paper-with-me

Papers

How Does Distilled Data Complexity Impact the Quality and Confidence of Non-Autoregressive Machine Translation?

2021-05-27 · Findings (ACL) 2021 8 · Weijia Xu, Shuming Ma, Dongdong Zhang, Marine Carpuat

While non-autoregressive (NAR) models are showing great promise for machine translation, their use is limited by their dependence on knowledge distillation from autoregressive models. To address this issue, we seek to understand why distillation is so effective. Prior work suggests that distilled training data is less complex than manual translations. Based on experiments with the Levenshtein Transformer and the Mask-Predict NAR models on the WMT14 German-English task, this paper shows that different types of complexity have different impacts: while reducing lexical diversity and decreasing reordering complexity both help NAR learn better alignment between source and target, and thus improve translation quality, lexical diversity is the main reason why distillation increases model confidence, which affects the calibration of different NAR models differently.

📄 PDF Abstract BibTeX arXiv:2105.12900

Code (0)

등록된 구현이 없습니다.

Tasks

DiversityKnowledge DistillationMachine TranslationTranslation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Does Knowledge Distillation Matter for Large Language Model based Bundle Generation?

2025-04-24 · Kaidong Feng, Zhu Sun, Jie Yang, Hui Fang 외

LLMs are increasingly explored for bundle generation, thanks to their reasoning capabilities and knowledge. However, deploying large-scale LLMs introduces significant efficiency challenges, primarily high computational c…

In-Context LearningKnowledge DistillationLanguage ModelingLanguage Modelling+1

eDifFIQA: Towards Efficient Face Image Quality Assessment Based On Denoising Diffusion Probabilistic Models

2024-03-12 · IEEE TBIOM (Transactions on Biometrics, Behavior, and Identity Science) 2024 3 · Žiga Babnik, Peter Peer, Vitomir Štruc

State-of-the-art Face Recognition (FR) models perform well in constrained scenarios, but frequently fail in difficult real-world scenarios, when no quality guarantees can be made for face samples. For this reason, Face I…

DenoisingFace Image QualityFace Image Quality AssessmentFace Recognition+3

Kandinsky 3.0 Technical Report

2023-12-06 · Vladimir Arkhipkin, Andrei Filatov, Viacheslav Vasilev, Anastasia Maltseva 외

We present Kandinsky 3.0, a large-scale text-to-image generation model based on latent diffusion, continuing the series of text-to-image Kandinsky models and reflecting our progress to achieve higher quality and realism …

Image GenerationImage to Video GenerationSuper-ResolutionText to Image Generation+2

An investigation of structures responsible for gender bias in BERT and DistilBERT

2024-01-12 · Thibaud Leteno, Antoine Gourru, Charlotte Laclau, Christophe Gravier

In recent years, large Transformer-based Pre-trained Language Models (PLM) have changed the Natural Language Processing (NLP) landscape, by pushing the performance boundaries of the state-of-the-art on a wide variety of …

AttributeFairness

Analyzing Knowledge Distillation in Neural Machine Translation

2018-10-01 · IWSLT (EMNLP) 2018 10 · Dakun Zhang, Josep Crego, Jean Senellart

Knowledge distillation has recently been successfully applied to neural machine translation. It allows for building shrunk networks while the resulting systems retain most of the quality of the original model. Despite th…

Knowledge DistillationMachine TranslationTranslation