jiangnanhugo / lmkitLinks
language models toolkits with hierarchical softmax setting
☆17Updated 7 years ago
Alternatives and similar repositories for lmkit
Users that are interested in lmkit are comparing it to the libraries listed below
Sorting:
- LibN3L: A light-weight neural network package for natural language☆82Updated 6 months ago
- Attempt at using LSTMs to predict semantic relatedness of sentences (a la Tai et al. in Improved Semantic Representations From Tree-Struc…☆22Updated 10 years ago
- EMNLP2015_code_Long Short-Term Memory Neural Networks for Chinese Word Segmentation☆76Updated 10 years ago
- ACL2015_code_Gated Recursive Neural Network for Chinese Word Segmentation☆28Updated 10 years ago
- Code for Exploring Segment Representations for Neural Segmentation Models☆30Updated 8 years ago
- BiLSTM-CRF for sequence labeling in Dynet☆81Updated 8 years ago
- Source code for an ACL2016 paper of Chinese word segmentation☆79Updated 6 years ago
- souce code for "Accelerating Neural Transformer via an Average Attention Network"☆78Updated 6 years ago
- This is the code&dataset for the paper [Hierarchical Memory Networks for Answer Selection on Unknown Words. COLING 2016]☆44Updated 7 years ago
- Answer Sentence Selection using Deep Learning☆63Updated 10 years ago
- Implementation in Tensorflow of A Structured Self-attentive Sentence Embedding with the sentiment analysis task.☆66Updated 8 years ago
- Tensorflow-LSTM-CRF tool for Named Entity Recognizer☆59Updated 8 years ago
- An attempt to implement the TreeLSTM in Theano☆44Updated 9 years ago
- Implementing , learning and re implementing "End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF" in keras☆71Updated 8 years ago
- Dialog State Tracking Challenge 6 (DSTC6)☆54Updated 7 years ago
- Word segmentation using neural networks based on package https://github.com/SUTDNLP/LibN3L☆23Updated 9 years ago
- QA - Answer Selection (Rank candidate answers for a given question)☆36Updated 7 years ago
- Keras (re)implementation of paper "Learning to Rank Short Text Pairs with Convolutional Deep Neural Networks. SIGIR, 2015"☆67Updated 9 years ago
- ☆28Updated 9 years ago
- ☆35Updated 8 years ago
- This released code corresponds to TACL paper "attentive convolution". Attentive Convolution aims to generate a vector for two sentences.☆105Updated 7 years ago
- Learning Word Representations by Jointly Modeling Syntagmatic and Paradigmatic Relations (ACL2015)☆28Updated 10 years ago
- Quasi-RNN for language modeling☆57Updated 8 years ago
- ☆10Updated 8 years ago
- ☆25Updated 9 years ago
- Chinese word segmentation model with word-based character embeddings.☆12Updated 7 years ago
- Bi-Directional Block Self-Attention☆122Updated 7 years ago
- Attention_CopyNet☆29Updated 9 years ago
- Gaussian Mixture Latent Vector Grammars☆30Updated 6 years ago
- ICASSP2017: End-to-end joint learning of natural language understanding and dialogue manager☆75Updated 8 years ago