There are no reviews yet. Be the first to send feedback to the community and the maintainers!
Abstractive-Summarization
Implementation of abstractive summarization using LSTM in the encoder-decoder architecture with local attention.TextRank-Keyword-Extraction
Keyword extraction using TextRank algorithm after pre-processing the text with lemmatization, filtering unwanted parts-of-speech and other techniques.Chatbot
Hybrid Conversational Bot based on both neural retrieval and neural generative mechanism with TTS.Machine-Translation-Transformers
Machine Translation using TransfromersDemonRangerOptimizer
Quasi Hyperbolic Rectified DEMON Adam/Amsgrad with AdaMod, Gradient Centralization, Lookahead, iterative averaging and decorrelated Weight DecayBERT-Disaster-Classification-Capsule-Routing
Exploration of BERT-BiLSTM models with Layer Aggregation (attention-based and capsule-routing-based) and Hidden-State Aggregation (attention-based and capsule-routing-based).Bi-GRU-CRF-NER
Attempted implementation of a Bi-directional GRU followed by a linear-chain-CRF (from scratch) for Named Entity Recognition.Self-Organizing-Map
SOM clustering on IRIS datasetauto-tldr-TextRank
Extractive Summarization based on statements ranked using TextRankMultilingual-BERT-Disaster
Resources for: Cross-Lingual Disaster-related Multi-label Tweet Classification with Manifold Mixup (ACL SRW 2020)INTER-INTRA-attentions
An experimental custom seq-2-seq model with both layer-wise (inter-layer), and intra-layer attention (attention to previous hidden states of the same RNN unit) for abstractive summarization.Dynamic-Memory-Network-Plus
Implementation of Dynamic Memory Network Plus for Question-Answering. Tested on Induction tasks of bAbi 10K dataset.3D-CNN-Keras
A simple 3D CNN in Keras for Lung Nodule Detection.Tweet-Disaster-Keyphrase
Official repository for "On Identifying Hashtags in Disaster Twitter Data" (AAAI 2020)RAKE-Keyword-Extraction
Keyword extraction using standard RAKE algorithm after pre-processing the text with lemmatization, filtering unwanted parts-of-speech and other techniques.GRU-Text-Generator
Implementation of character level auto text generator using multilayered GRU in KerasWide-Residual-Network
Implementation of a Wide Residual Network on Tensorflow for Image Classification. Trained and tested on Cifar10 dataset.KPDrop
Official Implementation of Keyphrase DropoutZeroPromptSearch
Implementation of an LLM prompting pipeline combined with wrappers for auto-decomposing reasoning steps and for search through the reasoning-step-space (eg. by beam search, MCTS etc.) guided by self-evaluation.QuestionGenerationPub
CapsuleRoutingEncoders
In this work, we study and compare multiple capsule routing algorithms for text classification including dynamic routing, Heinsen routing, and capsule-routing inspired attention-based sentence encoding techniques like dynamic self-attention. Further, similar to some works in computer vision, we do an ablation test of the capsule network where we remove the routing algorithm itself. We analyze the theoretical connection between attention and capsule routing, and contrast the two ways of normalizing the routing weights. Finally, we present a new way to do capsule routing, or rather iterative refinement, using a richer attention function to measure agreement among output and input capsules and with highway connections in between iterations.MonotonicLocationAttention
Causal-Inference
UIC CS-594 Causal Inference Project Fall 2019Neural_Net_Evolution
Learning Neural Net Parameters using Evolutionary StrategiesLove Open Source and this site? Check out how you can help us