STAR : Sentence Translation Alignment Rate for Document-to-Document Machine Translation
Large Language Models (LLMs) have enabled a shift from sentence-level to document-to-document (Doc2Doc) machine translation, promising improved global coherence. However, document-to-document generation in a single pass frequently suffers from structural misalignment, manifesting as sentence omissions or hallucinations that violate the core requirement of source-target correspondence. To address this, we introduce Sentence Translation Alignment Rate (STAR), an auxiliary metric that explicitly quantifies sentence-level structural fidelity. Building on this, we propose STAR-masked Preference Optimization (StarPO), a framework that ranks document-level hypotheses by structural quality and utilizes a dynamic alignment mask to focus optimization on misaligned segments. Experimental results across news and literary domains demonstrate that StarPO significantly enhances translation quality and structural integrity. Notably, StarPO allows compact models to surpass the performance of massive proprietary systems like GPT-4o while maintaining superior token efficiency.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationSimilar Papers 제목 키워드 기반
Extending Automatic Machine Translation Evaluation to Book-Length Documents
Despite Large Language Models (LLMs) demonstrating superior translation performance and long-context capabilities, evaluation methodologies remain constrained to sentence-level assessment due to dataset limitations, toke…
Machine TranslationSentAlign: Accurate and Scalable Sentence Alignment
We present SentAlign, an accurate sentence alignment tool designed to handle very large parallel document pairs. Given user-defined parameters, the alignment algorithm evaluates all possible alignment paths in fairly lar…
Machine TranslationSentenceTranslationSentence Alignment with Parallel Documents Facilitates Biomedical Machine Translation
Objective: Today's neural machine translation (NMT) can achieve near human-level translation quality and greatly facilitates international communications, but the lack of parallel corpora poses a key problem to the devel…
ArticlesMachine TranslationNMTSentence+3Non-Autoregressive Document-Level Machine Translation
Non-autoregressive translation (NAT) models achieve comparable performance and superior speed compared to auto-regressive translation (AT) models in the context of sentence-level machine translation (MT). However, their …
Document Level Machine TranslationMachine TranslationSentenceText Generation+1SpanAlign: Sentence Alignment Method based on Cross-Language Span Prediction and ILP
We propose a novel method of automatic sentence alignment from noisy parallel documents. We first formalize the sentence alignment problem as the independent predictions of spans in the target document from sentences in …
Machine TranslationSentenceSentence EmbeddingsTranslation