https://github.com/wjko2/NMT-Adapt
공식 코드Adapting High-resource NMT Models to Translate Low-resource Related Languages without Parallel Data
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/wjmacro/continualmt
공식 코드F-MALLOC: Feed-forward Memory Allocation for Continual Learning in Neural Machine Translation
https://github.com/wjxts/regularizedbn
공식 코드Understanding the Failure of Batch Normalization for Transformers in NLP
https://github.com/wmt-conference/ErrorSpanAnnotation
공식 코드Error Span Annotation: A Balanced Approach for Human Evaluation of Machine Translation
https://github.com/wns823/NMT_SSP
공식 코드https://github.com/wojzaremba/lstm
공식 코드https://github.com/wssun/eacs
공식 코드An Extractive-and-Abstractive Framework for Source Code Summarization
https://github.com/wszlong/sb-nmt
공식 코드https://github.com/wtma/PR-Embedding
공식 코드Conversational Word Embedding for Retrieval-Based Dialog System
https://github.com/wujunjie1998/btpgbt
공식 코드Towards General Error Diagnosis via Behavioral Testing in Machine Translation
https://github.com/wujunjie1998/twga
공식 코드Rethinking Targeted Adversarial Attacks For Neural Machine Translation
https://github.com/wwxu21/CER-MT
공식 코드https://github.com/wxjiao/Data-Rejuvenation
공식 코드Data Rejuvenation: Exploiting Inactive Training Examples for Neural Machine Translation
https://github.com/wxjiao/UncSamp
공식 코드Self-Training Sampling with Monolingual Data Uncertainty for Neural Machine Translation
https://github.com/wxjiao/is-chatgpt-a-good-translator
공식 코드https://github.com/wxjiao/parrot
공식 코드https://github.com/wxjiao/wmt2022-large-scale-african
공식 코드Tencent's Multilingual Machine Translation System for WMT22 Large-Scale African Languages
https://github.com/wxy-nlp/multitasknat
공식 코드https://github.com/xdqkid/S2S-AMR-Parser
공식 코드Improving AMR Parsing with Sequence-to-Sequence Pre-training
https://github.com/xiaomi/simust-c
공식 코드Rethinking the Reasonability of the Test Set for Simultaneous Machine Translation
https://github.com/xiaoyi0814/canmt
공식 코드https://github.com/xijiu9/Train_Transformers_with_INT4
공식 코드https://github.com/xingniu/multitask-ft-fsmt
공식 코드Multi-Task Neural Models for Translating Between Styles Within and Across Languages
https://github.com/xingniu/sockeye
공식 코드Bi-Directional Differentiable Input Reconstruction for Low-Resource Neural Machine Translation
https://github.com/xl2248/csa-nct
공식 코드Towards Making the Most of Dialogue Characteristics for Neural Chat Translation
https://github.com/xl2248/msctd
공식 코드https://github.com/xl2248/vhm
공식 코드A Variational Hierarchical Model for Neural Cross-Lingual Summarization
https://github.com/xl8-ai/wordsimt
공식 코드Enhanced Simultaneous Machine Translation with Word-level Policies
https://github.com/xlhex/SceneGraphModification
공식 코드https://github.com/xlhex/dpe
공식 코드Dynamic Programming Encoding for Subword Segmentation in Neural Machine Translation
https://github.com/xlhex/nlg_api_watermark
공식 코드Protecting Intellectual Property of Language Generation APIs with Lexical Watermark
https://github.com/xllyu-nlp/dempt
공식 코드https://github.com/xllyu-nlp/docia
공식 코드DoCIA: An Online Document-Level Context Incorporation Agent for Speech Translation
https://github.com/xrc10/unsup-cross-lingual-embedding-transfer
공식 코드Unsupervised Cross-lingual Transfer of Word Embedding Spaces
https://github.com/xtinkt/editable
공식 코드https://github.com/xu1998hz/sescore
공식 코드Not All Errors are Equal: Learning Text Generation Metrics using Stratified Error Synthesis
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.