Papers by Ryokan Ri

9 papers
Dynamic Injection of Entity Knowledge into Dense Retrievers (2025.findings-emnlp)

Copied to clipboard

Challenge: Dense retrievers struggle with queries involving less-frequent entities due to limited entity knowledge.
Approach: They propose a BERT-based retriever enhanced with a context-entity attention layer and dynamically updatable entity embeddings.
Outcome: The proposed retriever incorporates external entity knowledge without retraining.
EASE: Entity-Aware Contrastive Learning of Sentence Embedding (2022.naacl-main)

Copied to clipboard

Challenge: Existing methods for learning sentence embeddings are fine-tuning general-purpose pretrained models with a particular training supervision.
Approach: They propose a method for learning sentence embeddings via contrastive learning between sentences and related entities.
Outcome: The proposed method outperforms baseline methods in multilingual settings on a variety of tasks.
Pretraining with Artificial Language: Studying Transferable Knowledge in Language Models (2022.acl-long)

Copied to clipboard

Challenge: Existing studies show that pretraining with an artificial language with nesting dependency structure provides some knowledge transferable to natural language.
Approach: They propose to pretrain artificial languages with structural properties that mimic natural language and then test their performance on downstream tasks.
Outcome: The proposed language models show strong performance across languages and languages.
Large Vocabulary Size Improves Large Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Existing studies have investigated the properties of internal layers in large language models, but no studies have defined the vocabulary size.
Approach: They propose a method to use a new vocabulary instead of the pre-defined one in a continual training scenario.
Outcome: The proposed method outperforms the model with the pre-defined vocabulary in a continual training scenario.
Designing the Business Conversation Corpus (D19-52)

Copied to clipboard

Challenge: Existing parallel corpora for machine translation of written text and monologues are limited.
Approach: They propose to introduce a Japanese-English business conversation parallel corpus into machine translation training scenarios and show how it improves machine translation quality.
Outcome: The proposed corpus is used in a Japanese-English business conversation training scenario and shows how it performs.
mLUKE: The Power of Entity Representations in Multilingual Pretrained Language Models (2022.acl-long)

Copied to clipboard

Challenge: Existing methods for improving multilingual models only use entity information in pretraining and do not explicitly use entities in downstream tasks.
Approach: They propose to leverage Wikipedia entity representations for downstream tasks . they train a multilingual language model with 24 languages with entity representation .
Outcome: The proposed model outperforms word-based models in cross-lingual transfer tasks.
Revisiting the Context Window for Cross-lingual Word Embeddings (2020.acl-main)

Copied to clipboard

Challenge: Existing approaches to mapping-based cross-lingual word embeddings are based on the assumption that the source and target embeddable spaces are structurally similar.
Approach: They propose to use different context windows to evaluate bilingual word embeddings in various languages, domains, and tasks.
Outcome: The size of both the source and target window improves bilingual lexicon induction, especially on frequent nouns.
Data Augmentation with Unsupervised Machine Translation Improves the Structural Similarity of Cross-lingual Word Embeddings (2021.acl-srw)

Copied to clipboard

Challenge: Unsupervised cross-lingual word embedding methods learn a linear transformation matrix that maps two monolingual embeddable spaces that are separately trained with monolingual corpora.
Approach: They propose a method that maps two monolingual embedding spaces that are separately trained with monolingual corpora using a pseudo-parallel corpus.
Outcome: The proposed method outperforms other methods given the same amount of data and shows that using a pseudo-parallel corpus makes the source and target corpora (partially) parallel .
LEIA: Facilitating Cross-lingual Knowledge Transfer in Language Models with Entity-based Data Augmentation (2024.findings-acl)

Copied to clipboard

Challenge: Existing language adaptation methods overlook the benefits of cross-lingual supervision.
Approach: They propose a language adaptation tuning method that augments target corpus with English entity names and trains the model using left-to-right language modeling.
Outcome: The proposed method shows significant performance gains across non-English languages.

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