• seminar

seminar

SEMINAR

The talk starts from the position that intelligence is about finding relationships in temporal phenomena and using that knowledge to make predictions and adapt to one's environment. As more and more of everyday life is being digitized, the range of data accessible for mining purposes and the types of prediction that one can make grows rapidly.

A large part of the talk will be centered around mining search engine logs: they form a very direct reflection of what it is that occupies people. In addition, I will look at a number of scenarios in which we follow and interpret similar streaming signals and use them for prediction purposes. I will conclude with observations on new search paradigms that emerge with abundant human information signals.

http://staff.science.uva.nl/~mdr/

Date: 2011-12-08 10:15 - 12:00

Location: L308, Lennart Torstenssonsgatan 8

Permalink

SEMINAR

Date: 2011-12-01 10:15 - 12:00

Location: L308, Lennart Torstenssonsgatan 8

Permalink

SEMINAR

The Sketch Engine is a corpus query tool and web service that allows users to build and explore corpora.  After an introduction to the core functionality of the query tool, we shall see how corpora can be built from the web and also how a corpus you already have on your computer can be prepared for encoding in the Sketch Engine, uploaded, and encoded, and once it is there, what the range of search options and reports are.

http://www.kilgarriff.co.uk/

Date: 2011-11-24 10:15 - 12:00

Location: L308, Lennart Torstenssonsgatan 8

Permalink

SEMINAR

In this presentation, we will give an overview of the tools and algorithms we are developing at LTH in the field of semantic processing. We will review the systems we have designed in the past two years and we will introduce our goals for the next two years. We will also describe in more detail two outcomes of our recent project Semantica: the construction of large proposition databases extracted from Wikipedia and the derivation a subset of events formatted in the LODE format. As LODE uses RDF triples, users can query the event repository using the SPARQL language and extract information in a way similar to SQL databases. Finally, we will outline our on-going effort to apply semantic parsing to Swedish. The presentation will include demonstrations. (http://nlp.cs.lth.se/demonstrations/)

http://cs.lth.se/pierre_nugues

Date: 2011-11-17 10:15 - 12:00

Location: L308, Lennart Torstenssonsgatan 8

Permalink

SEMINAR

In this talk I will discuss how the meaning of spatial descriptions such as "the chair is to the left of the table" is grounded in perception. I will outline my previous work with mobile robots where the mappings between words and perceptual representations were learned automatically from observations. I will discuss how spatial descriptions are also grounded in dialogue - through the alignment between the conversational partners. Finally, I will present ideas towards a more complex model of grounding that also includes our knowledge about the interaction of objects in the world.

Date: 2011-11-10 10:15 - 12:00

Location: L308, Lennart Torstenssonsgatan 8

Permalink

SEMINAR

Swesaurus is a free Swedish wordnet that we are developing in the SweFN++ project. It is built using existing free lexical resources that gives Swesaurus some interesting properties such as fuzzy synsets.


The meat of this talk is my experience of linking SALDO, the backbone of Swesaurus, to Princeton Core Wordnet, but I will also give a general introduction and sketch our road map to Swesaurus 1.0, which we are planning to release in the beginning of next year.

Date: 2011-11-03 10:15 - 12:00

Location: L308, Lennart Torstenssonsgatan 8

Permalink

SEMINAR

Jenny Myrendal (Ph.D. student in linguistics) and I have received funding for the Web Science project "Ett (data-)lingvistiskt perspektiv på webben". Since Web Science (see http://webscience.org) is an area where CLT wants to contribute (all according to the CLT Strategic Plan), I will give an overview of our project plans and also (with your help!) try to answer the question: What does linguistics and computational linguistics have to to with the Web?

Date: 2011-10-27 10:15 - 12:00

Location: L308, Lennart Torstenssonsgatan 8

Permalink

SEMINAR

The presentation is a summary of my thesis, to be finished early in 2012. It explores parallel treebanks, texts and their translation which have been syntactically annotated and where corresponding parts are linked through alignment. Building parallel treebanks is a time-consuming and labour-intensive task. Additionally, for the treebank to be really useful, it needs to be large, containing millions of words. However, tools and/or annotated data are generally only available for a number of the largest languages in the world, and automatic annotation (as well as human annotation) induces errors, and we still need to check and manually correct the annotation, for the data to be useful.

The main question explored in this thesis is how to create a good quality parallel treebank. This is done in two separate ways. First, we describe how the Smultron parallel treebank was created. Second, we explore augmentation of automatically created annotation, in particular methods of projecting knowledge from multiple languages, known as multilingual annotation projection.

Date: 2011-10-20 10:15 - 12:00

Location: L308, Lennart Torstenssonsgatan 8

Permalink

SEMINAR

Abstract:
I am developing a pedagogical tool for children with communication disabilities. The tool will consist of a computer system which gives support for language learning and language training. The system is graphical, where the child can point to words or phrases to get explanations in the form of symbols, written text, or spoken words. The child can also reformulate the sentences, by moving words to new places or change the inflection of words. The system will then automatically reformulate the sentence, so that it will always be grammatically correct. The tool is intended to stimulate - in a playful way - the child's will to explore the possibilities of language.

In this talk I will report on the current status of the tool, and the underlying ideas. If you are lucky, I might even show some pseudo-mathematical theories about tree similarity in type-theoretical grammars...

If you are even luckier, I might give you more awesome animations in the style of my legendary CLT-workshop-discussion-introduction!

Date: 2011-10-13 10:15 - 12:00

Location: L308, Lennart Torstenssonsgatan 8

Permalink

SEMINAR

In this presentation, a dynamic semantic approach to subsymbolic perceptual aspects of meaning is presented. We show how a simple classifier of spatial information based on the Perceptron can be cast in TTR (Type Theory with Records). Furthermore, we show how subsymbolic aspects of meaning can be updated as a result of observing language use in interaction, thereby enabling fine-grained semantic plasticity and semantic coordination.

Date: 2011-09-29 10:15 - 12:00

Location: L308, Lennart Torstenssonsgatan 8

Permalink

X
Loading