arXiv subjects

Yichao Zhou

Publications and source records attributed to Yichao Zhou.

39 records · Page 3Linked to original sources

arXiv2018

Learning Gender-Neutral Word Embeddings

Word embedding models have become a fundamental component in a wide range of Natural Language Processing (NLP) applications. However, embeddings trained on human-generated corpora have been demonstrated to inherit strong gender stereotypes that reflect social constructs. To address this concern, in this paper, we propose a novel training procedure for learning gender-neutral word embeddings. Our approach aims to preserve gender information in certain dimensions of word vectors while compelling other dimensions to be free of gender influence. Based on the proposed method, we generate a Gender-Neutral variant of GloVe (GN-GloVe). Quantitative and qualitative experiments demonstrate that GN-GloVe successfully isolates gender information without sacrificing the functionality of the embedding model.

cs.CL↗

arXiv2017

Aztec: A Platform to Render Biomedical Software Findable, Accessible, Interoperable, and Reusable

Precision medicine and health requires the characterization and phenotyping of biological systems and patient datasets using a variety of data formats. This scenario mandates the centralization of various tools and resources in a unified platform to render them Findable, Accessible, Interoperable, and Reusable (FAIR Principles). Leveraging these principles, Aztec provides the scientific community with a new platform that promotes a long-term, sustainable ecosystem of biomedical research software. Aztec is available at https://aztec.bio and its source code is hosted at https://github.com/BD2K-Aztec.

cs.DL↗

arXiv2015

Computational Protein Design Using AND/OR Branch-and-Bound Search

The computation of the global minimum energy conformation (GMEC) is an important and challenging topic in structure-based computational protein design. In this paper, we propose a new protein design algorithm based on the AND/OR branch-and-bound (AOBB) search, which is a variant of the traditional branch-and-bound search algorithm, to solve this combinatorial optimization problem. By integrating with a powerful heuristic function, AOBB is able to fully exploit the graph structure of the underlying residue interaction network of a backbone template to significantly accelerate the design process. Tests on real protein data show that our new protein design algorithm is able to solve many prob- lems that were previously unsolvable by the traditional exact search algorithms, and for the problems that can be solved with traditional provable algorithms, our new method can provide a large speedup by several orders of magnitude while still guaranteeing to find the global minimum energy conformation (GMEC) solution.

cs.AI↗