google-research-datasets / seahorse
Seahorse is a dataset for multilingual, multi-faceted summarization evaluation. It consists of 96K summaries with human ratings along 6 quality dimensions: comprehensibility, repetition, grammar, attribution, main idea(s), and conciseness, covering 6 languages, 9 systems and 4 datasets.
☆85Updated 8 months ago
Related projects ⓘ
Alternatives and complementary repositories for seahorse
- Apps built using Inspired Cognition's Critique.☆58Updated last year
- Plug-and-play Search Interfaces with Pyserini and Hugging Face☆32Updated last year
- Code of ICLR paper: https://openreview.net/forum?id=-cqvvvb-NkI☆91Updated last year
- Open source library for few shot NLP☆77Updated last year
- SWIM-IR is a Synthetic Wikipedia-based Multilingual Information Retrieval training set with 28 million query-passage pairs spanning 33 la…☆44Updated last year
- A Multilingual Replicable Instruction-Following Model☆94Updated last year
- ☆73Updated last year
- Repo for training MLMs, CLMs, or T5-type models on the OLM pretraining data, but it should work with any hugging face text dataset.☆92Updated last year
- ☆95Updated last year
- [Data + code] ExpertQA : Expert-Curated Questions and Attributed Answers☆122Updated 8 months ago
- Embedding Recycling for Language models☆38Updated last year
- ☆97Updated 2 years ago
- ☆73Updated 3 years ago
- This repository contains materials for the SIGIR 2022 tutorial on opinion summarization.☆34Updated 2 years ago
- ☆65Updated last year
- The official code repo for "Sub-Sentence Encoder: Contrastive Learning of Propositional Semantic Representations".☆75Updated 10 months ago
- Official code and model checkpoints for our EMNLP 2022 paper "RankGen - Improving Text Generation with Large Ranking Models" (https://arx…☆136Updated last year
- Hugging Face Inference Toolkit used to serve transformers, sentence-transformers, and diffusers models.☆50Updated this week
- Do Multilingual Language Models Think Better in English?☆41Updated last year
- Mr. TyDi is a multi-lingual benchmark dataset built on TyDi, covering eleven typologically diverse languages.☆72Updated 2 years ago
- ☆46Updated this week
- ☆51Updated last year
- Helper scripts and notes that were used while porting various nlp models☆44Updated 2 years ago
- ☆29Updated 9 months ago
- Dense hybrid representations for text retrieval☆62Updated last year
- SPRINT Toolkit helps you evaluate diverse neural sparse models easily using a single click on any IR dataset.☆42Updated last year
- ☆55Updated last year
- No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval☆27Updated 2 years ago
- ☆37Updated last year