Pinned Repositories
acl-anthology
Data and software for building the ACL Anthology.
Akkademia
Translating Akkadian signs to transcriptions using NLP techniques such as HMM, MEMM and BiLSTM neural networks.
Assyrian-Dictionaries
Collection of Assyrian Dictionaries
ctc_sampling
Code for Sampling from Stochastic Finite Automata with Applications to CTC Decoding
finite_state
Read-only pre-release mirrors of OpenFst, OpenGrm N-Gram, OpenGrm Pynini, OpenGrm SFst and OpenGrm Thrax libraries.
google-research
Google Research
mozolm
MozoLM: A language model (LM) serving library
nisaba
Finite-state script normalization and processing utilities
eidos-audition
Collection of auditory models.
language-resources
Datasets and tools for basic natural language processing.
agutkin's Repositories
agutkin/Assyrian-Dictionaries
Collection of Assyrian Dictionaries
agutkin/ctc_sampling
Code for Sampling from Stochastic Finite Automata with Applications to CTC Decoding
agutkin/bdproto
BDPROTO: a database of phonological inventories from ancient and reconstructed languages
agutkin/cpyp
C++ library for modeling with Pitman-Yor processes
agutkin/dictionaries
Amharic/Tigrinya/Oromo Dictionaries
agutkin/fastText_multilingual
Multilingual word vectors in 78 languages
agutkin/hyperbolic_cones
Source code for the ICML'18 paper "Hyperbolic Entailment Cones for Learning Hierarchical Embeddings", https://arxiv.org/abs/1804.01882
agutkin/icelandic-pronunciation-dataset
60,000 Icelandic words transcribed in International Phonetic Alphabet
agutkin/low-resource-languages
Resources for conservation, development, and documentation of low resource (human) languages.
agutkin/pressagio
Pressagio is a library that predicts text based on n-gram models. For example, you can send a string and the library will return the most likely word completions for the last token in the string.
agutkin/prodige
A supplementary code for Beyond Vector Spaces: Compact Data Representation as Differentiable Weighted Graphs.
agutkin/SunoikisisDC-2016-2017
Planning Seminar and 2016-2017 WS and SS Courses
agutkin/syriac-corpus
This is the development repository for The Oxford-BYU Syriac Corpus project.
agutkin/syriac-corpus-1
A collection of Syraic texts from late antiquity and the early medieval period
agutkin/WIPS
PyTorch implementation of the paper "Representation Learning with Weighted Inner Product for Universal Approximation of General Similarities". IJCAI2019.