Nicholas Monath

 Nicholas Monath

 Contact

  College of Information and Computer Science
  University of Massachusetts Amherst
  140 Governors Drive
  University of Massachusetts
  Amherst, MA 01003
  nmonath [at] cs [dot] umass [dot] edu

Bio

I am a third year MS/PhD student in computer science at the University of Massachusetts Amherst advised by Professor Andrew McCallum. I am a member of the Information Extraction and Synthesis Laboratory. My research focuses on machine learning and natural language processing. I received my B.S. in computer science and mathematics from Brandeis University in 2013 where I worked with Professors James Storer and Antonella Di Lillo.

Research Interests

The focus of my research is on scalable methods for entity resolution, the task of determining the underlying entities referred to by a set of ambiguous mentions. I am interested in two settings of this problem, with and without an existing knowledge base. Without a knowledge base, entity resolution can be framed as clustering in which the data points are mentions and clusters of points are entities. As a clustering problem, it is particularly challenging because of the scale of the data, with both a large number of mentions and a large number of entities. Scaling clustering algorithms to large numbers of clusters is a focus of my work. With a knowledge base, the goal is to link mentions to their corresponding entities present in the knowledge base. In this supervised setting, I hope to study models for entities that are based on a wide variety of sources: occurrences in text, relations in knowledge bases, string surface form spelling, appearance statistics, and others. Some application areas I am interested in are: disambiguating scientific author names on research papers and linking named entities to Wikipedia.

Education



Graduate:
University of Massachusetts Amherst.
Started MS (only) Fall 2013
Entered MS/PhD Fall 2015

Undergraduate:
Brandeis University. BS 2013. Computer Science and Mathematics.

Publications and Presentations

Ari Kobren (*), Nicholas Monath (*), Akshay Krishnamurthy, and Andrew McCallum. An Online Hierarchical Algorithm for Extreme Clustering . In Submission. 2017. (* equal contribution) [arxiv preprint] [code]

Haw-Shiuan Chang, Abdurrahman Munir, Ao Liu, Johnny Tian-Zheng Wei, Aaron Traylor, Ajay Nagesh, Nicholas Monath, Patrick Verga, Emma Strubell, and Andrew McCallum. Extracting Multilingual Relations under Limited Resources: TAC 2016 Cold-Start KB construction and Slot-Filling using Compositional Universal Schema. NIST TAC KBP Workshop 2016. Notebook version [pdf]

Benjamin Roth, Nicholas Monath, David Belanger, Emma Strubell, Patrick Verga and Andrew McCallum Building Knowledge Bases with Universal Schema: Cold Start and Slot-Filling Approaches TAC KBP 2015 Workshop [pdf]

Nicholas Monath and Andrew McCallum. Discriminative Hierarchical Coreference for Inventor Disambiguation. Presentation. PatentsView Inventor Disambiguation Technical Workshop. September 2015 [slides] [code]

Mykel J. Kochenderfer and Nicholas Monath. Data Compression of Optimal Value Functions for Markov Decision Processes Data Compression Conference. Snowbird Utah 2013.

Awards

1st place. Inventor Disambiguation Challenge. PatentsView Inventor Disambiguation Technical Workshop. September 2015. [link] [slides] [code]. Our inventor name disambiguation system was integrated into USPTO PatentsView website.