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.
☆51Updated 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.☆60Updated last year
- Universal text classifier for generative models☆24Updated last year
- Using open source LLMs to build synthetic datasets for direct preference optimization☆72Updated last year
- Using short models to classify long texts☆21Updated 2 years ago
- Training & Implementation of chatbots leveraging GPT-like architecture with the aitextgen package to enable dynamic conversations.☆49Updated 3 years ago
- TextReducer - A Tool for Summarization and Information Extraction☆85Updated last year
- Completion After Prompt Probability. Make your LLM make a choice☆82Updated last year
- This repository contains code used for our Multi Sentence Inference NAACL'22 paper.☆12Updated 2 years ago
- RaKUn 2.0 - A fast keyword detection algorithm☆69Updated 5 months ago
- No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval☆29Updated 3 years ago
- A collection of datasets for language model pretraining including scripts for downloading, preprocesssing, and sampling.☆64Updated last year
- Showcase how mxbai-embed-large-v1 can be used to produce binary embedding. Binary embeddings enabled 32x storage savings and 40x faster r…☆19Updated last year
- 🚀 Automatically convert unstructured data into a high-quality 'textbook' format, optimized for fine-tuning Large Language Models (LLMs)☆25Updated 2 years ago
- Plug-and-play Search Interfaces with Pyserini and Hugging Face☆32Updated 2 years ago
- Simply, faster, sentence-transformers☆143Updated last year
- Seahorse is a dataset for multilingual, multi-faceted summarization evaluation. It consists of 96K summaries with human ratings along 6 q…☆89Updated last year
- LeXFiles and LegalLAMA: Facilitating English Multinational Legal Language Model Development☆20Updated 2 years ago
- Trully flash implementation of DeBERTa disentangled attention mechanism.☆67Updated 3 months ago
- Experiments with generating opensource language model assistants☆97Updated 2 years ago
- Tools for managing datasets for governance and training.☆87Updated last month
- Lightweight demos for finetuning LLMs. Powered by 🤗 transformers and open-source datasets.☆78Updated last year
- Entailment self-training☆25Updated 2 years ago
- Tool to apply Legal Matter Specification Standard (LMSS) to documents☆12Updated last year
- Official implementation of the paper "CoEdIT: Text Editing by Task-Specific Instruction Tuning" (EMNLP 2023)☆135Updated last year
- BLOOM+1: Adapting BLOOM model to support a new unseen language☆74Updated last year
- Finetune Falcon, LLaMA, MPT, and RedPajama on consumer hardware using PEFT LoRA☆104Updated 7 months ago
- SWIM-IR is a Synthetic Wikipedia-based Multilingual Information Retrieval training set with 28 million query-passage pairs spanning 33 la…☆49Updated 2 years ago
- Datasets collection and preprocessings framework for NLP extreme multitask learning☆189Updated 6 months ago
- Search through Facebook Research's PyTorch BigGraph Wikidata-dataset with the Weaviate vector search engine☆31Updated 4 years ago
- A context-aware embedding similarity score☆11Updated 2 years ago