Questions tagged [classifiers]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
0 votes
0 answers
44 views

What's the state-of-the-art tool for ​ASR (automatic speech recognition) Error Detection?

ASR Error Detection = automatically detect erroneous words in ASR output. The survey {1} was published 4 years ago. {2} didn't release their implementation. References: {1} Errattahi, Rahhal, Asmaa ...
2 votes
3 answers
236 views

Heads, classifiers

I'm really struggling to 'get' two things on my linguistics course right now, which is heads of phrases and classifiers. I understand that a head determines the nature of a phrase, but I just can't ...
4 votes
1 answer
163 views

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

I couldn't find how in general sortal classifiers work in compound words but I notice the following myself. By sortal classifiers I mean those that actualize shape boundaries, in contrast with ...
5 votes
0 answers
98 views

How did "murder of crows", "pride of lions" and similar collective classifiers in English come to be used?

Classifiers come in many varieties.[1] Many languages have them. Chinese has words like "本" (ben) used for books and similar nouns, 條 (tiao) for long, skinny things, etc. Vietnamese has ...
1 vote
0 answers
46 views

Causative classes in Cantonese

Recently me and WavesWashSands had a conversation about Cantonese and it's causatives. zing2, gaau2, tam3, gik1, haak3 etc. A lot of these look like they are just based on classes of moods. But are ...
0 votes
1 answer
112 views

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

I'm not sure what the difference between these 2 is: classifier = NaiveBayesClassifier.train(train_d) d1 = (nltk.classify.accuracy(classifier,train_d[:500]))*100 d2 = (nltk.classify.accuracy(...
3 votes
1 answer
135 views

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

Some languages, such as Japanese, mark number words with suffixes denoting size, shape, and other qualities (e.g., ichi (one) becomes ippon for one book). Why would such a linguistic practice develop?
1 vote
1 answer
118 views

NLP text classification approach for smart devices

As a project, I have been trying to understand the low-level heuristic approach from the perspective of a device attempting to behave smart, like Alexa and the likes Generally speaking, it starts ...
4 votes
2 answers
1k views

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

There are questions that are self consistent in the sense that they can be understood without a context. In other words, the sentence itself provide a clear information. An example of such a sentence ...
1 vote
1 answer
391 views

Classification of verbs by meaning?

I'd like to ask whether someone has ever tried to classify verbs (and other parts of speech) in a relatively small number of semantic groups /not necessarily disjoint/ and if yes, what groups they ...
0 votes
0 answers
485 views

Categorizing short sentences into a taxonomy

I feel like I might be in the wrong exchange, but I do not see a NLP exchange, so I figured this was the best bet. My current task is to take short sentences and try to categorize them based on some ...
5 votes
1 answer
181 views

What are the contrasts between classifiers in isolating languages and genders in highly inflected ones?

Both isolating languages and inflected languages can have ways of marking noun classes like masculine nouns, nouns that stand for flat things, etc. Some isolating languages, like Chinese, have ...
14 votes
1 answer
559 views

Are there languages in which plural classifiers co-occur with numerals?

I'm aware that a number of classifer languages have what might be called "plural classifiers" which -- unlike "normal" classifier -- force a plural, count interpretation, instead of being ambiguous ...
5 votes
1 answer
1k views

How exactly are noun classes different to classifiers?

Before the beta I would've thought questions like this one would be such basic concepts that most contributors would be familiar with them. But after a few questions on gender and animacy it seems ...