Papers by Yoshimasa Tsuruoka

13 papers
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.
NeoAMT: Neologism-Aware Agentic Machine Translation with Reinforcement Learning (2026.acl-long)

Copied to clipboard

Challenge: Neologism-aware machine translation aims to translate source sentences containing neologismes into target languages.
Approach: They propose an agentic framework for neologism-aware machine translation equipped with a Wiktionary-based search toolkit.
Outcome: The proposed framework is based on a Wiktionary-based search toolkit and a dedicated dataset for neologism-aware machine translation.
Word Alignment as Preference for Machine Translation (2024.emnlp-main)

Copied to clipboard

Challenge: Hallucination and omission are a problem in machine translation because of an LLM's size and low-resource languages.
Approach: They propose to use word alignment as preference to optimize an LLM-based MT model to mitigate hallucination and omission problems.
Outcome: The proposed model is able to mitigate hallucination and omission by using word alignment as preference.
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.
Accelerated Reinforcement Learning for Sentence Generation by Vocabulary Prediction (N19-1)

Copied to clipboard

Challenge: In reinforcement learning-based sentence generation, the large action space is often too computa-tionally demanding to be used with large training data.
Approach: They propose to reduce the action space by using dynamic vocabulary prediction to generate a fixed-size small vocabulary for each input to generate its target sentence.
Outcome: The proposed method achieves faster reinforcement learning (2.7x faster) with less GPU memory (2.3x less) and more rewards with fewer iterations of supervised pre-training.
Leveraging Multi-lingual Positive Instances in Contrastive Learning to Improve Sentence Embedding (2024.eacl-long)

Copied to clipboard

Challenge: Recent trends in learning monolingual and multilingual sentence embeddings are based on contrastive learning (CL) among an anchor, one positive and multiple negative instances.
Approach: They propose to leverage multiple positives to improve learning of multilingual sentence embeddings by using an anchor, one positive, and multiple negative instances.
Outcome: The proposed approach improves retrieval, semantic similarity, and classification performance on unseen languages.
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.
Using Semantic Similarity as Reward for Reinforcement Learning in Sentence Generation (P19-2)

Copied to clipboard

Challenge: Existing models for sentence generation use cross-entropy loss as the loss function . however, cross-etropy is unable to evaluate sentences as a whole and lacks flexibility . et al., 2018: a novel approach to improve sentence generation models .
Approach: They propose a method to train a model using estimated semantic similarity between output and reference sentences to alleviate cross-entropy loss problems.
Outcome: The proposed model improves the BLEU scores from the baseline LSTM NMT model.
WSPAlign: Word Alignment Pre-training via Large-Scale Weakly Supervised Span Prediction (2023.acl-long)

Copied to clipboard

Challenge: Existing word alignment methods rely on manual data and lack generalization ability.
Approach: They propose to use a weakly-supervised large-scale weakly supervised dataset for word alignment pre-training via span prediction to reduce the need for manual data.
Outcome: The proposed method improves upon the best supervised baseline by 3.3 6.1 points in F1 and 1.5 6.1 point in AER.
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 .
Enhancing Cross-lingual Sentence Embedding for Low-resource Languages with Word Alignment (2024.findings-naacl)

Copied to clipboard

Challenge: Current approaches to obtain cross-lingual sentence embeddings rely on pre-trained language models that implicitly align the contextual representations of similar units of sentences in different languages.
Approach: They propose a framework that explicitly aligns words between English and eight low-resource languages by using off-the-shelf word alignment models.
Outcome: The proposed framework improves on the bitext retrieval task and in high-resource languages.
Improving Word Alignment Using Semi-Supervised Learning (2025.findings-acl)

Copied to clipboard

Challenge: Existing word alignment methods rely on labeled data, but augmenting training with pseudo-labeled data improves performance.
Approach: They propose a semi-supervised framework to improve word alignment methods . they use pseudo-labeled data from multilingual encoder models as word aligners .
Outcome: The proposed framework outperforms the current state-of-the-art binary alignment method on word alignment datasets.

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