IBM / translucent-answer-predictionLinks
TAP (Translucent Answer Prediction), is a system to identify answers and evidence (in the form of supporting facts) in an RCQA task that requires multi-hop reasoning. TAP comprises two loosely coupled networks, called Local and Global Interaction eXtractor (LoGIX) and the Answer Predictor (AP).
☆28Updated 5 years ago
Alternatives and similar repositories for translucent-answer-prediction
Users that are interested in translucent-answer-prediction are comparing it to the libraries listed below
Sorting:
- Code and Data for our EMNLP 2020 paper titled 'Learning to Explain: Datasets and Models for Identifying Valid Reasoning Chains in Multiho…☆28Updated 3 years ago
- Code for ModularQA☆28Updated 4 years ago
- [EMNLP'21] Plan-then-Generate: Controlled Data-to-Text Generation via Planning☆76Updated 3 years ago
- The official implementation of ACL 2020, "Logic-Guided Data Augmentation and Regularization for Consistent Question Answering".☆71Updated last year
- The accompanying code for "Injecting Numerical Reasoning Skills into Language Models" (Mor Geva*, Ankit Gupta* and Jonathan Berant, ACL 2…☆89Updated last year
- Code to create pre-training data for a span selection pre-training task inspired by reading comprehension and an effort to avoid encoding…☆30Updated 3 years ago
- EMNLP 2021: Single-dataset Experts for Multi-dataset Question-Answering☆69Updated 3 years ago
- This repository maintains the QAConv dataset, a question-answering dataset on informative conversations including business emails, panel …☆83Updated 10 months ago
- Source code of the paper "Do Syntax Trees Help Pre-trained Transformers Extract Information?" (EACL 2021)☆76Updated 3 years ago
- Codes for ACL-IJCNLP 2021 Paper "Zero-shot Fact Verification by Claim Generation"☆65Updated 3 years ago
- ☆64Updated 2 years ago
- AIR retriever for Multi-Hop QA (ACL 2020 paper)☆30Updated 5 years ago
- [ACL 2020] Structure-Level Knowledge Distillation For Multilingual Sequence Labeling☆71Updated 2 years ago
- ACL'2020: Contextualized Sparse Representations for Real-Time Open-Domain Question Answering☆49Updated 4 years ago
- ABCD: A Graph Framework to Convert Complex Sentences to a Covering Set of Simple Sentences☆28Updated 2 years ago
- ReConsider is a re-ranking model that re-ranks the top-K (passage, answer-span) predictions of an Open-Domain QA Model like DPR (Karpukhi…☆49Updated 4 years ago
- This project is special for SemEval2020 task4 Commonsense Validation and Explanantion☆48Updated 5 years ago
- Code for NAACL 2021 full paper "Efficient Attentions for Long Document Summarization"☆67Updated 4 years ago
- The data and code for ACL2020 paper "Logical Natural Language Generation from Open-Domain Tables"☆167Updated 2 years ago
- Tools and datasets for Aristo Leaderboards☆42Updated 4 years ago
- Dataset for protoqa ("family feud") data☆33Updated 3 years ago
- Few-shot NLP benchmark for unified, rigorous eval☆92Updated 3 years ago
- Code and Models for the paper "End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering" (NeurIPS 20…☆109Updated 3 years ago
- Progressively Pretrained Dense Corpus Index for Open-Domain QA and Information Retrieval☆43Updated 2 years ago
- Code for ACL2021 paper: "GLGE: A New General Language Generation Evaluation Benchmark"☆57Updated 2 years ago
- This repository contains the code for "How many data points is a prompt worth?"☆48Updated 4 years ago
- Source code for paper on commonsense reasoning for 2020 Annual Conference of the Association for Computational Linguistics (ACL) 2020.☆29Updated last year
- This repository contains code and models for the paper: Semantic Graphs for Generating Deep Questions (ACL 2020).☆76Updated 3 years ago
- MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems☆67Updated 3 years ago
- Code and data for "Retrieval Enhanced Model for Commonsense Generation" (ACL-IJCNLP 2021).☆29Updated 3 years ago