Playing chess against the Transformer
We trained a Transformer autoregressive language model to learn to play chess; read on to find out how the experiment played out. Our goal was to provide insights into the type of learning Transformers are capable of, beyond the well-known text generation examples we’ve seen before. The transformer architecture Even if you don’t follow the field of Natural Language Processing, you’ve probably heard of the Transformer by now: a neural network architecture that relies on an attention mechanism to understand sequential data. Although not necessarily restric...
Modeling common sense with ConceptNet
To understand semantic connections between words in human language (e.g. what do apples have in common with oranges?), AI researchers have explored a wide range of strategies during the previous decades. Ontologies such as WordNet were constructed to represent knowledge about the meaning of words. In a broader sense these ontologies aim at representing the structure of the world itself. Such databases have supported classic AI interfaces like question ↔ answer systems. ConceptNet is a member of the family of semantic databases but it takes a more ‘fuzzy’ approach. ...
What emotion was intended, then?
Studies have shown even humans amongst each other frequently disagree about whether a sentence expresses a certain sentiment, and when it does, what type of sentiment it is. Ideally, we want to develop a system where the AI’s judgement agrees as much as possible with average human opinion. By studying the cases where assigning emotions to text is problematic, we can systematically improve our emotion recognition service.
Sentiment analysis with PHP
InterTextueel launches a new tool to recognize universal emotions in texts. The sentiment analysis service differs from traditional approaches which restrict search to positive or negative signals. Our emotion recognition software provides users with a more fine-grained idear of the mood of a text. Our methodology is knowledge-based and grammar-based and we are using intelligent techniques to detect false positives. Customers can deliver us their own text corpus or dataset and we will create new lexicons for them and fine-tune our algorithm to better match their specific domain and requirements.