IBM / translucent-answer-prediction
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 4 years ago
Related projects ⓘ
Alternatives and complementary repositories for translucent-answer-prediction
- Code and Data for our EMNLP 2020 paper titled 'Learning to Explain: Datasets and Models for Identifying Valid Reasoning Chains in Multiho…☆27Updated 2 years ago
- Code and data for "Retrieval Enhanced Model for Commonsense Generation" (ACL-IJCNLP 2021).☆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 3 years ago
- Code to create pre-training data for a span selection pre-training task inspired by reading comprehension and an effort to avoid encoding…☆30Updated 2 years ago
- This is the repo for the paper "Revealing the Importance of Semantic Retrieval for Machine Reading at Scale".☆59Updated 4 years ago
- The official implementation of ACL 2020, "Logic-Guided Data Augmentation and Regularization for Consistent Question Answering".☆72Updated 3 months ago
- Code for ModularQA☆28Updated 3 years ago
- An original implementation of ACL 2019, "Compositional Questions Do Not Necessitate Multi-hop Reasoning" (Single-hop Reading Comprehensio…☆58Updated 5 years ago
- Code for AAAI 2020 paper "Select, Answer and Explain: Interpretable Multi-hop Reading Comprehension over Multiple Documents"☆41Updated 4 years ago
- Code for the paper "Partially-Aligned Data-to-Text Generation with Distant Supervision" in EMNLP 2020.☆20Updated 3 years ago
- ☆46Updated 2 years ago
- Code for NAACL 2021 full paper "Efficient Attentions for Long Document Summarization"☆64Updated 3 years ago
- Iterative Rank-Aware Open IE☆30Updated 5 years ago
- [ACL'21 Findings] Why Machine Reading Comprehension Models Learn Shortcuts?☆16Updated last year
- Code for ACL2021 long paper: Knowledgeable or Educated Guess? Revisiting Language Models as Knowledge Bases☆29Updated 2 years ago
- resources for the IBM Airlines Table-Question-Answering Benchmark☆30Updated 2 years ago
- Code for our paper "Semantic Representation for Dialogue Modeling" in ACL2021☆44Updated 2 years ago
- [EMNLP'21] Plan-then-Generate: Controlled Data-to-Text Generation via Planning☆70Updated 2 years ago
- EMNLP 2021: Single-dataset Experts for Multi-dataset Question-Answering☆70Updated 2 years ago
- Codes for ACL-IJCNLP 2021 Paper "Zero-shot Fact Verification by Claim Generation"☆63Updated 2 years ago
- [ACL 2022] Ditch the Gold Standard: Re-evaluating Conversational Question Answering☆45Updated 2 years ago
- FaVIQ: Fact Verification from Information-seeking Questions☆43Updated last year
- ☆45Updated last year
- Tools and datasets for Aristo Leaderboards☆41Updated 3 years ago
- [EMNLP 2020] Discern: Discourse-Aware Entailment Reasoning Network for Conversational Machine Reading☆36Updated last year
- ☆21Updated 3 years ago
- The implementation of the paper "Harvesting and Refining Question-Answer Pairs for Unsupervised QA"☆33Updated 3 years ago
- ☆74Updated 2 years ago
- PathNet model for Multi-hop Reading Comprehension (https://arxiv.org/pdf/1811.01127.pdf)☆21Updated 3 years ago
- Code for our EMNLP 2020 Paper "AIN: Fast and Accurate Sequence Labeling with Approximate Inference Network"☆18Updated last year