Papers by Hiroyuki Deguchi

11 papers
Diversity Explains Inference Scaling Laws: Through a Case Study of Minimum Bayes Risk Decoding (2025.acl-long)

Copied to clipboard

Challenge: Existing studies show that MBR decoding improves model generation performance . however, the theoretical underpinnings of these results remain uncertain .
Approach: They propose a theoretical interpretation of MBR decoding from the perspective of bias–diversity decomposition.
Outcome: The proposed method improves the quality estimation of hypotheses by decomposing bias and diversity into two main factors.
Centroid-Based Efficient Minimum Bayes Risk Decoding (2024.findings-acl)

Copied to clipboard

Challenge: Minimum Bayes risk (MBR) decoding requires quadratic time since it computes the expected score between a translation hypothesis and all reference translations.
Approach: They propose a centroid-based MBR decoding method that clusters the translations in the feature space and calculates the expected score using the centroids of each cluster.
Outcome: The proposed method outperforms vanilla MBR decoding in translation quality by up to 0.5 COMET in the WMT’22 EnJa, EnDe, EnZh, and WMT'23 Enja translation tasks.
One Single Hub Text Breaks CLIP: Identifying Vulnerabilities in Cross-Modal Encoders via Hubness (2026.acl-long)

Copied to clipboard

Challenge: et al., 2010) show that hub embeddings are close to many unrelated examples in high-dimensional embeddable spaces . cross-modal encoders that project different modalities into a shared space are useful for cross-module applications .
Approach: They propose a method for identifying the hub embedding and its corresponding hub text . they use images to evaluate cross-modal encoders that project different modalities into a shared space .
Outcome: The proposed method can identify a single hub embedding and its corresponding hub text . it achieves comparable or higher similarity scores than human-written reference captions in many images .
Synchronous Syntactic Attention for Transformer Neural Machine Translation (2021.acl-srw)

Copied to clipboard

Challenge: Existing syntaxbased NMT models use monolingual syntactic information on either side or both.
Approach: They propose a mechanism that synchronizes source-side and target-side syntactic self-attentions by minimizing the difference between target- and target side self- attentions mapped by the encoder-decoder attention matrix.
Outcome: The proposed method improves translation performance on WMT14 En-De, WMT16 En-Ro, and ASPEC Ja-En (up to +0.38 points in BLEU).
Long-Tail Crisis in Nearest Neighbor Language Models (2025.findings-naacl)

Copied to clipboard

Challenge: Prior studies have shown that kNN-LM can retrieve long-tail contexts, leaving the model’s performance underexplored in estimating the probabilities of long-tailed target tokens.
Approach: They investigate the behavior of kNN-LM on low-frequency tokens, examining prediction probability, retrieval accuracy, and token distribution in the datastore.
Outcome: The proposed model improves the perplexity of given text by directly accessing a large datastore built from any text data during inference.
Subset Retrieval Nearest Neighbor Machine Translation (2023.acl-long)

Copied to clipboard

Challenge: k-nearest-neighbor machine translation (kNN-MT) is a new approach to improve NMT performance without additional training.
Approach: They propose a method that integrates example-search into the decoding algorithm to improve neighbor token retrieval.
Outcome: The proposed method achieves a speed-up of up to 132.2 times and an improvement in BLEU score of up 1.6 compared with kNN-MT in the WMT’19 translation task and the domain adaptation tasks in De-En and En-Ja.
TableMBR: Minimum Bayes Risk Table Generation Based on Structural Consistency (2026.acl-srw)

Copied to clipboard

Challenge: Experimental results show TableMBR outperforms the baseline, achieving relative improvements of up to 15% in F1 on Rotowire and 23% in accuracy on LiveSum.
Approach: They propose a text-to-table task that generates structured data from unstructured text . they propose 'tableMBR' that maintains structural consistency through minimum Bayes risk decoding .
Outcome: The proposed method outperforms the baseline and achieves relative improvements in F1 and LiveSum.
Bilingual Subword Segmentation for Neural Machine Translation (2020.coling-main)

Copied to clipboard

Challenge: Existing subword segmentation methods tokenize sentences without considering translation . proposed method could be more favorable to machine translation if it uses bilingual sentences .
Approach: They propose a subword segmentation method that tokenizes sentences by using subword units induced from bilingual sentences.
Outcome: The proposed method improves translation performance on translation tasks up to +0.81 BLEU.
Case-Based Decision-Theoretic Decoding with Quality Memories (2025.emnlp-main)

Copied to clipboard

Challenge: Minimum Bayes risk (MBR) decoding is a decision rule of text generation . however, it depends on sample texts drawn from the text generation model .
Approach: They propose a case-based decision-theoretic method to estimate the expected utility using examples of domain data.
Outcome: The proposed method outperforms MAP decoding in translation tasks and image captioning tasks on MSCOCO and nocaps datasets.
Hacking Neural Evaluation Metrics with Single Hub Text (2026.eacl-short)

Copied to clipboard

Challenge: Recent embedding-based neural text evaluation metrics are not reliable due to black-box nature of neural networks.
Approach: They propose to find a single adversarial text in the discrete space that is consistently evaluated as high-quality regardless of the test cases.
Outcome: The proposed method outperforms translations generated individually for each source sentence in English-to-Japanese and English- to-German translation tasks.
mbrs: A Library for Minimum Bayes Risk Decoding (2024.emnlp-demo)

Copied to clipboard

Challenge: Minimum Bayes risk (MBRS) decoding is a decision rule of text generation tasks that outperforms conventional maximum a posteriori (MAP) decoders by selecting high-quality outputs based on quality or preference rather than probability.
Approach: They propose to use minimum bayes risk (MBRS) decoding to determine outputs based on quality rather than probability.
Outcome: MBRS is an MIT-licensed open-source project with a focus on speed, reproducibility, and extensibility.

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