Papers with Code 아카이브

Language Modeling

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

1

평가표

0

보존된 평가 기록

0

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/soarsmu/BiasFinder

How to Fine-Tune BERT for Text Classification?

https://github.com/sobhan-moosavi/characterizingdrivingstyleswithdeeplearning

A Simple Way to Initialize Recurrent Networks of Rectified Linear Units

https://github.com/socc-io/piqaboo

Semi-supervised Sequence Learning

https://github.com/social-ai-studio/matk

VisualBERT: A Simple and Performant Baseline for Vision and Language

https://github.com/sohanpatnaik106/cabinet_qa

TAPEX: Table Pre-training via Learning a Neural SQL Executor

https://github.com/soheil/DeepKeyAttack

A Practical Deep Learning-Based Acoustic Side Channel Attack on Keyboards

https://github.com/solkx/tkdp

TKDP: Threefold Knowledge-enriched Deep Prompt Tuning for Few-shot Named Entity Recognition

https://github.com/somiltg/xquad

On the Cross-lingual Transferability of Monolingual Representations

https://github.com/sooftware/Attention-Implementation

Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context

https://github.com/sooftware/End-to-End-Speech-Recognition-Models

Listen, Attend and Spell

https://github.com/sooftware/End-to-end-Speech-Recognition

Listen, Attend and Spell

https://github.com/sooftware/Fairseq-Listen-Attend-Spell

Listen, Attend and Spell

https://github.com/sooftware/OpenSpeech

Listen, Attend and Spell

https://github.com/sooftware/attentions

Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context

https://github.com/sooftware/conformer

Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context

https://github.com/sooftware/jasper-pytorch

Jasper: An End-to-End Convolutional Neural Acoustic Model

https://github.com/sooftware/luna-transformer

Luna: Linear Unified Nested Attention

https://github.com/sooftware/nlp-attentions

Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context

https://github.com/sooheon/perceiver-jax

ReZero is All You Need: Fast Convergence at Large Depth

https://github.com/soumimaiti/speechlmscore_tool

SpeechLMScore: Evaluating speech generation using speech language model

https://github.com/souvikshanku/translit-former

Processing South Asian Languages Written in the Latin Script: the Dakshina Dataset

https://github.com/soyoung97/awd-lstm-gru

Improving Neural Language Models with a Continuous Cache

https://github.com/soyoung97/fairseq-mlm-scoring

Masked Language Model Scoring

https://github.com/soyoung97/mlm-scoring

Masked Language Model Scoring

https://github.com/spaditha/biobert

Pre-trained Language Model for Biomedical Question Answering

https://github.com/squeezeailab/kvquant

Efficient Streaming Language Models with Attention Sinks

https://github.com/sreejukomath/NLPProjects

Effective Use of Bidirectional Language Modeling for Transfer Learning in Biomedical Named Entity Recognition

https://github.com/sreyan88/reclap

GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities

https://github.com/srgrace/contextual-compression

In-context Autoencoder for Context Compression in a Large Language Model

https://github.com/srush/annotated-s4

Efficiently Modeling Long Sequences with Structured State Spaces

https://github.com/srush/minichain

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

https://github.com/srvk/eesen

First-Pass Large Vocabulary Continuous Speech Recognition using Bi-Directional Recurrent DNNs

https://github.com/ssharpe42/NLQAC_Instance_Selection

Personalized Language Model for Query Auto-Completion

https://github.com/ssharpe42/NLQAC_ObjSeg

Personalized Language Model for Query Auto-Completion

https://github.com/ssharpe42/VNLQAC

Personalized Language Model for Query Auto-Completion

https://github.com/ssymmetry/bbt-fincuge-application

BBT-Fin: Comprehensive Construction of Chinese Financial Domain Pre-trained Language Model, Corpus and Benchmark

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.