paper-with-me

홈 › Papers

HUME: Human UCCA-Based Evaluation of Machine Translation

2016-06-30 · EMNLP 2016 11 · Alexandra Birch, Omri Abend, Ondrej Bojar, Barry Haddow

Human evaluation of machine translation normally uses sentence-level measures such as relative ranking or adequacy scales. However, these provide no insight into possible errors, and do not scale well with sentence length. We argue for a semantics-based evaluation, which captures what meaning components are retained in the MT output, thus providing a more fine-grained analysis of translation quality, and enabling the construction and tuning of semantics-based MT. We present a novel human semantic evaluation measure, Human UCCA-based MT Evaluation (HUME), building on the UCCA semantic representation scheme. HUME covers a wider range of semantic phenomena than previous methods and does not rely on semantic annotation of the potentially garbled MT output. We experiment with four language pairs, demonstrating HUME's broad applicability, and report good inter-annotator agreement rates and correlation with human adequacy scores.

📄 PDF Abstract BibTeX arXiv:1607.00030

Code (1)

bhaddow/hume-emnlp16 공식 구현

Tasks

Machine TranslationSentenceTranslation

Similar Papers 제목 키워드 기반

Incorporate Semantic Structures into Machine Translation Evaluation via UCCA

2020-10-17 · WMT (EMNLP) 2020 11 · Jin Xu, Yinuo Guo, Junfeng Hu

Copying mechanism has been commonly used in neural paraphrasing networks and other text generation tasks, in which some important words in the input sequence are preserved in the output sequence. Similarly, in machine tr…

Machine TranslationSentenceSentence SimilarityText Generation+1

VolHuMe: a High-Resolution Large Scale Dataset of Volumetric Human Meshes

2026-06-22 · Giulia Martinelli, Niccolò Bisagno, Nicola Garau, Esa Rahtu 외 arxiv

We introduce VolHuMe, a dataset of high-quality 4D human scans captured with a state-of-the-art volumetric studio using 64 RGB and 32 depth cameras. VolHuMe contains individual captures of 104 subjects and provides exten…

Point Clouds

MILE-RefHumEval: A Reference-Free, Multi-Independent LLM Framework for Human-Aligned Evaluation

2026-02-10 · Nalin Srun, Parisa Rastin, Guénaël Cabanes, Lydia Boudjeloud Assala arxiv

We introduce MILE-RefHumEval, a reference-free framework for evaluating Large Language Models (LLMs) without ground-truth annotations or evaluator coordination. It leverages an ensemble of independently prompted evaluato…

Image Captioning

HUMEMBR: Learning Human Routines for Predictive Embodied Navigation

2026-06-29 · Samira Huber, Klaas Pelzer, Duc M. Nguyen, Xuesu Xiao 외 arxiv

Understanding and navigating human-centered environments over extended periods of time while considering human behavior and routines remains a fundamental challenge in robotics. In real-world settings, robots may be aske…

Question Answering

Meaning Representation of Numeric Fused-Heads in UCCA

2021-06-04 · Ruixiang Cui, Daniel Hershcovich

We exhibit that the implicit UCCA parser does not address numeric fused-heads (NFHs) consistently, which could result either from inconsistent annotation, insufficient training data or a modelling limitation. and show wh…

Machine TranslationNatural Language InferenceQuestion AnsweringTranslation