In this paper, we study a new learning paradigm for Neural Machine Translation (NMT). Instead of maximizing the likelihood of the human translation as in previous works, we minimize the distinction between human translation and the translation given by an NMT model. To achieve this goal, inspired by the recent success …
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
169,181 papers · 148 categories
Trend · papers per month
48 results for “NMT Quality”
Improves NMT with user feedback from eBay ratings and search tasks.
problem Improving neural machine translation quality with user feedback.
method Offline bandit learning of NMT parameters using real user feedback from eBay.
result Implicit task-based feedback from cross-lingual search tasks improves NMT quality.
Paper aims to improve education online in South Africa using NMT for Setswana.
problem Inclusion of machine translation for low-resourced local languages in online education.
method Demonstrates state-of-the-art performance on English-to-Setswana translation using the Transformer architecture.
result Current NMT techniques show promise for African languages, beating previous methods by 5.33 BLEU points.
This paper improves neural machine translation training by selecting and denoising data.
problem Reduces negative impact of noisy data on neural machine translation training.
method Measures and selects domain data, applies denoising curriculum using online data selection.
result Significant effectiveness for training on noisy data.
Paper examines NMT robustness to nonsensical inputs.
problem NMT systems fail when source sentences are altered.
method Soft-attention technique to replace words in source sentences.
result Proposed technique achieves high success rate and outperforms existing methods.
Proposes a method to generate diverse translations by conditioning on target domain.
problem NMT models lack diversity in translations, even with search algorithms.
method Condition the decoder on a latent variable representing target domain, generated by a target encoder.
result Generated diverse translations without affecting performance or training time.
Dynamic segmentation algorithm improves NMT performance by favoring character-level processing.
problem Suboptimal static segmentation choices in NMT systems.
method Adaptive Computation Time algorithm for dynamic segmentation, trainable end-to-end.
result The model prefers character-level processing when given the freedom to navigate different segmentation levels.
Study improves calibration of NMT models, especially EOS and attention uncertainty.
problem Improper functioning of beam-search inference due to miscalibrated NMT models.
method Design and apply recalibration methods based on EOS and attention uncertainty signals.
result Improved accuracy and better sequence-level calibration of NMT models.
EBR improves NMT by re-ranking samples drawn from MLE-trained models.
problem Discrepancy between MLE and BLEU score in neural machine translation.
method Train an energy-based model to mimic BLEU score, then use it for re-ranking.
result EBR consistently improves NMT performance by +4 BLEU points on IWSLT'14 German-English.
Paper uses NMT to predict solutions to stochastic optimization problems quickly.
problem Predicting solutions to stochastic discrete optimization problems under uncertainty.
method Applied a state-of-the-art NMT algorithm with minimal adaptations and hyperparameter tuning.
result NMT can produce accurate solutions in milliseconds with less variability.
Study finds optimal vocabulary size for neural machine translation.
problem Imbalanced class distribution in language data affects NMT performance.
method Casts NMT as a classification task, analyzes vocabulary sizes, and tests multiple languages.
result Certain vocabulary sizes outperform others, explaining NMT performance.
Improves NMT performance on diverse datasets without forgetting.
problem Catastrophic forgetting in NMT models on heterogeneous datasets.
method Non-parametric n-gram level retrieval combined with expressive neural network.
result Gains on all evaluation sets on a heterogeneous dataset.
Study on RL from human bandit feedback for sequence-to-sequence learning, showing reliability and learnability.
problem Reliability and learnability of human bandit feedback for RL from sequence-to-sequence learning.
method Investigated reliability of human bandit feedback, analyzed influence on reward estimator learnability, and tested improvements with regression-based reward estimator.
result Improvements of over 1 BLEU can be achieved by integrating a regression-based reward estimator trained on cardinal feedback into RL for NMT.
Tensor Train layer improves BLEU scores in NMT models.
problem Improving Neural Machine Translation (NMT) models' performance.
method Implemented Tensor Train layer in TensorFlow for NMT training.
result Higher learning rates and more 'rectangular' core dimensions improve BLEU scores.
An NMT system for Indic languages outperforms Google Translate.
problem Challenges in translating Indic languages efficiently.
method Encoder-decoder with attention mechanism for neural machine translation.
result Outperforms Google Translate with a 6 BLEU score margin on English-Gujarati translation.
This paper proposes a curriculum learning framework for NMT to reduce training time and improve performance.
problem Slow training and need for heuristics in NMT systems.
method A curriculum learning framework that decides training samples based on estimated difficulty and model competence.
result Up to 70% decrease in training time and up to 2.2 BLEU accuracy improvements.
This paper tackles rare word problem in low-resource language pairs using NMT.
problem Rare word problem in neural machine translation, especially for low-resource languages.
method Three solutions: enhanced source context, morphology learning, and wordnet synonyms.
result Significant improvements in BLEU scores (+1.0 points) on English-Vietnamese and Japanese-Vietnamese.
This study improves NMT using reinforcement learning, overcoming its instability.
problem Stability issues in reinforcement learning for neural machine translation.
method Systematic study on reinforcement learning factors and a new method for monolingual data.
result Competitive results on WMT17 Chinese-English translation task, setting a state-of-the-art performance.
Sockeye is an open-source toolkit for neural machine translation.
problem Improving Neural Machine Translation (NMT) models and techniques.
method Scalable training and inference for three NMT architectures, including attentional, self-attentional, and fully convolutional networks.
result Sockeye achieves competitive BLEU scores across different NMT architectures, including a best score for its transformer implementation.
Improved GEC models use scored data from large pretraining to outperform.
problem Addressing data sparsity in Grammatical Error Correction.
method Derive example-level scores from a smaller, higher-quality dataset and incorporate delta-log-perplexity into training schedules.
result Models trained on scored data achieve state-of-the-art results.
A simple modification enables a universal NMT model with language-specific parameters.
problem Creating a universal NMT model that can adapt to different languages and domains.
method Introducing a contextual parameter generator (CPG) that dynamically adjusts model parameters based on source and target language embeddings.
result The system achieves state-of-the-art performance and zero-shot translation, demonstrating the effectiveness of the CPG.
In this paper, we present Neural Phrase-based Machine Translation (NPMT). Our method explicitly models the phrase structures in output sequences using Sleep-WAke Networks (SWAN), a recently proposed segmentation-based sequence modeling method. To mitigate the monotonic alignment requirement of SWAN, we introduce a new …
AutoLoss learns optimal schedules for alternating optimization tasks.
problem Optimizing different task objectives with alternating updates.
method Meta-learning framework to learn and determine the optimization schedule.
result AutoLoss improves convergence quality on multiple ML tasks.
Improves NMT by sampling context from predicted sequence during training.
problem Error accumulation and overcorrection in NMT due to mismatched training and inference contexts.
method Samples context words from both ground truth and predicted sequences during training.
result Significant improvements on multiple datasets, including Chinese->English and WMT'14 English->German.
CODE2SEQ generates natural language sequences from code snippets.
problem Generating natural language descriptions from code.
method CODE2SEQ represents code as AST paths and uses attention to select relevant paths.
result CODE2SEQ outperforms previous models for code-to-text tasks.
A new quantization strategy reduces Transformer model size and inference time.
problem Heavy computation load and memory overhead in Transformer models for mobile devices.
method Mixed precision quantization with varying bits per word in embedding blocks.
result 11.8x smaller model size and 3.5x speed up for on-device NMT.
New method improves likelihood-free parameter estimation in complex models.
problem Estimating parameters in simulation-based models with unknown likelihood.
method Nested multi-time-scale stochastic approximation (NMTS) method.
result Eliminates bias and accelerates convergence in likelihood-free inference.
Sparse Transformers degrade semantic information first, with early layers encoding more.
problem Understanding how sparse Transformers affect learned representations and semantic information.
method Probed Transformers with progressively pruned weights to observe changes in semantic information and model behavior.
result Complex semantic information is first to degrade in sparse Transformers, with early layers encoding more.
Paper tackles zero-shot translation by encouraging consistent agreement in models.
problem Challenges of generalizing multilingual translation without parallel data.
method Reformulated as probabilistic inference, introduced consistent agreement-based training.
result Agreement-based learning improves zero-shot translation by 2-3 BLEU points.
Paper introduces a method to assess liquidity risk in meme tokens using entity-linked address analysis.
problem High market volatility and vulnerability to manipulation in meme tokens.
method Multi-dimensional approach integrating fund flow analysis, behavioral similarity, and anomalous transaction detection.
result Significant disparities between apparent and actual liquidity in meme token markets.
TIMeSynC combines financial service interactions for intent prediction.
problem Aligning and learning from multi-domain, multi-resolution sequences for accurate intent prediction.
method An encoder-decoder transformer model addressing sequence alignment, temporal dynamics, and dynamic/static sequence combination.
result Significant improvement in intent prediction over existing methods.
Solution for voice conversion with limited data using hierarchical seq2seq and attention models.
problem Voice conversion between speakers with limited parallel audio pairs.
method Hierarchical sequence to sequence model with attention-based decoder, trained on single speaker dataset.
result Improved voice conversion quality using mel spectrograms and wavenet vocoder.
MLMs score better than autoregressive models without finetuning.
problem Improving language model scores without fine-tuning.
method Compute pseudo-log-likelihood scores (PLLs) by masking tokens one by one.
result PLLs outperform GPT-2 scores in various NLP tasks.
AirRL uses RL to infer urban air quality from selected stations.
problem Inferring fine-grained urban air quality from limited monitoring stations.
method Reinforcement learning model with a dynamic station selector and air quality regressor.
result AirRL achieves highest performance in air quality inference experiments.
Study on sparse recovery with mixed-quality data, establishing sample-size conditions.
problem Sparse recovery with heterogeneous noise from high- and low-quality sources.
method Establishes linear trade-off for sufficient conditions, analyzes LASSO algorithm.
result Linear trade-off for sufficient conditions, robustness of LASSO to data heterogeneity.
Protein structure prediction has been a grand challenge problem in the structure biology over the last few decades. Protein quality assessment plays a very important role in protein structure prediction. In the paper, we propose a new protein quality assessment method which can predict both local and global quality of …
Measures DNA quality degradation effects.
problem Identifying degraded DNA sequence data.
method Novel quality quantification based on intentional degradation effects.
result Quantified measures of degradation can be used for multiple purposes.
Automated MRI image quality assessment framework using machine learning.
problem Manual quality assessment of MRI images is time-consuming and costly.
method Machine learning model trained on human observer labels without reference images.
result Framework achieves 93.7% accuracy in estimating image quality.
Framework improves ML performance by identifying high-quality data.
problem Poor data quality hampers ML performance.
method Intelligent data-centric evaluation framework combining quality measurements and unsupervised learning.
result Framework improves ML system performance in real-world use case.
This note investigates the causes of the quality anomaly, which is one of the strongest and most scalable anomalies in equity markets. We explore two potential explanations. The "risk view", whereby investing in high quality firms is somehow riskier, so that the higher returns of a quality portfolio are a compensation …
Do-AIQ: A Design-of-Experiment Approach to Quality Evaluation of AI Mislabel Detection Algorithmstat.ML
Do-AIQ framework evaluates AI algorithms' quality using DOE.
problem Quality evaluation of AI mislabel detection algorithms.
method Design-of-experiment approach with high-dimensional constraint space design and surrogate modeling.
result Established framework for evaluating AI algorithm quality robustly.
A Technical Survey on Statistical Modelling and Design Methods for Crowdsourcing Quality Controlcs.HC
Survey bridges quality control mechanisms and statistical models for crowdsourcing.
problem Crowdsourcing quality control issues in machine learning systems.
method Unified frameworks for quality control mechanisms and statistical models.
result Taxonomies and future directions for quality control research.
Framework evaluates quality of synthetic data generated with differential privacy.
problem Ensuring synthetic data retains statistical quality after applying differential privacy.
method Developed a framework to evaluate synthetic data quality from a practical researcher's viewpoint.
result Synthetic data can be evaluated against training data or underlying populations, and for specific tasks like inference or prediction.
The impact of MRI image quality on statistical and predictive analysis on voxel based morphologyeess.IV
MRI image quality affects statistical and predictive analysis of brain morphology.
problem Impact of MRI image quality on statistical and predictive analysis of brain morphology.
method Systematic testing of image quality on univariate statistics and machine learning classification using three large datasets.
result Low-quality MRI data significantly affects detecting significant sex/gender differences in smaller samples, but not in larger ones.
The paper assesses quality measures for machine learning models using cross-validation.
problem Evaluating the accuracy and robustness of quality measures for machine learning models.
method Cross-validation approach to estimate prediction error and quantify explained variation. Confidence bounds and local quality measures derived from residuals.
result The reliability and robustness of quality measures are assessed through numerical examples and confidence bounds.
Automatically assesses the quality of online health articles.
problem Lack of automated tools to evaluate the quality of online health information.
method Data mining approach using 10 quality criteria and feature selection.
result Classifier achieved 84%-90% accuracy on 10 criteria.
Generative models predict page quality without training, useful for low-resource settings.
problem Detecting low-quality content in web articles.
method Human evaluation and analysis of 500 million web articles.
result Generative models can predict page quality without training, useful for low-resource settings.
Unified evaluation for both quality and diversity in NLP.
problem Measuring both quality and diversity in NLP models.
method Proposes HUSE, a metric combining human and statistical evaluation.
result HUSE detects both quality and diversity defects in NLP models.