facebookresearch / simmc
With the aim of building next generation virtual assistants that can handle multimodal inputs and perform multimodal actions, we introduce two new datasets (both in the virtual shopping domain), the annotation schema, the core technical tasks, and the baseline models. The code for the baselines and the datasets will be opensourced.
☆130Updated 10 months ago
Related projects: ⓘ
- Code for SIMMC 2.0: A Task-oriented Dialog Dataset for Immersive Multimodal Conversations☆103Updated last year
- PyTorch code for EMNLP 2020 Paper "Vokenization: Improving Language Understanding with Visual Supervision"☆186Updated 3 years ago
- OpenDialKG: Explainable Conversational Reasoning with Attention-based Walks over Knowledge Graphs☆133Updated 2 years ago
- ☆138Updated 3 years ago
- Tutorials on training and testing retrieval-based models (DrQA & DPR)☆51Updated 3 years ago
- PyTorch original implementation of "Unsupervised Question Decomposition for Question Answering"☆119Updated last year
- [NAACL 2021] Factual Probing Is [MASK]: Learning vs. Learning to Recall https://arxiv.org/abs/2104.05240☆167Updated last year
- Zero-shot dialogue state tracking (DST)☆82Updated 2 years ago
- Neural Text Generation with Unlikelihood Training☆311Updated 3 years ago
- Data & Code for ACCENTOR: "Adding Chit-Chat to Enhance Task-Oriented Dialogues" (NAACL 2021)☆71Updated 2 years ago
- An original implementation of EMNLP 2020, "AmbigQA: Answering Ambiguous Open-domain Questions"☆116Updated 2 years ago
- Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue. In ICLR, 2020 (spotlight)☆129Updated 4 years ago
- Baseline implementation for DSTC8 User Response Prediction Challenge☆72Updated last year
- Code and data to support the paper "PAQ 65 Million Probably-Asked Questions andWhat You Can Do With Them"☆200Updated 3 years ago
- A Repo to curate all creative NLG papers☆80Updated 2 years ago
- Pytorch implementation of "A Probabilistic Formulation of Unsupervised Text Style Transfer" by He. et. al. at ICLR 2020☆163Updated last year
- An original implementation of ACL 2019, "Multi-hop Reading Comprehension through Question Decomposition and Rescoring"☆138Updated 2 years ago
- A Constrained Text Generation Challenge Towards Generative Commonsense Reasoning☆139Updated 8 months ago
- A BART version of an open-domain QA model in a closed-book setup☆120Updated 4 years ago
- Neural Module Network for Reasoning over Text, ICLR 2020☆122Updated 3 years ago
- Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference☆45Updated last year
- Authors' implementation of EMNLP-IJCNLP 2019 paper "Answering Complex Open-domain Questions Through Iterative Query Generation"☆194Updated 4 years ago
- Official repository for "SimpleTOD: A Simple Language Model for Task-Oriented Dialogue"☆236Updated 6 months ago
- Official code and data repository for our ACL 2019 long paper "Generating Question-Answer Hierarchies" (https://arxiv.org/abs/1906.02622)…☆95Updated last month
- CMU Document Grounded Conversation Dataset☆110Updated 5 years ago
- Code from the paper "What do Models Learn from Question Answering Datasets?" (EMNLP 2020)☆54Updated 3 years ago
- ☆53Updated last year
- ☆100Updated this week
- Evaluate your dialog model with 17 metrics! (see paper)☆96Updated 4 years ago
- Grounded conversational dataset for end-to-end conversational AI (official DSTC7 data)☆174Updated 3 weeks ago