May 1st, 2014 - Galway


Introduction

Efficient means for capturing and representing computational semantics of data are critical for coping with current limitations of information systems, especially if one wants to make sense of large amounts of information coming from heterogeneous and/or poorly structured resources. Efforts aimed at representing meaning of data in a machine-readable way (i.e., Semantic Web or deductive databases) have achieved some level of success. There are alternatives to the top-down, assertional approaches to semantics, which can work even without (too much) expensive human involvement. One of the most widely and successfully used are distributional semantics models that have been researched within the field of computational linguistics. These models, based on the distributional hypothesis [1], provide a bottom-up approach to the computational representation of meaning, where the statistical co-occurrence of terms in unstructured corpora can provide a basis for the construction of simplified but comprehensive and extensible models of semantic content. Distributional models can provide flexible models of meaning which work over large-scale and heterogeneous data. Their applications include semantic search, sentiment analysis, question answering, knowledge discovery, among others.

[1] Harris, Z. (1954). "Distributional structure". Word 10 (23): 146–162.

Objective

The workshop will focus on providing an introduction to distributional semantics, its state-of-the-art and current distributional semantics research within Insight.

Program

Introductory talks

- Introduction to Distributional Semantics, Andre Freitas : 11:30 - 12:15 

- Introduction to Latent Semantic Analysis & Explicit Semantic Analysis, Nitish Agarwal : 12:15 - 12:45 

Lunch : 12:45 - 13:30

Research talks

- Natural Language Queries over Heterogeneous Linked Data Graphs: A Distributional-Compositional Semantics Approach, Andre Freitas : 13:30 - 14:00

On the Reflection of Topics in the DBpedia Semantic Graph and Word-Sense Disambiguation, Ioana Hulpus : 14:00 - 14:30

- Complexity, Coherence, Entropy (CoCoE): Structural and Information-Theoretic Measures for Empirical Assessment of LOD Datasets, Vit Novacek : 14:30 - 15:00 

- Wikipedia-based Distributional Semantics for Entity Relatedness, Nitish Agarwal : 15:00 - 15:30

Coffee Break : 15:30 - 15:50

- Loose Semantic Coupling in Event Processing Systems via Distributional Semantics, Souleiman Hasan : 15:50 - 16:20

Adaptive Representations for Tracking Breaking News on Twitter, Igor Brigadir : 16:20 - 16:50

- A Distributional Semantics Approach for Selective Reasoning on Commonsense Graph Knowledge Bases, Andre Freitas : 16:50 - 17:10

Panel Session

- What distributional semantics can bring to the semantic systems table?, Paul Buitelaar, Siegfried Handschuh, Edward Curry, Vit Novacek : 17:10 - 17:40

Location

Insight Centre for Data Analytics @ NUIGalway
DERI Building
IDA Business Park,
Lower Dangan,
Galway

Directions from the city center: At Eire Square (100m from the new coach station) take the 404 bus (direction Newcastle). The timetable can be found here. Leave the bus at the bus stop close to the Westwood hotel (ask the driver).

Organizers

Andre Freitas
Paul Buitelaar
Nitish Agarwal
Edward Curry
Siegfried Handschuh

Registration

If you are interested in attending or presenting at the workshop please send an email to andre [dot] freitas [at] deri [dot] org.