LOGIN TO YOUR ACCOUNT

Username
Password
Remember Me
Or use your Academic/Social account:

CREATE AN ACCOUNT

Or use your Academic/Social account:

Congratulations!

You have just completed your registration at OpenAire.

Before you can login to the site, you will need to activate your account. An e-mail will be sent to you with the proper instructions.

Important!

Please note that this site is currently undergoing Beta testing.
Any new content you create is not guaranteed to be present to the final version of the site upon release.

Thank you for your patience,
OpenAire Dev Team.

Close This Message

CREATE AN ACCOUNT

Name:
Username:
Password:
Verify Password:
E-mail:
Verify E-mail:
*All Fields Are Required.
Please Verify You Are Human:
fbtwitterlinkedinvimeoflicker grey 14rssslideshare1

Future Fellowships - Grant ID: FT130101105

Title
Future Fellowships - Grant ID: FT130101105
Funding
ARC | Future Fellowships
Contract (GA) number
FT130101105
Start Date
2013/01/01
End Date
2017/12/31
Open Access mandate
no
Organizations
-
More information
http://purl.org/au-research/grants/arc/FT130101105

 

  • Learning Structural Kernels for Natural Language Processing

    Beck, Daniel; Cohn, Trevor; Hardmeier, Christian; Specia, Lucia (2015)
    Projects: ARC | Future Fellowships - Grant ID: FT130101105 (FT130101105)
    Structural kernels are a flexible learning\ud paradigm that has been widely used in Natural\ud Language Processing. However, the problem\ud of model selection in kernel-based methods\ud is usually overlooked. Previous approaches\ud mostly rely on setting default values for kernel\ud hyperparameters or using grid search,\ud which is slow and coarse-grained. In contrast,\ud Bayesian methods allow efficient model\ud selection by maximizing the evidence on the\ud training data through gradient-ba...

    Joint Emotion Analysis via Multi-task Gaussian Processes

    Beck, D.; Cohn, T.; Specia, L. (2014)
    Projects: ARC | Future Fellowships - Grant ID: FT130101105 (FT130101105)
    We propose a model for jointly predicting\ud multiple emotions in natural language sentences.\ud Our model is based on a low-rank\ud coregionalisation approach, which combines\ud a vector-valued Gaussian Process\ud with a rich parameterisation scheme. We\ud show that our approach is able to learn\ud correlations and anti-correlations between\ud emotions on a news headlines dataset. The\ud proposed model outperforms both singletask\ud baselines and other multi-task approaches.

    Hawkes processes for continuous time sequence classification : an application to rumour stance classification in Twitter

    Lukasik, Michal; Srijith, P. K; Vu, Duy; Bontcheva, Kalina; Zubiaga, Arkaitz; Cohn, Trevor
    Projects: EC | PHEME (611233), ARC | Future Fellowships - Grant ID: FT130101105 (FT130101105)
    Classification of temporal textual data sequences is a common task in various domains such as social media and the Web. In this paper we propose to use Hawkes Processes for classifying sequences of temporal textual data, which exploit both temporal and textual information. Our experiments on rumour stance classification on four Twitter datasets show the importance of using the temporal information of tweets along with the textual content.
  • No project research data found
  • Scientific Results

    Chart is loading... It may take a bit of time. Please be patient and don't reload the page.

    PUBLICATIONS BY ACCESS MODE

    Chart is loading... It may take a bit of time. Please be patient and don't reload the page.

    Publications in Repositories

    Chart is loading... It may take a bit of time. Please be patient and don't reload the page.

Share - Bookmark

App Box