https://github.com/bobchennan/espnet
Improved training of end-to-end attention models for speech recognition
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
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 They have superseded recurrent neural network-based models, which had previously superseded the purely statistical models, such as word n-gram language model.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
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Improved training of end-to-end attention models for speech recognition
Decrypting Cryptic Crosswords: Semantically Complex Wordplay Puzzles as a Target for NLP
Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation
Clustering of Deep Contextualized Representations for Summarization of Biomedical Texts
Accelerating Neural Architecture Search using Performance Prediction
Scaling Language Models: Methods, Analysis & Insights from Training Gopher
Decomposed Prompting to Answer Questions on a Course Discussion Board
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
Benchmarking and Explaining Large Language Model-based Code Generation: A Causality-Centric Approach
Analyzing Speaker Information in Self-Supervised Models to Improve Zero-Resource Speech Processing
HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units
GraphTeam: Facilitating Large Language Model-based Graph Analysis via Multi-Agent Collaboration
PLDR-LLM: Large Language Model from Power Law Decoder Representations
Offline RL for Natural Language Generation with Implicit Language Q Learning
What Matters in Training a GPT4-Style Language Model with Multimodal Inputs?
Pay Less Attention with Lightweight and Dynamic Convolutions
Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.