software

List of open-source implementations for IESL projects

TextKBQA

TextKBQA is a TensorFlow implementation of the paper "Question Answering on Knowledge Bases and Text using Universal Schema and Memory Networks"

Box Embeddings Library

A fully open source Python library for geometric representation learning, compatible with both PyTorch and TensorFlow, which allows existing neural network layers to be replaced with or transformed into boxes easily.

BRAN

Bi-affine Relation Attention Network (BRAN) is a model which simultaneously predicts relationships between all mention pairs in a document. We form pairwise predictions over entire paper abstracts using an efficient self-attention encoder. All-pairs mention scores allow us to perform multi-instance learning by aggregating over mentions to form entity pair representations. We further adapt to settings without mention-level annotation by jointly training to predict named entities and adding a corpus of weakly labeled data.

DIVE

Distributional inclusion vector embedding (DIVE) is a unsupervised method of hypernym discovery via per-word non-negative vector embeddings which preserve the inclusion property of word contexts in a low-dimensional and interpretable space. It can also be viewed as an unsupervised method which compresses sparse bag of words by grouping words into topics and makes the visualization of word co-occurring statistics much more easier.

Dilated CNN for Named Entity Recognition

ID-CNN is designed to have better capacity than traditional CNNs for large context and structured prediction, and is a faster alternative to Bi-LSTMs for NER. Please see our paper "Fast and Accurate Entity Recognition with Iterated Dilated Convolutions" for more details.

MINERVA

MINERVA is a RL agent which answers queries in a knowledge graph of entities and relations. Starting from an entity node, MINERVA learns to navigate the graph conditioned on the input query till it reaches the answer entity. For example, given the query, (Colin Kaepernick, PLAYERHOMESTADIUM, ?), MINERVA takes the highlighted path in the knowledge graph below. Note: Only the solid edges are observed in the graph, the dashed edges are unobserved.

PERCH

PERCH is a new non-greedy algorithm for online hierarchical clustering that scales to both a massive number of samples and the number of clusters.