Ighina / DeepTilingLinks
A TextTiling-based algorithm for text segmentation (aka topic segmentation) that uses neural sentence encoders, as well as extractive summarization and semantic search applications built on top of it.
☆49Updated 2 years ago
Alternatives and similar repositories for DeepTiling
Users that are interested in DeepTiling are comparing it to the libraries listed below
Sorting:
- Efficient few-shot learning with cross-encoders.☆58Updated last year
- Using open source LLMs to build synthetic datasets for direct preference optimization☆65Updated last year
- Plug-and-play Search Interfaces with Pyserini and Hugging Face☆32Updated 2 years ago
- TextReducer - A Tool for Summarization and Information Extraction☆88Updated last year
- Universal text classifier for generative models☆24Updated last year
- A collection of datasets for language model pretraining including scripts for downloading, preprocesssing, and sampling.☆61Updated last year
- Using short models to classify long texts☆21Updated 2 years ago
- SWIM-IR is a Synthetic Wikipedia-based Multilingual Information Retrieval training set with 28 million query-passage pairs spanning 33 la…☆49Updated last year
- RaKUn 2.0 - A fast keyword detection algorithm☆68Updated last month
- A unified versatile interface for dialogue datasets☆18Updated last year
- Fine-tuning 6-Billion GPT-J (& other models) with LoRA and 8-bit compression☆67Updated 2 years ago
- Completion After Prompt Probability. Make your LLM make a choice☆80Updated 10 months ago
- 🚀 Automatically convert unstructured data into a high-quality 'textbook' format, optimized for fine-tuning Large Language Models (LLMs)☆25Updated last year
- Training & Implementation of chatbots leveraging GPT-like architecture with the aitextgen package to enable dynamic conversations.☆48Updated 3 years ago
- Logical structure analysis for visually structured documents☆91Updated 3 years ago
- ☆63Updated 5 months ago
- Entailment self-training☆25Updated 2 years ago
- Seahorse is a dataset for multilingual, multi-faceted summarization evaluation. It consists of 96K summaries with human ratings along 6 q…☆89Updated last year
- Pre-train Static Word Embeddings☆85Updated last week
- Generate visual podcasts about novels using open source models☆25Updated 2 years ago
- Code accompanying the submission "Structural Text Segmentation of Legal Documents" by Aumiller et al.☆97Updated 2 years ago
- RWKV is a RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best …☆10Updated last year
- ☆51Updated 7 months ago
- No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval☆29Updated 2 years ago
- LeXFiles and LegalLAMA: Facilitating English Multinational Legal Language Model Development☆20Updated 2 years ago
- Code for SaGe subword tokenizer (EACL 2023)☆26Updated 9 months ago
- Official implementation of the paper "CoEdIT: Text Editing by Task-Specific Instruction Tuning" (EMNLP 2023)☆130Updated 11 months ago
- ☆62Updated last year
- C++ inference wrappers for running blazing fast embedding services on your favourite serverless like AWS Lambda. By Prithivi Da, PRs welc…☆23Updated last year
- QAmeleon introduces synthetic multilingual QA data using PaLM, a 540B large language model. This dataset was generated by prompt tuning P…☆34Updated 2 years ago