A model library for exploring state-of-the-art deep learning topologies and techniques for optimizing Natural Language Processing neural networks

A collection of datasets that pair questions with SQL queries.

A Japanese tokenizer based on recurrent neural networks

Simple Solution for Multi-Criteria Chinese Word Segmentation

A frame-semantic parsing system based on a softmax-margin SegRNN.

Source code for an ACL2017 paper on Chinese word segmentation

BiLSTM-CRF for sequence labeling in Dynet

Source code for an ACL2016 paper of Chinese word segmentation

Code for paper "End-to-End Reinforcement Learning for Automatic Taxonomy Induction", ACL 2018

An Implementation of Transformer (Attention Is All You Need) in DyNet

Deep Recurrent Generative Decoder for Abstractive Text Summarization in DyNet

Transition-based joint syntactic dependency parser and semantic role labeler using a stack LSTM RNN architecture.

Dataset and model for disentangling chat on IRC

Code for the paper "Extreme Adaptation for Personalized Neural Machine Translation"

Source code for the paper "Morphological Inflection Generation with Hard Monotonic Attention"

Dynet-based Biaffine Parser

An attentional NMT model in Dynet

See http://github.com/onurgu/joint-ner-and-md-tagger This repository is basically a Bi-LSTM based sequence tagger in both Tensorflow and Dynet which can utilize several sources of information about each word unit like word embeddings, character based embeddings and morphological tags from an FST to obtain the representation for that specific wor…

DyNet implementation of stack LSTM experiments by Grefenstette et al.

Selective Encoding for Abstractive Sentence Summarization in DyNet