Blogg

This blog is a piece of opinion where I sketch the process of developing NLP-based applications for second language learning and look at the process from the point of view of typical (mis)conceptions and challenges, as I have experienced them. Are we over-trusting the potential of NLP? Are teachers by definition reluctant to use NLP-based solutions in classrooms? How, if at all, can academic universities ensure sustainability of the developed applications?

I en värld där AI tar en allt större plats har datadriven forskning blivit orden på allas läppar. I det här blogginlägget tänkte jag prata lite om vad det innebär att forska med hjälp av stora mängder textdata, primärt inom humaniora. Detta inlägg är det första i en serie om de olika delarna av en data-intensiv forskningsmetodologi.

Shafqat Mumtaz Virk, Harald Hammarström, Markus Forsberg, Søren Wichmann

Recently, we have seen a surge of methods that claim to embed meaning from textual corpora. But is that possible? Can text really reveal meaning, and if so, can current NLP methods detect it? Can our methods, as they some times claim, understand? Perhaps the larger question is the following: can we bring meaning to words using only the information stored in text? This question is essential for any Artificial Intelligence (AI) system that uses text as a basis.

A comment often received by the reviewers of manuscripts to scientific conferences and journals is one about the representative sample under scrutiny and whether there are any solid arguments for accepting that the population characteristics, and particularly the features extracted from the empirical data acquired from such a population (e.g. from speech production) provide sufficient or accurate enough information to use in various algorithmic approaches (e.g. in machine learning).

What if you could find all arguments in a text without having to read it? Or, what if you could search a database for a controversial topic and immediately get arguments for and against it, gathered from text all around the internet? Or, imagine when writing an essay you would automatically get an estimation of how persuasive your arguments are.

Continuing on last month's theme on Swedish parliamentary data, we would like to introduce a new tool designed to use and explore them.

The Swedish PoliGraph is unfortunately not able to tell when a politician lies, at least not yet. Rather it is a graph that connects politicians to their roles and participation in the Swedish parliament. With it, we can ask questions such as:

The Swedish Parliament (Riksdagen) continuously releases open data on its website, which includes documents approved and used during parliamentary sessions as well as what each member of parliament votes during each roll call (voting session).

In recent years, neural network based approaches (i.e. deep learning) have been the main models for state-of-the-art systems in natural language processing, whether that is in machine translation, natural language inference, language modeling or sentiment analysis. At the same time researchers have asked themselves what kind of linguistic information these neural networks are able to capture.