Recent content by Jespersen

Yeah, you definitely need to play around with the settings (I may have made the defaults too random). Try the default first (4/8 for everything), then something like: quality at 6/8, 'spin phrases' at 8/8, 'spin words' at 1/8 + relevant keywords for the same content... compare the two and see if...

One more spinner for you guys. Vector Spinner was my experiment in creating a spinner which doesn't use a thesaurus - instead, it looks for synonyms for both entire phrases and individual words using an approach inspired by automatic translation, based around NLP analysis of gigabytes of...

One more spinner for you guys. Vector Spinner was my experiment in creating a spinner which doesn't use a thesaurus - instead, it looks for synonyms for both entire phrases and individual words using an approach inspired by automatic translation, based around NLP analysis of gigabytes of...

I'm still looking for more testers if anyone's interested. I updated the spinner to rewrite expressions with nouns at phrase level (using a technique inspired by machine translation), making it faster, simpler, and more readable, so if you weren't convinced before, check out the updated demo. I...

If you know Python, that's cool too, since I can give you an example of what to do. Sent you a PM.

I've been working on a completely data-driven spinner, accessible as an API, and I'm currently looking for testers. How is this spinner different from existing ones? It doesn't use a thesaurus. Instead, similarities in word meaning, rules of grammar, and probabilities of words occurring in a...

Sorry for the downtime. I must have accidentally broken something when updating it. I didn't change much so far, but I tried to filter out some nonsense ('make' -> 'perform'... ugh). In any case, it's back.

Awesome! I'm glad most people like it. I know it might still end up generating kludge, but I already have an idea how to improve the overall readability of the results (and maybe add more synonyms at the same time) so you can expect an update over the following week or so. Remember: If you like...

Cool, any thoughts? I'm very interested in feedback from people who depend on spinners for generating content. In the meantime... I watched IM Smart Money's comparison of WordAi & SpinnerChief, and decided to see how my spinner matches up against commercial ones. WordAi ($49.95 a month)...

Got a premium account to share free stuff. But enough about my insanity. I wrote a nested spinner as a pet project a while ago - I believe it beats most currently available free spinners, at least for phrasal spin - and where it doesn't (e.g. it might have issues with some very specific words)...

The standard procedure for making sure this is definitely not a .css issue would be to temporarily comment out/delete ALL .css info (and then repeat the same for parts of code until you track the source of the issue down).

You may want to look up VDM Publishing / Alphascript Publishing and how they handled things. It's a Germany-based 'publisher' who runs the most successful model of selling Wikipedia content as books (so yes, this idea for a business is fairly widespread).

Yep, I normally use NLTK, it just wasn't necessary in the end because I wanted to see how simple I can keep a thing like this. Using Wordnet-based similarity measures improves accuracy, but it lowers performance approximately 20 times, so...

I don't mean to point anything obvious out, but that's pretty basic graph traversal. Except that as everybody pointed out, it's ridiculously impractical. It needs more complexity than purely random generation and you will need to cap the results at some point, which means you'll only spin a...

A quick and dirty Python script which takes a list of paragraphs (= articles) from a .txt file as input and replaces every sentence in each with similar sentences taken from other paragraphs in the collections. It doesn't spin anything (that'd be a good next step though), but the results aren't...