https://github.com/sdadas/polish-roberta
공식 코드Pre-training Polish Transformer-based Language Models at Scale
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/seamusl/gahealth
공식 코드https://github.com/seanie12/CLAPS
공식 코드Contrastive Learning with Adversarial Perturbations for Conditional Text Generation
https://github.com/sebastian-nehrdich/byt5-sanskrit-analyzers
공식 코드One Model is All You Need: ByT5-Sanskrit, a Unified Model for Sanskrit NLP Tasks
https://github.com/sebastianruder/latent-variable-vecmap
공식 코드A Discriminative Latent-Variable Model for Bilingual Lexicon Induction
https://github.com/securedl/arabic_jailbreak
공식 코드https://github.com/seekingdream/nmtsloth
공식 코드LLMEffiChecker: Understanding and Testing Efficiency Degradation of Large Language Models
https://github.com/seyoungsong/classical-chinese-transfer
공식 코드When Does Classical Chinese Help? Quantifying Cross-Lingual Transfer in Hanja and Kanbun
https://github.com/seyoungsong/hanja-platform
공식 코드HERITAGE: An End-to-End Web Platform for Processing Korean Historical Documents in Hanja
https://github.com/sfu-natlang/SFUTranslate
공식 코드Better Neural Machine Translation by Extracting Linguistic Information from BERT
https://github.com/sfu-natlang/attention_explanation
공식 코드Interrogating the Explanatory Power of Attention in Neural Machine Translation
https://github.com/sh1doy/summarization_tf
공식 코드https://github.com/shachardon/prequel
공식 코드PreQuEL: Quality Estimation of Machine Translation Outputs in Advance
https://github.com/shadoom7/hallucination_research
공식 코드https://github.com/shadowkiller33/parascore
공식 코드https://github.com/shahparth123/eng_guj_parallel_corpus
공식 코드Neural Machine Translation System of Indic Languages -- An Attention based Approach
https://github.com/shamilcm/pedra
공식 코드https://github.com/shantipriyap/hausavqa
공식 코드HaVQA: A Dataset for Visual Question Answering and Multimodal Research in Hausa Language
https://github.com/sharif-slpl/se-2024-task-06-shroom
공식 코드SLPL SHROOM at SemEval2024 Task 06: A comprehensive study on models ability to detect hallucination
https://github.com/shark-nlp/attentivemlp
공식 코드Attentive Multi-Layer Perceptron for Non-autoregressive Generation
https://github.com/shark-nlp/cont
공식 코드https://github.com/shark-nlp/openicl
공식 코드https://github.com/shashiongithub/Split-and-Rephrase
공식 코드https://github.com/shawnkx/NAT-with-Local-AT
공식 코드Incorporating a Local Translation Mechanism into Non-autoregressive Translation
https://github.com/sheffieldnlp/deepQuest-py
공식 코드https://github.com/sheffieldnlp/mlqe-pe
공식 코드MLQE-PE: A Multilingual Quality Estimation and Post-Editing Dataset
https://github.com/shenbinqian/hadqaet
공식 코드https://github.com/shennong-program/mlmd
공식 코드https://github.com/shennong-program/pycgs
공식 코드https://github.com/shennong-program/shennongname
공식 코드https://github.com/shentianxiao/language-style-transfer
공식 코드https://github.com/shesterg/jwsign-machine-translation
공식 코드https://github.com/shifts-project/shifts
공식 코드Shifts 2.0: Extending The Dataset of Real Distributional Shifts
https://github.com/shijie-wu/neural-transducer
공식 코드https://github.com/shijing001/ffn_corpus
공식 코드FFN: a Fine-grained Chinese-English Financial Domain Parallel Corpus
https://github.com/shininglab/systematic-generalization-via-meaningful-learning
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.