Christos Baziotis

ekphrasis. Ekphrasis is a text processing tool, geared towards text from social networks, such as Twitter or Facebook. Ekphrasis performs tokenization, word normalization, word segmentation (for splitting hashtags) and spell correction, using word statistics from 2 big corpora (english Wikipedia, twitter - 330mil english tweets).

neat-vision. Neat (Neural Attention) Vision, is a visualization tool for the attention mechanisms of deep-learning models for Natural Language Processing (NLP) tasks. (framework-agnostic)

datastories-semeval2017-task4. Deep-learning model presented in "DataStories at SemEval-2017 Task 4: Deep LSTM with Attention for Message-level and Topic-based Sentiment Analysis".

seq3. Source code for the NAACL 2019 paper "SEQ^3: Differentiable Sequence-to-Sequence-to-Sequence Autoencoder for Unsupervised Abstractive Sentence Compression"

ntua-slp-semeval2018. Deep-learning models of NTUA-SLP team submitted in SemEval 2018 tasks 1, 2 and 3.

lm-prior-for-nmt. This repository contains source code for the paper "Language Model Prior for Low-Resource Neural Machine Translation"

keras-utilities. Utilities for Keras - Deep Learning library

twitter-stream-downloader. A service for downloading twitter streaming data. You can save the data either in text files on disk, or in a database (MongoDB).

prolog-cfg-parser. A toy SWI-Prolog context-free grammar (CFG) parser, that extracts knowledge (facts) from text.

datastories-semeval2017-task6. Deep-learning model presented in "DataStories at SemEval-2017 Task 6: Siamese LSTM with Attention for Humorous Text Comparison".

hierarchical-rnn-biocreative-4. Repository containing the winning submission for the BioCreative VI Task A (2017). The model is a Hierarchical Bidirectional Attention-Based RNN, implemented in Keras.

patric-triangles. MPI implementation of a parallel algorithm for finding the exact number of triangles in massive networks

ntua-slp-semeval2018-task2. Deep-learning models submitted by NTUA-SLP team in SemEval 2018 Task 2: Multilingual Emoji Prediction https://arxiv.org/abs/1804.06657

ntua-slp-semeval2018-task1. Deep-learning models submitted by NTUA-SLP team in SemEval 2018 Task 1: Affect in Tweets https://arxiv.org/abs/1804.06658

nmt-pretraining-objectives. This repository contains the source code and data for the paper: "Exploration of Unsupervised Pretraining Objectives for Machine Translation" in Findings of ACL 2021.

ntua-slp-pytorch-ex-1. First assignment for familiarising yourself with PyTorch. The goal of the assignment is to implement a baseline RNN model for sentiment classification in Twitter messages, by completing the missing parts in the code :)