alignment-with-openfst
Crf Autoencoder Framework
An implementation of the CRF autoencoder framework for tasks in natural language processing and machine translation
21 stars
19 watching
8 forks
Language: C++
last commit: about 8 years ago
Linked from 1 awesome list
Related projects:
| Repository | Description | Stars |
|---|---|---|
 richardlitt/ldc-word-aligner | A Python-based tool for annotating manual word alignments in parallel texts. | 2 |
 liyuanlucasliu/lm-lstm-crf | A PyTorch-based tool for sequence labeling using a combination of CRF and LSTM models to capture label dependencies and leverage contextualized representations. | 846 |
 rlhf-v/rlhf-v | Aligns large language models' behavior through fine-grained correctional human feedback to improve trustworthiness and accuracy. | 245 |
 pprett/nut | A toolkit for natural language understanding and machine learning | 118 |
| richardlitt/lrl | Developing tools and scripts to extract data from low-resource languages, focusing on language processing and machine learning applications. | 2 |
 aidc-ai/ovis | An MLLM architecture designed to align visual and textual embeddings through structural alignment | 575 |
| ldmt-muri/morpholm | This project develops language models that incorporate morphological knowledge to improve their understanding of linguistic structures and relationships. | 3 |
 cbcrg/mta-nf | Automates multiple sequence alignment by evaluating and selecting the best guide tree variations | 2 |
 artificiai/multilingual-latent-dirichlet-allocation-lda | An LDA-based text clustering pipeline for multiple languages | 82 |
| ldmt-muri/kin-morph-fst | An analysis tool for breaking down words into their component parts in the Kinyarwanda language | 6 |
 moses-smt/giza-pp | A toolkit for training statistical machine translation models and word alignment. | 264 |
 melih-unsal/demogpt | A comprehensive toolset for building Large Language Model (LLM) based applications | 1,733 |
 lefnord/rstt | A Ruby wrapper around the Stuttgarter Tree Tagger for natural language processing tasks | 6 |
 kuhumcst/cstlemma | A lemmatiser tool for multiple languages using affix rules and supervised learning from full-form dictionaries. | 36 |
 kimtaro/ve | A linguistic framework for natural language processing tasks. | 216 |