StevenLau6 / FINDSum
A Large-Scale Dataset for Long Text and Multi-Table Summarization
☆16Updated 9 months ago
Related projects ⓘ
Alternatives and complementary repositories for FINDSum
- TAT-QA (Tabular And Textual dataset for Question Answering) contains 16,552 questions associated with 2,757 hybrid contexts from real-wor…☆97Updated 2 months ago
- Codebase, data and models for the SummaC paper in TACL☆85Updated 11 months ago
- Code, datasets, and checkpoints for the paper "Improving Passage Retrieval with Zero-Shot Question Generation (EMNLP 2022)"☆96Updated last year
- The data and the PyTorch implementation for the models and experiments in the paper "Exploiting Asymmetry for Synthetic Training Data Gen…☆58Updated last year
- [NAACL 2022] Robust (Controlled) Table-to-Text Generation with Structure-Aware Equivariance Learning.☆55Updated 7 months ago
- [Neurips2023] Source code for Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory☆54Updated last year
- ☆167Updated last year
- [ACL 2022] A hierarchical table dataset for question answering and data-to-text generation.☆64Updated this week
- PyTorch implementation and pre-trained models for ASP - Autoregressive Structured Prediction with Language Models, EMNLP 22. https://arxi…☆100Updated 10 months ago
- Data and code for ACL 2022 paper "MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Data"☆41Updated last month
- Code and Data for NeurIPS2021 Paper "A Dataset for Answering Time-Sensitive Questions"☆63Updated 2 years ago
- ☆72Updated last year
- ACL2023 - AlignScore, a metric for factual consistency evaluation.☆111Updated 8 months ago
- ☆25Updated 2 years ago
- Detect hallucinated tokens for conditional sequence generation.☆63Updated 2 years ago
- Code and data accompanying the paper "TRUE: Re-evaluating Factual Consistency Evaluation".☆71Updated this week
- Code for the paper "Open Domain Question Answering with A Unified Knowledge Interface" (ACL 2022)☆57Updated last year
- ☆16Updated 10 months ago
- ☆83Updated last year
- Code and models for the paper "Questions Are All You Need to Train a Dense Passage Retriever (TACL 2023)"☆60Updated last year
- BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval☆57Updated last month
- Repository for MuSiQue: Multi-hop Questions via Single-hop Question Composition, TACL 2022☆97Updated 5 months ago
- ConvGQR: Generative Query Reformulation for Conversational Search. A codebase for ACL 2023 accepted paper.☆24Updated 8 months ago
- ☆55Updated last year
- ☆67Updated 9 months ago
- When FLUE Meets FLANG: Benchmarks and Large Pretrained Language Model for Financial Domain☆45Updated 4 months ago
- Codebase of ACL2024 paper "Spiral of Silence: How is Large Language Model Killing Information Retrieval?—A Case Study on Open Domain Ques…☆14Updated 5 months ago
- Data and code for EMNLP 2022 paper "ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering"☆83Updated 2 years ago
- This repository contains source code for the PASTA model, a pre-trained language model for table-based fact verification.☆18Updated last year
- Pytorch Implementation of EncT5: Fine-tuning T5 Encoder for Non-autoregressive Tasks☆63Updated 2 years ago