4 votes
Accepted

How is the ability of sortal classifiers to form compound words in Chinese and other Sino-Tibetan languages?

Modern Standard Mandarin Chinese does indeed have a propensity for "noun-classifier" compounds (名量式复合词 míngliàng-shì fùhécí). This is a subject with some active research going on. According ...
Michaelyus's user avatar
  • 7,361
3 votes
Accepted

Differences in Naive Bayes Classifier NLTK, same code, different answers?

In the first case, you're training with the entire data set, then testing on different chunks of it. In the second case, you're training with chunks of the data set, then testing on the whole thing. ...
Draconis's user avatar
  • 65.4k
3 votes

Markers for size, shape etc. on number words in Japanese

The pon in 'ippon' is not actually a suffix (well, at least not according to the academic tradition of Russian japonology). It is [hon], a calque from Chinese classifier (aka a measure word) 本 [běn]. ...
Manjusri's user avatar
  • 2,771
1 vote

NLP text classification approach for smart devices

Alexa is far less smart than we're led to believe. The real short answer to your question is: Those classifications are man-made, i.e. defined by developers. In Alexa, they're called a "Skill", and ...
Pascal-Denis Lussier's user avatar
1 vote
Accepted

How to identify context independent (self-consistent) sentences?

I think that the problem mostly narrows down to the reference of NPs, since verbs, adjectives, adverbs and all kinds of function words, but also indefinite or quantified NPs like a car or all humans ...
Natalie Clarius's user avatar
1 vote

How to identify context independent (self-consistent) sentences?

Neither of your example sentences are entirely context-free. An AI might comment for each: 1) "I don't recall the experiment." 2) "I don't recall the task." Once you write a program that can ...
amI's user avatar
  • 656

Only top scored, non community-wiki answers of a minimum length are eligible