Papers with Code 아카이브
Machine Translation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 10
- 평가표
- 84
- 보존된 평가 기록
- 438
Machine translation is the task of translating a sentence in a source language to a different target language.
Approaches for machine translation can range from rule-based to statistical to neural-based. More recently, encoder-decoder attention-based architectures like BERT have attained major improvements in machine translation.
One of the most popular datasets used to benchmark machine translation systems is the WMT family of datasets. Some of the most commonly used evaluation metrics for machine translation systems include BLEU, METEOR, NIST, and others.
<span style="color:grey; opacity: 0.6">( Image credit: Google seq2seq )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/facebookresearch/covost
공식 코드CoVoST 2 and Massively Multilingual Speech-to-Text Translation
https://github.com/facebookresearch/deit
공식 코드ResMLP: Feedforward networks for image classification with data-efficient training
https://github.com/facebookresearch/evaluation-of-nmt-bt
공식 코드On The Evaluation of Machine Translation Systems Trained With Back-Translation
https://github.com/facebookresearch/fairscale/blob/main/fairscale/experimental/nn/data_parallel/gossip/distributed.py
공식 코드SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum
https://github.com/facebookresearch/fairseq
공식 코드https://github.com/facebookresearch/flores
공식 코드https://github.com/facebookresearch/mega
공식 코드https://github.com/facebookresearch/mlqe
공식 코드Unsupervised Quality Estimation for Neural Machine Translation
https://github.com/facebookresearch/seamless_communication
공식 코드SeamlessM4T: Massively Multilingual & Multimodal Machine Translation
https://github.com/facebookresearch/sonar
공식 코드SONAR: Sentence-Level Multimodal and Language-Agnostic Representations
https://github.com/facebookresearch/stopes
공식 코드No Language Left Behind: Scaling Human-Centered Machine Translation
https://github.com/facebookresearch/ternary_binary_transformer
공식 코드https://github.com/facebookresearch/text-simplification-evaluation
공식 코드Reference-less Quality Estimation of Text Simplification Systems
https://github.com/facebookresearch/transformer-sequential
공식 코드Addressing Some Limitations of Transformers with Feedback Memory
https://github.com/facebookresearch/vizseq
공식 코드https://github.com/fadedcosine/knn-kd
공식 코드Nearest Neighbor Knowledge Distillation for Neural Machine Translation
https://github.com/faiyazkhan11/ban-cap
공식 코드BAN-Cap: A Multi-Purpose English-Bangla Image Descriptions Dataset
https://github.com/fajri91/minangNLP
공식 코드https://github.com/fallcat/stupidNMT
공식 코드Hard-Coded Gaussian Attention for Neural Machine Translation
https://github.com/fandongmeng/DTMT_InDec
공식 코드DTMT: A Novel Deep Transition Architecture for Neural Machine Translation
https://github.com/fangleigit/RetroSub
공식 코드Leveraging Reaction-aware Substructures for Retrosynthesis Analysis
https://github.com/fanny-jourdan/FairTranslate
공식 코드https://github.com/fanqiwan/fusellm
공식 코드https://github.com/fantabulous-j/class
공식 코드Pre-training Cross-lingual Open Domain Question Answering with Large-scale Synthetic Supervision
https://github.com/farhandhanani/mlmac
공식 코드https://github.com/fatemeh-azadi/unsupervised-qe
공식 코드Mismatching-Aware Unsupervised Translation Quality Estimation For Low-Resource Languages
https://github.com/fdalvi/NeuroX
공식 코드What Is One Grain of Sand in the Desert? Analyzing Individual Neurons in Deep NLP Models
https://github.com/fe1ixxu/BiBERT
공식 코드BERT, mBERT, or BiBERT? A Study on Contextualized Embeddings for Neural Machine Translation
https://github.com/fe1ixxu/alma
공식 코드A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models
https://github.com/fe1ixxu/cd_id_mmt
공식 코드Language-Aware Multilingual Machine Translation with Self-Supervised Learning
https://github.com/fe1ixxu/intra-distillation
공식 코드The Importance of Being Parameters: An Intra-Distillation Method for Serious Gains
https://github.com/fe1ixxu/lms_fd
공식 코드Condensing Multilingual Knowledge with Lightweight Language-Specific Modules
https://github.com/fe1ixxu/stratified_mixture_of_experts
공식 코드Towards Being Parameter-Efficient: A Stratified Sparsely Activated Transformer with Dynamic Capacity
https://github.com/feiwang3311/Lantern
공식 코드Demystifying Differentiable Programming: Shift/Reset the Penultimate Backpropagator
https://github.com/flc777/glat
공식 코드Glancing Transformer for Non-Autoregressive Neural Machine Translation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.