Home > Unit > UMIACS

UMIACS

Title: Semantic and Stylistic Variations in Machine Translation

Abstract: While parallel texts represent invaluable resources for machine translation, they inevitably introduce biases in the cross-lingual mappings learned by machine translation models.  In addition to the domain bias and translationese bias studied in past work, we argue that another form of bias arises from subtle choices in content and style made by translators to appropriately convey the meaning of the source to their target audience.

Title: Weakly Supervised Learning for Detection of Online Harassment

Title: Text Analytics in Finance: A Case Study and Some Considerations

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 the NLP platform we are building at Bloomberg, including example applications. I will close with some ways in which NLP for financial text analytics is similar to and different from NLP as commonly done in research, and some ideas for productive NLP work.

Title- Interpretable Machine Learning: What it means, How we're getting there

The Ins and Outs of Preposition Semantics: Challenges of Coverage and Cross-linguistic Adequacy

Title: Information Abolition

Title: A Framework to Model Human Behavior at LargeScale during Natural Disasters


Title: From Linguistic Signal to Mental State: Computational Models of Framing


Theme 4: Flexible Speech Recognition

Panelists:

Pages

Subscribe to UMIACS