Our Research Areas
20 MAY, 2020
Examining the State-of-the-Art in News Timeline Summarization
In this paper, we compare different TLS strategies using appropriate evaluation frameworks, and propose a simple and effective combination of methods that improves over the state-of-the-art on all tested benchmarks. For a more robust evaluation, we also present a new TLS dataset, which is larger and spans longer time periods than previous datasets.


20 MAY, 2020
A Large-Scale Multi-Document Summarization Dataset from the Wikipedia Current Events Portal
Multi-document summarization (MDS) aims to compress the content in large document collections into short summaries and has important applications in story clustering for newsfeeds, presentation of search results, and timeline generation.
1 FEB, 2019
Latent Multi-task Architecture Learning
We present experiments on synthetic data and data from OntoNotes 5.0, including four different tasks and seven different domains. Our extension consistently outperforms previous approaches to learning latent architectures for multi-task problems and achieves up to 15% average error reductions over common approaches to MTL.

-
Data Science
22 Sep, 2016
A Hierarchical Model of Reviews for Aspect-based Sentiment Analysis
Sebastian
7 Min Read
-
General
01 Oct, 2018
A Review of the Neural History of Natural Language Processing
Sebastian
9 Min Read
-
Data Science
24 Aug, 2016
An introduction to Generative Adversarial Networks (with code in TensorFlow)
John
12 Min Read
-
Research
13 Oct, 2016
An overview of word embeddings and their connection to distributional semantic models
Sebastian
6 Min Read