Gaurav Kumar
January 29, 2019
When:
February 11, 2019 @ 12:00 pm – 1:15 pm
Where:
Hackerman Hall B17, 3400 N Charles St, Baltimore, MD 21218, USA
Events
Murali Karthick Baskar (Brno University of Technology) “Promising Accurate Prefix Boosting for sequence-to-sequence ASR”
January 29, 2019
When:
February 4, 2019 @ 12:00 pm – 1:15 pm
Where:
Hackerman Hall B17, 3400 N Charles St, Baltimore, MD 21218, USA
Abstract: Promising accurate prefix boosting (PAPB) is a discriminative training technique for attention based sequence-to-sequence (seq2seq) ASR. PAPB is devised to unify the training and testing scheme effectively. The training procedure involves maximizing the score of[…]
Oliver Adams
January 29, 2019
When:
January 28, 2019 @ 12:00 pm – 1:15 pm
Where:
Hackerman Hall B17, 3400 N Charles St, Baltimore, MD 21218, USA
Brendan O’Connor (UMass Amherst) “Demographic Bias in Social Media Language Analysis: A Case Study of African-American English”
January 29, 2019
When:
February 1, 2019 @ 12:00 pm – 1:15 pm
Where:
Hackerman Hall B17, 3400 N Charles St, Baltimore, MD 21218, USA
Abstract: We conduct a case study of dialectal language in online conversational text by investigating African-American English (AAE) on Twitter, through a demographically supervised model to identify AAE-like language associated with geo-located messages. We verify[…]
Yi-Chia Wang (Uber AI) “Improving Customer Support at Uber with Conversational AI”
October 2, 2018
When:
November 30, 2018 @ 12:00 pm – 1:15 pm
Where:
Hackerman Hall B17, 3400 N Charles St, Baltimore, MD 21218, USA
Abstract Goal-oriented conversational systems are becoming ubiquitous in daily life for tasks ranging from personal assistants to customer support systems. For these systems to engage users and achieve their goals, they need to 1) not[…]
Tamara Broderick (MIT) “Automated Scalable Bayesian Inference via Data Summarization”
October 2, 2018
When:
October 26, 2018 @ 12:00 pm – 1:15 pm
Where:
Hackerman Hall B17, 3400 N Charles St, Baltimore, MD 21218, USA
Abstract The use of Bayesian methods in large-scale data settings is attractive because of the rich hierarchical relationships, uncertainty quantification, and prior specification these methods provide. Many standard Bayesian inference algorithms are often computationally expensive,[…]
Spence Green (Lilt) “Recent Progress in Interactive Neural Machine Translation”
September 4, 2018
When:
November 26, 2018 @ 12:00 pm – 1:15 pm
Where:
Hackerman Hall B17, 3400 N Charles St, Baltimore, MD 21218, USA
Abstract In this talk I’ll describe recent progress in interactive neural machine translation, which is a human-in-the-loop machine learning task. First, I’ll motivate interactive MT, which is an idea that dates to the 1960s that[…]
