microsoft / icecapsLinks
Intelligent Conversation Engine: Code and Pre-trained Systems. Version 0.2.0.
☆287Updated 2 years ago
Alternatives and similar repositories for icecaps
Users that are interested in icecaps are comparing it to the libraries listed below
Sorting:
- Authors' implementation of EMNLP-IJCNLP 2019 paper "Answering Complex Open-domain Questions Through Iterative Query Generation"☆195Updated 5 years ago
- Code for the AllenNLP demo.☆197Updated 2 years ago
- ☆345Updated 6 years ago
- Code to reproduce experiments in the paper "Task-Oriented Dialogue as Dataflow Synthesis" (TACL 2020).☆309Updated last year
- An Analysis Toolkit for Natural Language Generation (Translation, Captioning, Summarization, etc.)☆445Updated last month
- Unsupervised Question answering via Cloze Translation☆219Updated 3 years ago
- Utilities, Baselines, Statistics and Descriptions Related to the MSMARCO DATASET☆189Updated 5 years ago
- A toolkit for evaluating the linguistic knowledge and transferability of contextual representations. Code for "Linguistic Knowledge and T…☆209Updated 3 years ago
- EMNLP 2020: "Dialogue Response Ranking Training with Large-Scale Human Feedback Data"☆344Updated 9 months ago
- ☆265Updated 3 years ago
- Scripts and links to recreate the ELI5 dataset.☆326Updated 3 years ago
- Jack the Reader☆259Updated 6 years ago
- Code from the paper "Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation - NAACL-2019.☆127Updated 2 years ago
- GAP is a gender-balanced dataset containing 8,908 coreference-labeled pairs of (ambiguous pronoun, antecedent name), sampled from Wikipe…☆227Updated 4 years ago
- ☆229Updated 7 years ago
- ☆323Updated 2 years ago
- Automatically extracting keyphrases that are salient to the document meanings is an essential step to semantic document understanding. An…☆156Updated 2 years ago
- This dataset contains 108,463 human-labeled and 656k noisily labeled pairs that feature the importance of modeling structure, context, an…☆560Updated 3 years ago
- A Corpus for Multilingual Document Classification in Eight Languages.☆151Updated 3 years ago
- WWW 2018: CESI: Canonicalizing Open Knowledge Bases using Embeddings and Side Information☆102Updated 2 years ago
- NLP library designed for reproducible experimentation management☆294Updated last year
- The official implementation of ICLR 2020, "Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering".☆432Updated last year
- Framework for learning dialogue agents in a two-player game setting.☆160Updated 2 years ago
- Dynamic Meta-Embeddings for Improved Sentence Representations☆334Updated 4 years ago
- Neural text-to-text question generation☆216Updated 4 years ago
- One million English sentences, each split into two sentences that together preserve the original meaning, extracted from Wikipedia edits.☆123Updated 6 years ago
- interactive explorer for language models☆135Updated 3 years ago
- XLNet for generating language.☆166Updated 4 years ago
- Large corpus of uncompressed and compressed sentences from news articles.☆123Updated 8 years ago
- Hearst Patterns Revisited: Automatic Hypernym Detection from Large Text Corpora☆153Updated 3 years ago