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/lena-voita/the-story-of-heads
공식 코드Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned
https://github.com/lenacabrera/gb_mnmt
공식 코드https://github.com/leukas/charlevelmt
공식 코드Are Character-level Translations Worth the Wait? Comparing ByT5 and mT5 for Machine Translation
https://github.com/leukas/sdd
공식 코드Subword-Delimited Downsampling for Better Character-Level Translation
https://github.com/leukas/wmt21
공식 코드https://github.com/levelower/vfa
공식 코드https://github.com/lgcnsai/ps-kd-pytorch
공식 코드Self-Knowledge Distillation with Progressive Refinement of Targets
https://github.com/lhan87/hope
공식 코드https://github.com/libeineu/Context-Aware
공식 코드Does Multi-Encoder Help? A Case Study on Context-Aware Neural Machine Translation
https://github.com/libeineu/GPKD
공식 코드Learning Light-Weight Translation Models from Deep Transformer
https://github.com/libeineu/SDT-Training
공식 코드https://github.com/libeineu/fairseq_mmt
공식 코드https://github.com/libeineu/mmt-vqa
공식 코드https://github.com/libeineu/ode-transformer
공식 코드ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence Generation
https://github.com/lifu-tu/ENGINE
공식 코드ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation
https://github.com/lighteternal/PENELOPIE
공식 코드PENELOPIE: Enabling Open Information Extraction for the Greek Language through Machine Translation
https://github.com/lijiabei-7/leccr
공식 코드https://github.com/lilt/tec
공식 코드https://github.com/lin-tan/CURE
공식 코드CURE: Code-Aware Neural Machine Translation for Automatic Program Repair
https://github.com/linghao-jin/canmt-challenges
공식 코드https://github.com/linzehui/mRASP
공식 코드Pre-training Multilingual Neural Machine Translation by Leveraging Alignment Information
https://github.com/lioutasb/TaLKConvolutions
공식 코드https://github.com/lisasiyu/drtt
공식 코드https://github.com/lishaofeng/NLP_Backdoor
공식 코드https://github.com/lishuang-w/idiomkb
공식 코드https://github.com/litterbrother-xiao/overview-of-non-autoregressive-applications
공식 코드A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyond
https://github.com/lium-lst/nmtpy
공식 코드NMTPY: A Flexible Toolkit for Advanced Neural Machine Translation Systems
https://github.com/lium-lst/wmt17-newstask
공식 코드LIUM Machine Translation Systems for WMT17 News Translation Task
https://github.com/liuxubo717/v-act
공식 코드Visually-Aware Audio Captioning With Adaptive Audio-Visual Attention
https://github.com/liyc7711/doc2doc
공식 코드P-Transformer: Towards Better Document-to-Document Neural Machine Translation
https://github.com/locuslab/TCN
공식 코드An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
https://github.com/longyuewangdcu/document-mt-llm
공식 코드Document-Level Machine Translation with Large Language Models
https://github.com/longyuewangdcu/tvsub
공식 코드Learning to Remember Translation History with a Continuous Cache
https://github.com/lorelupo/divide-and-rule
공식 코드Divide and Rule: Effective Pre-Training for Context-Aware Multi-Encoder Translation Models
https://github.com/lorelupo/focused-concat
공식 코드Focused Concatenation for Context-Aware Neural Machine Translation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.