Seq2Seq | Synced

by Synced 2021-09-17 3

MIT Presents New Approach for Sequence-to-Sequence Learning with Latent Neural Grammars

A new MIT CSAIL paper presents an alternative, hierarchical approach to sequence-to-sequence learning with quasi-synchronous grammars to improve sequence-to-sequence models’ compositional generalization on diagnostic tasks.

by Synced 2021-09-02 1

AI Machine Learning & Data Science Research

Cambridge U & Facebook’s ProoFVer: High-Performance Natural Logic-Based Fact Verification With Explainability

A research team from the University of Cambridge and Facebook AI proposes ProoFVer, a proof system for fact verification using natural logic. ProoFVer provides faithful explanations while outperforming state-of-the-art fact verification models.

by Synced 2018-07-06 0

AI Research

Microsoft Paper Introduces First GEC System To Reach Human-Level Performance

A new research paper demonstrating the first Automatic Grammatical Error Correction system to reach human-level performance has been published on arXiv by Tao Ge, Furu Wei and Ming Zhou from the Natural Language Computing Group, Microsoft Research Asia.

by Synced 2017-03-03 0

Industry Research

Beyond Seq2Seq with Augmented RNNs by Edward Grefenstette, Google, Inc.

This talk summarizes the limitations of RNN (including LSTM, GRU), from both empirical and computational hierarchy mechanism perspectives.