for training.
Outcome: The proposed method constructs multiple-choice QA datasets from the same bilingual domain corpus used for training, thereby enabling direct analysis of multilingual knowledge acquisition.
Entity Embedding Completion for Wide-Coverage Entity Disambiguation (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing state-of-the-art ED models do not address out-of vocabulary entities that are absent from training data.
Approach: They propose to extend a state-of-the-art ED model by dynamically computing embeddings of out-ofvocabulary entities by using entity descriptions and mention contexts.
Outcome: The proposed model performs comparable to existing models whose embeddings are trained for all candidate entities as well as embedd-free models.
Data augmentation using back-translation for context-aware neural machine translation (D19-65)

Copied to clipboard

Challenge: A single sentence does not always convey information that is enough to translate it into other languages.
Approach: They obtain large-scale pseudo parallel corpora by back-translating monolingual data and examine their impact on translation accuracy.
Outcome: The large-scale pseudo parallel corpora obtained by back-translating monolingual data showed that the model trained with small parallel corporeals and large-sized pseudo parallels improved translation accuracy.
Early Discovery of Disappearing Entities in Microblogs (2023.acl-long)

Copied to clipboard

Challenge: a study on detecting disappearing entities from noisy microblogs has been published on the real world . a major challenge is detecting uncertain contexts of disappearing entity from noisy posts .
Approach: They propose to use Twitter to detect disappearing entities from noisy microblogs . they build large-scale Twitter datasets of disappearing entity and refine word embeddings based on these data .
Outcome: The proposed method outperforms baseline methods on noisy microblog streams and more than 70% of disappearing entities in Wikipedia are discovered earlier than the update on Wikipedia.
uBLEU: Uncertainty-Aware Automatic Evaluation Method for Open-Domain Dialogue Systems (2020.acl-srw)

Copied to clipboard

Challenge: Existing evaluation metrics for text generation tasks do not consider uncertain responses without writing additional reference responses by hand.
Approach: They propose a human-aided, uncertainty-aware evaluation method for open-domain dialogue systems, BLEU.
Outcome: The proposed method is comparable to existing methods on Twitter and improves state-of-the-art evaluation method RUBER.
Learning to Describe Unknown Phrases with Local and Global Contexts (N19-1)

Copied to clipboard

Challenge: Existing methods for contextual guessing and definition generation do not take clues from local contexts.
Approach: They propose a neural description model that takes clues from local and global contexts . they assume that the target phrase is newly emerged and there is no global context .
Outcome: The proposed model takes clues from local and global contexts over existing methods . it is more effective than existing methods for non-standard English explanation .

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