Papers by Satoshi Nakamura
Automatic Machine Translation Evaluation using Source Language Inputs and Cross-lingual Language Model (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods for machine translation evaluation use source sentences as pseudo references instead of word symbols. |
| Approach: | They propose an automatic machine translation evaluation method that uses source sentences as pseudo references instead of source sentences. |
| Outcome: | The proposed method achieves higher correlation with human judgments than baseline evaluation method that uses only hypothesis and reference sentences. |
LLMs Are Zero-Shot Context-Aware Simultaneous Translators (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing SiMT systems operate on a sentence level, disregarding the context established by previous sentences or the broader context implied by previous words. |
| Approach: | They show that open-source LLMs perform on par with or better than some state-of-the-art baselines in simultaneous machine translation tasks, zero-shot. |
| Outcome: | The proposed models perform on par with or better than state-of-the-art baselines in simultaneous machine translation tasks, zero-shot. |
Incorporating Noisy Length Constraints into Transformer with Length-aware Positional Encodings (2020.coling-main)
Copied to clipboard
| Challenge: | Neural Machine Translation suffers from an under-translation problem due to limited modeling of output sequence lengths. |
| Approach: | They propose a method to train a Transformer model using length constraints based on positional encoding. |
| Outcome: | The proposed method outperforms a vanilla Transformer in an English-to-Japanese translation by 3.22 points . the noise injection improved robustness for length prediction errors, especially within the window size. |
Japanese Dialogue Corpus of Information Navigation and Attentive Listening Annotated with Extended ISO-24617-2 Dialogue Act Tags (L18-1)
Copied to clipboard
| Challenge: | Large-scale conventional dialogue corpora are mainly built for specified tasks with specially designed dialogue states. |
| Approach: | They propose to annotate large-scale dialogue data with an extended ISO-24617-2 dialogue act tag-set to model a natural conversation with machines. |
| Outcome: | The proposed corpus covers a wider range of dialogue tasks than existing task-oriented systems or text-chat systems. |
Construction of English-French Multimodal Affective Conversational Corpus from TV Dramas (L18-1)
Copied to clipboard
| Challenge: | Existing technologies for speech recognition and speech synthesis focus on non-verbal content and paralinguistic information. |
| Approach: | They propose to construct a multimodal affective conversational corpus based on TV dramas . their data contain parallel English-French languages in lexical, acoustic, and facial features . |
| Outcome: | The proposed corpus can be used to assess speech recognition, speech recognition and synthesis, linguistic, and paralinguistic speech-to-speech translation and multimodal dialog systems. |
LLaST: Improved End-to-end Speech Translation System Leveraged by Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | ***LLaST*** is a framework for building high-performance Large Language model based Speech-to-text Translation systems. |
| Approach: | They propose a framework for building high-performance Large Language model based Speech-to-text Translation systems. |
| Outcome: | The proposed model outperforms the CoVoST-2 benchmark and showcases exceptional scaling capabilities powered by LLMs. |
Redefining Machine Simultaneous Interpretation: From Incremental Translation to Human-Like Strategies (2026.findings-acl)
Copied to clipboard
| Challenge: | Simultaneous machine translation requires high-quality translations under strict real-time constraints. |
| Approach: | They extend the action space of simultaneous machine translation with four adaptive actions . they adapt these actions in a large language model framework and construct training references . |
| Outcome: | The proposed framework improves semantic metrics and achieves lower delay compared to reference translations and salami-based baselines. |
Evaluating the Robustness of Discrete Prompts (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing methods that generate discrete prompts from a small set of training instances have reported superior performance, but manual writing prompts that generalize well is challenging due to several reasons. |
| Approach: | They propose to use discrete prompts to learn lexical constructs that would not be encountered in manually-written prompts. |
| Outcome: | The proposed method is robust against perturbations to NLI inputs but sensitive to other types of perturbations such as shuffling and deletion of prompt tokens. |
NAIST-SIC-Aligned: An Aligned English-Japanese Simultaneous Interpretation Corpus (2024.lrec-main)
Copied to clipboard
| Challenge: | Simultaneous interpretation data is a task where an utterance is translated in real-time. |
| Approach: | They propose to use an automatically-aligned parallel English-Japanese SI dataset to make it suitable for model training. |
| Outcome: | The proposed model improves translation quality and latency over baselines. |
Emotional Speech Corpus for Persuasive Dialogue System (2020.lrec-1)
Copied to clipboard
| Challenge: | Emotional expressions can be used to express the speaker’s emotion more directly than using only emotion expression in the text. |
| Approach: | They built a speech dialogue corpus in a persuasive scenario that uses emotional expressions to build a system with emotional expression. |
| Outcome: | The proposed system can express the speaker's emotion more directly than using only emotion expression in the text, and the results show that the collected emotional expressions with their speeches have higher emotional expressiveness for expressing the system's emotions to users. |
Dialogue Scenario Collection of Persuasive Dialogue with Emotional Expressions via Crowdsourcing (L18-1)
Copied to clipboard
| Challenge: | Existing methods for data collection and annotation are costly and prevent launching new dialogue systems. |
| Approach: | They asked crowd workers to create persuasive dialogue systems using emotional expressions . they annotated emotional states and users' acceptance for system persuasion . |
| Outcome: | The proposed system has sufficient agreement even without training, the researchers found . the experiment showed that the collected data are comparable to real-world dialogue recording methods . |
Improving Spoken Language Understanding by Wisdom of Crowds (2020.coling-main)
Copied to clipboard
| Challenge: | Existing systems that use statistical approaches to improve spoken language understanding (SLU) lack of training data is an important problem, especially for new system tasks. |
| Approach: | They propose to use crowdsourcing and knowledge community websites to augment the spoken language understanding system by collecting paraphrasing variations for new system tasks and augmented them using similar questions from a knowledge community website. |
| Outcome: | The proposed architecture augmented more than 120,000 samples to improve accuracies even with small seed data. |
Reflection-based Word Attribute Transfer (2020.acl-srw)
Copied to clipboard
| Challenge: | Existing word embeddings represent analogic relations to change attributes, such as gender, such that king is male. |
| Approach: | They propose a method for word attribute transfer based on reflection mappings without such an analogy operation. |
| Outcome: | The proposed method can transfer attributes of the given words without changing the words that do not have the target attributes. |
TransLLaMa: LLM-based Simultaneous Translation System (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Decoder-only large language models have limited applications in simultaneous machine translation . naively translating each source word immediately results in compromised target quality . |
| Approach: | a study shows that a pre-trained open-source LLM can control input segmentation directly by generating a special "wait" token. |
| Outcome: | a new open-source model can control input segmentation directly by generating a special "wait" token. |
Enhancing Contextual Word Representations Using Embedding of Neighboring Entities in Knowledge Graphs (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods for pre-trained language models lack explicit grounding in real-world entities. |
| Approach: | They propose a mechanism that integrates the structure of a KG into recent PLM architectures by generalizing the embeddings of neighboring entities. |
| Outcome: | The proposed method improves a classification task, entity typing task and language comprehension tasks. |
Subspace Representations for Soft Set Operations and Sentence Similarities (2024.naacl-long)
Copied to clipboard
| Challenge: | Embedding-based word representations are crucial for capturing the semantic meanings of individual words. |
| Approach: | They propose to embed word sets and corresponding set operations within pre-trained word embedding spaces. |
| Outcome: | The proposed representations outperform vector-based representations in sentence similarity and set retrieval tasks. |
Guiding Neural Machine Translation with Retrieved Translation Pieces (N18-1)
Copied to clipboard
| Challenge: | Neural machine translation (NMT) has trouble with lowfrequency words or phrases and generalizing across domains. |
| Approach: | They propose a method for recalling low-frequency words and phrases into neural machine translation by retrieving n-grams from a search engine and incorporating them into the decoding process. |
| Outcome: | The proposed method improves translation results up to 6 BLEU points on three narrow domain translation tasks where repetitiveness of the target sentences is particularly salient. |