Seminars

Sun Mon Tue Wed Thu Fri Sat
1
2
3
Michael Auli (Facebook) “Sequence to Sequence Learning: Fast Training and Inference with Gated Convolutions” 12:00 pm
Michael Auli (Facebook) “Sequence to Sequence Learning: Fast Training and Inference with Gated Convolutions” @ Hackerman Hall B17
Oct 3 @ 12:00 pm – 1:15 pm
Abstract Neural architectures for machine translation and language modeling is an active research field. The first part of this talk introduces several architectural changes to the original work of Bahdanau et al. 2014. We replace[...]
4
5
6
7
8
9
10
Malcolm Slaney (Google) “Auditory Attention: From Saliency to Models to Applications” 12:00 pm
Malcolm Slaney (Google) “Auditory Attention: From Saliency to Models to Applications” @ Hackerman Hall B17
Oct 10 @ 12:00 pm – 1:15 pm
Abstract Understanding attention is key to many auditory tasks. In this talk I would like to summarize several aspects of attention that we have used to better understand how humans use attention in our daily lives.[...]
11
12
13
Laura Dietz (University of New Hampshire) “Retrieving Complex Answers through Knowledge Graph and Text” 12:00 pm
Laura Dietz (University of New Hampshire) “Retrieving Complex Answers through Knowledge Graph and Text” @ Hackerman Hall B17
Oct 13 @ 12:00 pm – 1:15 pm
Abstract We all turn towards Wikipedia with questions we want to know more about, but eventually find ourselves on the limit of its coverage. Instead of providing “ten blue links” as common in Web search,[...]
14
15
16
17
Amanda Stent (Bloomberg) “Text Analytics in Finance: A Case Study and Some Considerations” 12:00 pm
Amanda Stent (Bloomberg) “Text Analytics in Finance: A Case Study and Some Considerations” @ Hackerman Hall B17
Oct 17 @ 12:00 pm – 1:15 pm
Abstract The finance industry increasingly seeks insight from unstructured data, including through text analytics. In this talk, I will give a brief survey of NLP as used in text analytics, then talk in detail about[...]
18
19
20
Sharon Gannot (Bar-Ilan University, Israel) “Speech Enhancement Using a Deep Mixture of Experts” 12:00 pm
Sharon Gannot (Bar-Ilan University, Israel) “Speech Enhancement Using a Deep Mixture of Experts” @ Hackerman Hall B17
Oct 20 @ 12:00 pm – 1:15 pm
Abstract In this study, we present a deep mixture of experts (DMoE) neural-network architecture for single microphone speech enhancement. By contrast to many speech enhancement algorithms that overlook the spectral variability of the speech signal,[...]
21
22
23
24
Katharina Kann (LMU Munich) “Low-resource Morphological Generation with Neural Sequence-to-Sequence Models” 12:00 pm
Katharina Kann (LMU Munich) “Low-resource Morphological Generation with Neural Sequence-to-Sequence Models” @ Hackerman Hall B17
Oct 24 @ 12:00 pm – 1:15 pm
Abstract As languages other than English are moving more and more into the focus of NLP, accurate handling of morphology is getting constantly more important. This talk presents approaches to morphological generation, casting morphological inflection[...]
25
26
27
28
29
30
31
Kate Knill (University of Cambridge) “Are All Languages Created Equal for Speech Recognition?” 12:00 pm
Kate Knill (University of Cambridge) “Are All Languages Created Equal for Speech Recognition?” @ Hackerman Hall B17
Oct 31 @ 12:00 pm – 1:15 pm
Abstract When considering building speech recognition and keyword search (KWS) systems for a ‘new’ language, two key questions are “how much data is going to be needed?” and “what resources are available?”. This talk will look[...]

Center for Language and Speech Processing