In this talk I will cover two papers in which we teach computers to mimic human reasoning over language. In particular, we focus on the problem of answering complex natural language questions from large textual knowledge bases.  In the first paper, I will introduce a simple, fast, and mostly unsupervised approach for question answering (QA) that semantically aligns each word in the question and candidate answer with the most similar word in the supporting evidence text. Our word similarity method operates over neural representations that model the underlying text at different levels of abstractions, ranging from characters to full sentences. Despite its simplicity and lack of supervision, our approach obtains state-of-the-art performance on two QA datasets, outperforming many other supervised neural approaches.  In the second paper, we focus on multi-hop QA, where several facts must be aggregated to answer a question. I will introduce an unsupervised strategy for the selection of evidence sentences for multi-hop QA that (a) maximizes the relevance of the selected sentences, (b) minimizes the overlap between the selected facts, and (c) maximizes the coverage of both question and answer. I will show that this strategy not only improves the performance of a downstream QA system, but also improves the explainability of its decisions.  tinyurl.com/ZoomMihai 

We will be using https://arizona.zoom.us/j/183045568 (scheduled until May 12, 2020).

Advisor:  Joanna Masel
                Ecology & Evolutionary Biology,
                University of Arizona

 Zoom link: https://arizona.zoom.us/j/543758411

We are at a moment in time where mathematical models have a significant role in public policy. A group of us have had informal discussions to better understand the issues and how we might get involved in addressing some of them. To this end, we are planning on starting a working group for people interested in modeling/data analysis/control and mitigation strategies for COVID-19, and more generally, for epidemics.

We will repurpose the Tuesday seminar slots (12:30-1:30 pm) to run a zoom seminar for the remainder of the term. This will be a forum to learn about the mathematical modeling of epidemics, of methods to deal with limited/uncertain data and questions about how to design/compare mitigation strategies. 

The link to join the zoom meeting is https://arizona.zoom.us/s/183045568. Misha Chertkov will get things started with a presentation tomorrow (3/24).

Our apologies for this mass mailing. To get future updates, please  subscribe to the mailing list for this working group by sending an email to covid-19-math@list.arizona.ed

We have a small collection of some of the relevant work, as well as short projects at the level of a first-year grad student on a google drive folder:  

https://drive.google.com/drive/folders/1OjQ6ahioBx7INcBvTOEr5UgP5gHg44tb?usp=sharing (This folder is viewable by everyone with a math.arizona.edu account. Please let one of us know if you would like to have edit access so that you can add material etc.)

Alternatively, this material also available on UA Box at https://arizona.box.com/s/cxv4i4aqhk7uty33pc3y8f0rmcb8gs6y

Best wishes,

Misha Chertkov, Kevin Lin and Shankar Venkataramani

We are at a moment in time where mathematical models have a significant role in public policy. A group of us have had informal discussions to better understand the issues and how we might get involved in addressing some of them. To this end, we are planning on starting a working group for people interested in modeling/data analysis/control and mitigation strategies for COVID-19, and more generally, for epidemics.

We will repurpose the Tuesday seminar slots (12:30-1:30 pm) to run a zoom seminar for the remainder of the term. This will be a forum to learn about the mathematical modeling of epidemics, of methods to deal with limited/uncertain data and questions about how to design/compare mitigation strategies. 

The link to join the zoom meeting is https://arizona.zoom.us/s/183045568. Misha Chertkov will get things started with a presentation tomorrow (3/24).

Our apologies for this mass mailing. To get future updates, please  subscribe to the mailing list for this working group by sending an email to covid-19-math@list.arizona.ed

We have a small collection of some of the relevant work, as well as short projects at the level of a first-year grad student on a google drive folder:  

https://drive.google.com/drive/folders/1OjQ6ahioBx7INcBvTOEr5UgP5gHg44tb?usp=sharing (This folder is viewable by everyone with a math.arizona.edu account. Please let one of us know if you would like to have edit access so that you can add material etc.)

Alternatively, this material also available on UA Box at https://arizona.box.com/s/cxv4i4aqhk7uty33pc3y8f0rmcb8gs6y

Best wishes,

Misha Chertkov, Kevin Lin and Shankar Venkataramani

We are at a moment in time where mathematical models have a significant role in public policy. A group of us have had informal discussions to better understand the issues and how we might get involved in addressing some of them. To this end, we are planning on starting a working group for people interested in modeling/data analysis/control and mitigation strategies for COVID-19, and more generally, for epidemics.

We will repurpose the Tuesday seminar slots (12:30-1:30 pm) to run a zoom seminar for the remainder of the term. This will be a forum to learn about the mathematical modeling of epidemics, of methods to deal with limited/uncertain data and questions about how to design/compare mitigation strategies. 

The link to join the zoom meeting is https://arizona.zoom.us/s/183045568. Misha Chertkov will get things started with a presentation tomorrow (3/24).

Our apologies for this mass mailing. To get future updates, please  subscribe to the mailing list for this working group by sending an email to covid-19-math@list.arizona.ed

We have a small collection of some of the relevant work, as well as short projects at the level of a first-year grad student on a google drive folder:  

https://drive.google.com/drive/folders/1OjQ6ahioBx7INcBvTOEr5UgP5gHg44tb?usp=sharing (This folder is viewable by everyone with a math.arizona.edu account. Please let one of us know if you would like to have edit access so that you can add material etc.)

Alternatively, this material also available on UA Box at https://arizona.box.com/s/cxv4i4aqhk7uty33pc3y8f0rmcb8gs6y

Best wishes,

Misha Chertkov, Kevin Lin and Shankar Venkataramani

We are at a moment in time where mathematical models have a significant role in public policy. A group of us have had informal discussions to better understand the issues and how we might get involved in addressing some of them. To this end, we are planning on starting a working group for people interested in modeling/data analysis/control and mitigation strategies for COVID-19, and more generally, for epidemics.

We will repurpose the Tuesday seminar slots (12:30-1:30 pm) to run a zoom seminar for the remainder of the term. This will be a forum to learn about the mathematical modeling of epidemics, of methods to deal with limited/uncertain data and questions about how to design/compare mitigation strategies. 

The link to join the zoom meeting is https://arizona.zoom.us/s/183045568. Misha Chertkov will get things started with a presentation tomorrow (3/24).

Our apologies for this mass mailing. To get future updates, please  subscribe to the mailing list for this working group by sending an email to covid-19-math@list.arizona.ed

We have a small collection of some of the relevant work, as well as short projects at the level of a first-year grad student on a google drive folder:  

https://drive.google.com/drive/folders/1OjQ6ahioBx7INcBvTOEr5UgP5gHg44tb?usp=sharing (This folder is viewable by everyone with a math.arizona.edu account. Please let one of us know if you would like to have edit access so that you can add material etc.)

Alternatively, this material also available on UA Box at https://arizona.box.com/s/cxv4i4aqhk7uty33pc3y8f0rmcb8gs6y

Best wishes,

Misha Chertkov, Kevin Lin and Shankar Venkataramani