Papers with Code 아카이브
Language Modelling
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 6
- 평가표
- 55
- 보존된 평가 기록
- 466
A language model is a model of natural language. Language models are useful for a variety of tasks, including speech recognition, machine translation, natural language generation (generating more human-like text), optical character recognition, route optimization, handwriting recognition, grammar induction, and information retrieval.
Large language models (LLMs), currently their most advanced form, are predominantly based on transformers trained on larger datasets (frequently using words scraped from the public internet). They have superseded recurrent neural network-based models, which had previously superseded the purely statistical models, such as word n-gram language model.
Source: Wikipedia
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/bohanli/vae-pretraining-encoder
공식 코드A Surprisingly Effective Fix for Deep Latent Variable Modeling of Text
https://github.com/boknilev/asr-repr-analysis
공식 코드Analyzing Phonetic and Graphemic Representations in End-to-End Automatic Speech Recognition
https://github.com/bolajiy/golden-retriever
공식 코드https://github.com/bonaventuredossou/mlm_al
공식 코드AfroLM: A Self-Active Learning-based Multilingual Pretrained Language Model for 23 African Languages
https://github.com/bonaventuredossou/multitask_fon
공식 코드https://github.com/bootphon/spokenlm-phoneme
공식 코드Improving Spoken Language Modeling with Phoneme Classification: A Simple Fine-tuning Approach
https://github.com/bootphon/zerospeech2021_baseline
공식 코드https://github.com/booydar/lm-rmt
공식 코드https://github.com/booydar/t5-experiments
공식 코드https://github.com/booydar/transformer-xl
공식 코드https://github.com/bopan3/vis-shepherd
공식 코드VIS-Shepherd: Constructing Critic for LLM-based Data Visualization Generation
https://github.com/boracaglayan/bis-nl2sql
공식 코드BIS: NL2SQL Service Evaluation Benchmark for Business Intelligence Scenarios
https://github.com/borgwardtlab/pst
공식 코드https://github.com/borororo/zy-bert
공식 코드TCM-SD: A Benchmark for Probing Syndrome Differentiation via Natural Language Processing
https://github.com/boschresearch/autoclip
공식 코드AutoCLIP: Auto-tuning Zero-Shot Classifiers for Vision-Language Models
https://github.com/boschresearch/clin_x
공식 코드https://github.com/boschresearch/eurekaMoments
공식 코드Eureka-Moments in Transformers: Multi-Step Tasks Reveal Softmax Induced Optimization Problems
https://github.com/boschresearch/steps-parser
공식 코드https://github.com/boschresearch/switchprompt
공식 코드SwitchPrompt: Learning Domain-Specific Gated Soft Prompts for Classification in Low-Resource Domains
https://github.com/boschresearch/temporal-tagging-eacl
공식 코드Multilingual Normalization of Temporal Expressions with Masked Language Models
https://github.com/boscoj2008/adapterem
공식 코드https://github.com/bothe/dialogue-act-recognition
공식 코드A Context-based Approach for Dialogue Act Recognition using Simple Recurrent Neural Networks
https://github.com/boun-tabi-lmg/turkish-lm-tuner
공식 코드TURNA: A Turkish Encoder-Decoder Language Model for Enhanced Understanding and Generation
https://github.com/boun-tabi/generativelm-genes
공식 코드Generative Language Models on Nucleotide Sequences of Human Genes
https://github.com/bowang-lab/clinical-camel
공식 코드Clinical Camel: An Open Expert-Level Medical Language Model with Dialogue-Based Knowledge Encoding
https://github.com/bowang-lab/joint-ner-and-re
공식 코드End-to-end Named Entity Recognition and Relation Extraction using Pre-trained Language Models
https://github.com/bozheng-hit/vocapxlm
공식 코드Allocating Large Vocabulary Capacity for Cross-lingual Language Model Pre-training
https://github.com/bozhenhhu/a-review-of-plms-and-methods-for-protein-structure-prediction
공식 코드Protein Language Models and Structure Prediction: Connection and Progression
https://github.com/bplaut/llm-calibration-and-correctness-prediction
공식 코드Probabilities of Chat LLMs Are Miscalibrated but Still Predict Correctness on Multiple-Choice Q&A
https://github.com/bplaut/softmax-probs-predict-llm-correctness
공식 코드Probabilities of Chat LLMs Are Miscalibrated but Still Predict Correctness on Multiple-Choice Q&A
https://github.com/bpucla/sri_text
공식 코드https://github.com/bradleypallen/evaluating-kg-class-memberships-using-llms
공식 코드Evaluating Class Membership Relations in Knowledge Graphs using Large Language Models
https://github.com/bradleypallen/zero-shot-classifiers-for-conceptual-engineering
공식 코드https://github.com/bradyfu/awesome-multimodal-large-language-models
공식 코드https://github.com/brandeis-llc/L-CSTS
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.