REVIEW 8 cited by
COMET: A Neural Framework for MT Evaluation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
We present COMET, a neural framework for training multilingual machine translation evaluation models which obtains new state-of-the-art levels of correlation with human judgements. Our framework leverages recent breakthroughs in cross-lingual pretrained language modeling resulting in highly multilingual and adaptable MT evaluation models that exploit information from both the source input and a target-language reference translation in order to more accurately predict MT quality. To showcase our framework, we train three models with different types of human judgements: Direct Assessments, Human-mediated Translation Edit Rate and Multidimensional Quality Metrics. Our models achieve new state-of-the-art performance on the WMT 2019 Metrics shared task and demonstrate robustness to high-performing systems.
Forward citations
Cited by 8 Pith papers
-
GigaSpeechBench: A Real-World Multilingual Speech-to-Text Benchmark
GigaSpeechBench is a new 680-hour in-the-wild multilingual ASR/AST benchmark with five modules for low-resource languages, Chinese dialects, English accents, domain terminology, and age-varied speech, showing model pe...
-
Seed LiveInterpret 2.0: End-to-end Simultaneous Speech-to-speech Translation with Your Voice
An end-to-end simultaneous speech-to-speech translation model with voice cloning, trained with a two-stage reinforcement learning reward scheme, reports high accuracy and low latency on the authors' RealSI benchmark.
-
Beyond N-Grams: Rethinking Evaluation Metrics and Strategies for Multilingual Abstractive Summarization
Across eight languages, n-gram metrics such as ROUGE correlate less with human ratings in fusional languages than in isolating and agglutinative ones, while the neural metric COMET correlates better, especially in low...
-
Reasoning Before Translation: Enhancing Legal Machine Translation with Structured Reasoning
On Swiss legal translation, reinforcement learning with a ChrF reward improves small open models more than supervised fine-tuning, but frontier reasoning models still score higher.
-
Introducing the Swiss Food Knowledge Graph: AI for Context-Aware Nutrition Recommendation
The paper introduces SwissFKG, a knowledge graph integrating Swiss recipes, nutrients, allergens, and dietary guidelines, populated via an LLM pipeline and used for a Graph-RAG question answering demo.
-
Psychology-Driven Enhancement of Humour Translation
A decomposition-and-recomposition prompt method for humor translation reports large gains on LLM-based metrics, but the evaluation lacks human validation and statistical checks.
-
An Empirical Study of LLM-as-a-Judge: How Design Choices Impact Evaluation Reliability
The reliability of LLM-as-a-Judge depends strongly on scoring rubrics and reference answers; sampling with averaging outperforms greedy decoding, and chain-of-thought reasoning adds little when rubrics are clear.
-
From Sentences to Sequences: Rethinking Languages in Biological System
A new RNA inverse folding model (RiFold) using stochastic-order decoding and structure-aware metrics outperforms prior methods, and the paper shows sequence recovery and structural recovery are correlated but not equivalent.
Discussion (0). Sign in to comment.