Questionnaire 3: Chatterbots

A chatterbot (chat bots, talk bots) is a type of conversational agent; it is a computer program known as Artificial Conversational Entity (ACE), which is designed to simulate a real conversation with human users.

ASIMO, created by Honda, is a humanoid robot that is able to walk and interact with humans.

And when we talk about a simulation, we really mean that because chatterbots are not capable of “understanding” the conversation. The way they “converse” is just simply by recognizing words or phrases from the human user, which allows them to use pre-calculated responses which can move the conversation on in an apparently meaningful way without requiring them to know what they are talking about.

Questionnaire 3: Question Answering (QA)

Have you ever asked yourself what happens when you introduce a question in your computer? No? Never? Then you will get surprised with today’s post because I am going to talk about Question Answering (QA).

Question Answering (QA)

Question Answering (QA) is, in information retrieval, the task of answering automatically a question asked in natural language. In order to provide you with a proper answer a QA computer program can use either a pre-structured database or a collection of natural language documents (such as the World Wide Web, for instance).

Questionnaire 2: Word Sense Disambiguation & Named Entity Recognition

We have talked in the previous post about Machine Translation (MT) because it is considered a sub-field of the Computational Linguistics that we are currently studying. Broadly speaking, MT consists of translating words or speech from one natural language to another one using translation software. As we said, MT faces two problems in two different sub-areas of Natural Language Processing (NLP) that we are going to discover today in this post.

The Tower of Babel by Pieter Brueghel the Elder. "Come, let us go down and confuse their language so they will not understand each other." (Genesis 11:7)

Word Sense Disambiguation (WSD):

In the first place, and as you all may have guessed by now, Word Sense Disambiguation (WSD) consists of identifying which sense of a word is the most suitable in a given sentence, considering, obviously, that the word has a large number of distinct senses. To achieve this goal there are two different possible approaches: deep approaches and shallow approaches.

Questionnaire 2: Machine Translation (MT)

Now, we have a clear idea of what Natural Language Processing (NLP) is; besides, we have already mentioned the most common tasks that have to do with NLP. In this post, what I would like to do is to start explaining briefly some of those topics for you to have a better understanding of them.

Trans·la·tion

Machine Translation (MT):

Machine Translation (MT) is a sub-field of Computational Linguistics whose main purpose is to develop computer software in order to translate automatically text or speech from one natural language to another one. At a first approach, MT substitutes words in one natural language for words in the target language. However, with the use of several corpus techniques we can obtain more complex translations.

Questionnaire 2: Classic HLT topics

Those of you who are hooked on Human Language Technologies (HLT) will already  know that along the year researchers publish books, give lectures and conferences… about different topics that have to do with this area of Computational Linguistics that we are currently studying.

"Oh, mother! Your databases are *so* 20th century!" "I just don't understand you unstructured kids!"

For that reason I have decided to bring here some of the most classic or important topics discussed in the field of Natural Language Processing (NLP). Here come the examples:

Questionnaire 1: Research centres for Human Language Technologies (II)

We continue showing you examples of research centres for Human Language Technologies (HLT); today we travel to the Netherlands in order to discover The Institute for Logic, Language and Computation (ILLC) at the University of Amsterdam (Universiteit van Amsterdam).

University of Amsterdam logo

The ILLC , with researchers from the Faculty of Sciences and the Faculty of Humanities, started off in 1986 as the Institute for Logic, Language and Information; but it was not until 1991 that it was officially established as a University Research Institute. Since that year, several faculties and groups such as The Applied Logic Lab have joined the ILLC.

Questionnaire 1: Research centres for Human Language Technologies (I)

If you have been following my blog lately, you will already know what Human Language Technologies (HLT) are, as well as some of the most relevant figures that are currently investigating this field. In this post what I would like to do is to start showing you some examples of the best research centres that we have today.

Main entrance to the DFKI

The first centre that we are going to mention due to its great importance is the German Research Centre for Artificial Intelligence (DFKI GmbH). The DFKI, Germany’s leading research centre in the area of innovative software technology, has facilities in Kaiserslautern, Saarbrücken, Bremen, and a project office in Berlin. It has been recognized as a remarkable “centre of excellence” since its foundation as a nonprofit organization in 1988 by several renowned German IT companies and two research facilities. Nowadays, with an overall annual budget of more than € 25 million, the DFKI works hard in its “Living Labs” in order to launch innovative and technological solutions and products for its customers.

Questionnaire 1: Yorick Wilks (Researchers) (II)

In this article I am going to keep on presenting important researchers and scholars that have successfully contributed to the development of the areas that we have been studying lately. Today I am going to introduce you to Yorick Wilks, who is Professor of Artificial Intelligence at the University of Sheffield and whose research interests include: artificial intelligence, computational linguistics, theoretical linguistics, machine translation, dialogue management and understanding systems and named entity recognition, among other topics.

Professor Yorick Wilks

Yorick Wilks was born in the United Kingdom in 1939 and was educated at Torquay Boys’ Grammar School (Devon, England), before attending Pembroke College, at the widely known University of Cambridge (Cambridgeshire, England), where he obtained his Ph.D. in 1968 under Professor R. B. Braithwaite for his thesis Argument and Proof.

Questionnaire 1: Hans Uszkoreit (Researchers) (I)

This term we are studying Human Language Technologies (HLT) and for that reason I have published in the previous posts some definitions that I found useful to gain a good insight into this topic. However, I think it is the time to meet some of the most important researchers, scholars and professors on this field.

Hans Uszkoreit's portrait

The first researcher that I am going to present is Hans Uszkoreit, who is Professor of Computational Linguisitcs at the Department of Computational Linguistics and Phonetics of Saarland University at Saarbrücken (Germany). At the same time he serves as Scientific Director at the German Research Centre for Artificial Intelligence (DFKI), where he heads the Language Technology Lab.

Questionnaire 1: What is Human Language Technology? (Expert opinions) (II)

We continue quoting definitions of what Human Language Technology (HLT) is, expressed by authorised scholars and institutions in order to gain a real insight into this interesting topic. In this second post, as we have previously published Hans Uszkoreit’s thesis, we are going to make a reference to an HLT definition by a renowned university.

The University of Sheffield (Portobello centre)

The definition that we are going to present today was given by the Natural Language Processing Group at the University of Sheffield (South Yorkshire, England), in whose head we find Yorick Wiks, another important and distinguished researcher in the field of computer science and artificial intelligence. They described Natural Language Processing as follows: