Stanford CoreNLP Reviews & Product Details

The Stanford Parser is an easy introduction to natural language processing (NLP). The program uses a combination of approaches to identify and tag both the individual components (syntax) within a sentence and to accurately assign the relationship between the words (semantics). Users can download the Java based version of the program, or experiment with it on their website. Review collected by and hosted on G2.com.

The Stanford Parser is one of many natural language parsers available on the market. I prefer Stanford for its ease and accessibility. The use of a recurrent neural network may produce greater results for someone working in a highly technical and linguistically complex environment, where immediacy and accuracy are equally weighted. Review collected by and hosted on G2.com.

The Stanford Parser is a natural Language parser that doesn't require a ivy league degree to use; plus it is free; which is a huge plus; I use it surprising more than you would think, as i am currently trying to use it to feed langue into a Machine Learning Data Structure; with the ultimate goal of creating a better chat bot Review collected by and hosted on G2.com.

Although built on solid foundations; the User Interface is very 1990's / Early 2000's; If the GUI was re-designed or even updated to modern standards, i feel it would benefit greatly. Review collected by and hosted on G2.com.

The amount of options that Stanford NER provides means you'll never go anywhere else for any kind of NER tasks Review collected by and hosted on G2.com.

The lack of good support of non-English languages Review collected by and hosted on G2.com.

Ease of use and implementation and works effectively in most cases. Open source license and straightforward algorithm. Review collected by and hosted on G2.com.

There are more powerful tools out there like spaCy which use deep learning techniques to identify more information like context in a sentence. Review collected by and hosted on G2.com.

Ability to train a topic model since most textual analysis programs I have used does not have the utility to train a program to be specific to a particular dataset. Review collected by and hosted on G2.com.

Not as effective for small sample sized texts. Since the program's primary focus is on training topic models, there is not an effective amount of analysis on smaller documents, which makes programs with built in textual analysis (such as sentiment based, natural language processing) more useful. Review collected by and hosted on G2.com.

It has the most common, and even some uncommon, algorithms implemented. And the best part is, they are in Java! Review collected by and hosted on G2.com.

I think documentation can be a little difficult to use. But still much better than many other ML libraries. Review collected by and hosted on G2.com.

I have been using Stanford tokenizer for six years and I love it. It's easy to integrate with any application and can recognize special character like ",", "$" etc. It also has the functionality of removing token matched with some regex. It also has a variety of configuration according to the user's requirements. Review collected by and hosted on G2.com.

It converts bracket to other symbols e.g. LCB-, -LRB-, -RCB-, -RRB which sometimes require extra processing later. Review collected by and hosted on G2.com.

Son niveaux de facilité , le code et claire nouveaux produit a faire connaitre au grand public

et productif . Review collected by and hosted on G2.com.

l'extraction de fichier et plutôt lente . Review collected by and hosted on G2.com.

I've used the Stanford NLTK parse is various natural language processing projects. It works very well, documentation is good enough. Review collected by and hosted on G2.com.

There is nothing I would specifically call out about the Stanford NLP Parsing tools. Review collected by and hosted on G2.com.