Papers by Yuki Arase
Adaptive LoRA Merge with Parameter Pruning for Low-Resource Generation (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for adapting LLMs to low-resource tasks keep LoRA parameters frozen and the low-level problem out of their scope. |
| Approach: | They propose a LoRA merge method that updates and prunes LoRA parameters through fine-tuning with minimal target task data. |
| Outcome: | The proposed method improves performance on a low-resource language generation task and improves on previous methods. |
Language-agnostic Representation from Multilingual Sentence Encoders for Cross-lingual Similarity Estimation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to extract language-specific information from multilingual sentence embeddings are remarkably successful in cross-lingual and multilingual NLU tasks. |
| Approach: | They propose to extract language-specific information from the original embedding and use it to retrieve an embeddable that fully represents the sentence’s meaning. |
| Outcome: | The proposed method outperforms baselines on cross-lingual sentences even in low-resource language pairs where only tens of thousands of parallel sentence pairs are available. |
Text Classification with Negative Supervision (2020.acl-main)
Copied to clipboard
| Challenge: | Existing models for text representations have shown state-of-the-art performance on text classification tasks, however, the discrepancy between semantic similarity of texts and labelling standards affects classifiers. |
| Approach: | They propose a simple multitask learning model that uses negative supervision to generate distinct representations for texts with different labels. |
| Outcome: | The proposed model outperforms state-of-the-art models on classification tasks in three different languages. |
Unbalanced Optimal Transport for Unbalanced Word Alignment (2023.acl-long)
Copied to clipboard
| Challenge: | Figure 1 illustrates the challenges of monolingual word alignment. |
| Approach: | They propose to use the family of optimal transport (OT) to achieve unbalanced word alignment that values alignment and null alignment on unsupervised datasets. |
| Outcome: | The proposed methods are competitive against the state-of-the-art methods on challenging datasets with high null alignment frequencies. |
Adversarial Training on Disentangling Meaning and Language Representations for Unsupervised Quality Estimation (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods for unsupervised quality estimation of machine translation are limited to several major language pairs. |
| Approach: | They propose a method to distill language-agnostic meaning embeddings from multilingual sentence encoders for unsupervised quality estimation of machine translation. |
| Outcome: | The proposed method achieves higher correlations with human evaluations on unsupervised translation quality estimation. |
DIRECT: Direct and Indirect Responses in Conversational Text Corpus (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Neural conversation models have been able to generate fluent responses through training on a dialogue corpus, but they lack the ability to reveal the implied intentions of users. |
| Approach: | They propose to train neural conversation models on a dialogue corpus that provides pragmatic paraphrases to advance techniques for natural language understanding in dialogue systems. |
| Outcome: | The proposed corpus provides 71,498 pairs of indirect–direct utterance pairs accompanied by a multi-turn dialogue history extracted from the MultiWoZ dataset. |
Aligning Sentence Simplification with ESL Learner’s Proficiency for Language Acquisition (2025.naacl-long)
Copied to clipboard
| Challenge: | Text simplification is crucial for improving accessibility and comprehension for English as a Second Language (ESL) learners. |
| Approach: | They propose to simplify complex sentences to appropriate levels while also increasing vocabulary coverage of the target level. |
| Outcome: | The proposed method can increase frequency and diversity of vocabulary of the target level by more than 20% compared to baseline models, while maintaining high simplification quality. |
Controllable Text Simplification with Deep Reinforcement Learning (2022.aacl-short)
Copied to clipboard
| Challenge: | Existing methods for controlling sentence difficulty have not taken into account sentence-level difficulties. |
| Approach: | They propose a method for controlling the difficulty of a sentence based on deep reinforcement learning. |
| Outcome: | The proposed method generates sentences of appropriate difficulty for the target audience through reinforcement learning. |
Controllable Paraphrase Generation for Semantic and Lexical Similarities (2024.lrec-main)
Copied to clipboard
| Challenge: | Lexically diverse paraphrases are crucial in data augmentation because they enhance the linguistic diversity of the corpus. |
| Approach: | They propose a controllable model for semantic and lexical similarities by attaching tags to the head of the input sentence. |
| Outcome: | The proposed model can paraphrase an input sentence according to the tags specified. |
Definition Modelling for Appropriate Specificity (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing definition generation techniques have faced various problems such as the out-of-vocabulary problem and over/under-specificity problems. |
| Approach: | They propose to leverage a pre-trained encoder-decoder model and introduce a re-ranking mechanism to model specificity in definitions. |
| Outcome: | The proposed method significantly outperforms the state-of-the-art method on standard evaluation datasets and shows that it addresses the over/under-specificity problems. |
Contextualized context2vec (D19-55)
Copied to clipboard
| Challenge: | Lexical substitution ranks substitution candidates from the viewpoint of paraphrasability for a target word in a given sentence. |
| Approach: | They propose a method that combines two approaches to contextualize word embeddings for lexical substitution. |
| Outcome: | The proposed method outperforms the current state-of-the-art method and assigns English proficiency levels to all target words and substitution candidates. |
Evaluation Dataset for Japanese Medical Text Simplification (2024.naacl-srw)
Copied to clipboard
| Challenge: | Existing studies on medical text simplification in English have not been well explored in Japanese because of the lack of a parallel corpus of this domain. |
| Approach: | They propose a lexically constrained reranking method that allows to avoid technical terms to be output. |
| Outcome: | The proposed method improves on the weblogs of Japanese patients and reduces the need for a training corpus. |
Compositional Phrase Alignment and Beyond (2020.emnlp-main)
Copied to clipboard
| Challenge: | Phrase alignment is the basis for sentence pair interactions, such as paraphrase identification and textual entailment recognition. |
| Approach: | They propose a phrase alignment model that embeds similarity distributions into powerful contextualized representations that can be used to model sentence pair interactions. |
| Outcome: | The proposed method significantly outperforms that used in a previous study and achieves a performance competitive with that of experienced human annotators. |
Edit-Constrained Decoding for Sentence Simplification (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies have shown that lexically constrained decoding is effective for sentence simplification, but their constraints can be loose and may lead to sub-optimal generation. |
| Approach: | They propose an edit operation based on lexically constrained decoding for sentence simplification using a dictionary of technical terms as constraints. |
| Outcome: | The proposed method outperforms previous studies on English simplification corpora and is based on lexical paraphrasing. |
Recursive Neural Network Based Preordering for English-to-Japanese Machine Translation (P18-3)
Copied to clipboard
| Challenge: | Existing methods for preordering require a manual feature design, making language dependent design difficult. |
| Approach: | They propose a preordering method with recursive neural networks that learn features from raw inputs. |
| Outcome: | The proposed method is comparable to the state-of-the-art method but without a manual feature design. |
Edit Distance Based Curriculum Learning for Paraphrase Generation (2021.acl-srw)
Copied to clipboard
| Challenge: | Existing studies show that curriculum learning improves translation quality on machine translation . paraphrase generation allows a certain level of semantic divergence between source and target . |
| Approach: | They propose to apply curriculum learning to paraphrase generation for the first time . they propose to use edit distance to improve paraphrase quality . |
| Outcome: | The proposed method improves paraphrase generation quality, compared with previous methods . it uses edit distance, which is not possible for previous methods, the authors say . |
Light-Weight Hallucination Detection using Contrastive Learning for Conditional Text Generation (2025.acl-srw)
Copied to clipboard
| Challenge: | Existing methods for hallucination detection are limited to the scenario where we can access the LLMs that have generated the outputs. |
| Approach: | They propose a hallucination detection method that uses contrastive learning to pull faithful outputs and input contexts together while pushing hallucinous outputs apart. |
| Outcome: | The proposed method outperforms GPT-4o prompting in binary hallucination detection. |
Dialogue-Act Prediction of Future Responses Based on Conversation History (P19-2)
Copied to clipboard
| Challenge: | Sequence-to-sequence models are a common approach to develop chatbots, but they are prone to a black-box response generation process. |
| Approach: | They propose a method to predict a DA of the next response based on the history of previous utterances and their DAs. |
| Outcome: | The proposed model achieves 10.8% higher F1-score and 3.0% higher accuracy on DA prediction compared to baseline using only a single utterance . |
Annotation of Adverse Drug Reactions in Patients’ Weblogs (2020.lrec-1)
Copied to clipboard
| Challenge: | Adverse drug reactions are a severe problem that significantly degrade quality of life and make the therapeutic approach unacceptable. |
| Approach: | They crawled patient’s weblog articles shared on an online patient-networking platform and annotated the effects of drugs therein reported. |
| Outcome: | The proposed dataset is unique for the richness of annotated information, including detailed descriptions of drug reactions with full context. |
Text Simplification with Reinforcement Learning Using Supervised Rewards on Grammaticality, Meaning Preservation, and Simplicity (2020.aacl-srw)
Copied to clipboard
| Challenge: | Existing studies in text-to-text generation do not align with human-perspectives for these perspectives. |
| Approach: | They propose to use BERT regressors fine-tuned for grammaticality, meaning preservation, and simplicity as reward estimators to optimize rewards for text simplification. |
| Outcome: | The proposed method achieves text simplification conforming to human-perspectives. |
CEFR-based Lexical Simplification Dataset (L18-1)
Copied to clipboard
| Challenge: | Existing tools for lexical simplification are not tailored to language education with word levels and lists of candidates subjective. |
| Approach: | They construct a language dataset for lexical simplification based on CEFR levels . target and candidate words are assigned CEFR-J wordlists and English Vocabulary Profile . |
| Outcome: | The proposed method is based on the common European Framework of References for Languages (CEFR) levels and candidates are selected using an online thesaurus. |
Distinct Label Representations for Few-Shot Text Classification (2021.acl-short)
Copied to clipboard
| Challenge: | Existing methods for few-shot text classification ignore the semantic relevance of labels and are difficult to train because of the lack of training examples. |
| Approach: | They propose a method that generates distinct label representations that embed information specific to each label. |
| Outcome: | The proposed method significantly improves few-shot text classification across models and datasets. |
Monolingual Phrase Alignment as Parse Forest Mapping (2023.starsem-1)
Copied to clipboard
| Challenge: | Existing methods for phrase alignment are based on unordered tree mapping . syntactic ambiguities can affect alignment quality, so we expand it to parse forests instead of 1-best trees. |
| Approach: | They propose to expand existing method to align parse forests rather than 1-best trees, where syntactic structures and phrase alignment are simultaneously identified. |
| Outcome: | The proposed method improves the state-of-the-art method by aligning forests rather than 1-best trees. |
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. |
Distilling Word Meaning in Context from Pre-trained Language Models (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to transform contextualised representations weaken excessive effects of contextual information. |
| Approach: | They propose a self-supervised learning method that distils word meaning in context from a pre-trained masked language model. |
| Outcome: | The proposed method outperforms the state-of-the-art method for lexical semantics and STS estimation. |
SPADE: Evaluation Dataset for Monolingual Phrase Alignment (L18-1)
Copied to clipboard
| Challenge: | Existing studies on sentential paraphrase detection focus on finer grained paraphrases, i.e., phrasal paraphrase. |
| Approach: | They propose to use the SPADE to evaluate syntactic phrase alignment in paraphrasal sentences. |
| Outcome: | The proposed method is compared with humans and provides benchmarks to show its performance. |
Distractor Generation for Fill-in-the-Blank Exercises by Question Type (2023.acl-srw)
Copied to clipboard
| Challenge: | Existing studies have generated words that are semantically similar to the correct words as distractors for fill-in-the-blank questions. |
| Approach: | They propose a method to automatically generate distractors for fill-in-the-blank questions in entrance examinations for Japanese universities. |
| Outcome: | The proposed method is effective on 500 actual questions on English fill-in-the-blank questions in Japanese universities. |
Consistent Response Generation with Controlled Specificity (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to generate fluent responses generate inconsistent responses . we use a sequence-to-sequence model to generate specific responses based on a co-occurrence degree . |
| Approach: | They propose a method to control the specificity of responses while maintaining the consistency with the utterances. |
| Outcome: | The proposed method produces highly consistent responses in open-domain dialogues . it can generate fluent responses while maintaining the consistency with the utterances compared to the conventional model . |
JADE: Corpus for Japanese Definition Modelling (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing corpus for definition modelling techniques is limited to English . this study aimed to develop a corpus that provides definitions of words and phrases . |
| Approach: | They investigated and released a corpus for Japanese definition modelling . the JADE provides 630k sets of targets, their definitions, and usage examples as contexts . |
| Outcome: | The JADE corpus provides 630k sets of targets, their definitions, and usage examples as contexts for 41k unique targets. |
Tiny Word Embeddings Using Globally Informed Reconstruction (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for word embedding reconstruction use only local information of subwords and pre-trained word embeds. |
| Approach: | They propose a global loss function that uses words other than the target word to improve word embedding reconstruction by a factor of 200. |
| Outcome: | The proposed method reduces the model size of pre-trained word embeddings by a factor of 200 while preserving its quality. |
Leveraging High-Resource English Corpora for Cross-lingual Domain Adaptation in Low-Resource Japanese Medicine via Continued Pre-training (2025.findings-emnlp)
Copied to clipboard
Kazuma Kobayashi, Zhen Wan, Fei Cheng, Yuma Tsuta, Xin Zhao, Junfeng Jiang, Jiahao Huang, Zhiyi Huang, Yusuke Oda, Rio Yokota, Yuki Arase, Daisuke Kawahara, Akiko Aizawa, Sadao Kurohashi
| Challenge: | low-resource language corpora in professional domains like medicine hinder cross-lingual domain adaptation of pre-trained large language models. |
| Approach: | They examine how linguistic features affect performance on a Japanese–English medical knowledge benchmark. |
| Outcome: | The proposed model can leverage English-language resources in medical domains while ensuring sufficient coverage of language-specific expressions in a target language. |
Controllable Text Simplification with Lexical Constraint Loss (P19-2)
Copied to clipboard
| Challenge: | Existing models that only consider the sentence level generate words beyond the target level. |
| Approach: | They propose a method to control the level of a sentence in a text simplification task . they add the target grade level as input and weight words in the loss function . |
| Outcome: | The proposed method improves both BLEU and SARI scores and achieves aggressive rewriting. |
Transfer Fine-Tuning: A BERT Case Study (D19-1)
Copied to clipboard
| Challenge: | Recent advances in sentence representation learning have improved the performance of BERT models, but the computational power required is an obstacle preventing practical applications from adopting the technology. |
| Approach: | They propose to inject phrasal paraphrase relations into BERT to generate suitable representations for semantic equivalence assessment instead of increasing model size. |
| Outcome: | The proposed model improves a smaller model while maintaining the model size. |
Self-Ensemble of N-best Generation Hypotheses by Lexically Constrained Decoding (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies have improved generation quality by explicitly reranking N-best candidates. |
| Approach: | They propose a method that ensembles N-best hypotheses to improve natural language generation by combining high-quality fragments of N- best hypothese . they use tokens that should or should not be present in the final output as lexical constraints to improve quality of generation. |
| Outcome: | Empirical results show that the proposed method outperforms strong N-best reranking methods on paraphrase generation, summarisation, and constrained text generation. |
CEFR-Based Sentence Difficulty Annotation and Assessment (2022.emnlp-main)
Copied to clipboard
| Challenge: | Controllable text simplification is a crucial assistive technique for language learning and teaching. |
| Approach: | They propose a sentence-level assessment model to handle unbalanced level distribution . previous studies have suggested that controllable text simplification is difficult to apply . |
| Outcome: | The proposed method outperforms baselines in readability assessment by scoring macro-F1 on the level assessment. |
SAPPHIRE: Simple Aligner for Phrasal Paraphrase with Hierarchical Representation (2020.lrec-1)
Copied to clipboard
| Challenge: | Monolingual phrase alignment is a fundamental problem in natural language understanding and crucial technique in various applications. |
| Approach: | They propose a simple Aligner for Phrasal Paraphrase with HIerarchical REpresentation that uses word embeddings to train phrase alignments. |
| Outcome: | The proposed algorithm outperforms the previous methods and establishes the state-of-the-art. |