Finding offer times using stanford nlp

Question

Q1. I am trying to get the full sentence time, I just don't know how to do it using nlp. Any help was appreciated.

Q2. What information can I extract from a sentence using nlp?

Currently I can, I get: 1. Choosing a sentence Verb object of an object. 3.POS tags.

Any information can be extracted, please let me know.

Answer 1

Penna Village Bank defines VBD and VBN as the past tense and past participle of the verb, respectively. In many sentences, it’s enough to simply get the POS tags and check for the presence of these two tags. In others, however, verbs can be several times, while the sentence as a whole is in the past tense. For these cases, you need to use parsing. Stanford NLP also provides a parser. You can use this to discover the outermost phrase (tagged VP ). If the past tense / participle form of the verb is the ancestor of all other verbs in the verb phrase, the time of your sentence should be marked as the past tense.

In the example provided by Dror, you get the following:

 (ROOT (S (NP (PRP I)) (VP (VBD did) (RB n't) (VP (VB want) (NP (DT the) (NN dog) (S (VP (TO to) (VP (VB eat) (NP (PRP$ my) (NN homework)))))))) (. .))) 

Despite eating past tense, the top verb in the verb phrase is correctly labeled VBD (i.e., past tense).

edit (additional information):

Complex sentences have the so-called primary time and secondary time. For offers like "By the time I get there, he’s already gone," there’s no such thing as "full time." You can only distinguish between primary and secondary.

If you need information about perfect, continuous, etc., you will need to infer rules based on POS tags. For instance. the auxiliary verb in the present tense, followed by the verb in the past tense, expresses the present perfect tense (if there are obvious counterexamples, add to the answer ... I can’t think of it now).

Answer 2

Basically, the time of a sentence in English is determined by the form of the verb, which is the head of the sentence. You can learn more about this topic in this post Context Stress Context . Identification of the head verb and its form is possible using a parser.

The type of information that can be extracted from the proposal depends on the analysis you perform. You can extract other components of a sentence, such as prepositional additions, predicative additions and additions, as well as other grammatical attributes, such as aspect, secondary time, modality, and polarity. Some offers contain built-in offers, as in the example below from the Contextors API . In this case, you can also extract this information from the built-in sentence.

Answer 3

I want full tension, for example: simple present OR present perfect continuous intense ... as far as I know, I can’t get just from POS tags

Note that what you have in the above examples is not an example of tension, but rather are examples of certain time / aspect configurations. While time itself (past, present, future) takes place in time, aspect categories (progressive, continuous, perfect, etc.) are more likely to connect randomness with the flow of time (i.e. are they limited / completed , was a continuous event, etc.). Thus, tension and aspect are two different grammatical categories. In English, they both form part of the verbal complex, which makes it easy to confuse them, as well as find / analyze them in one method. In many other languages, they are implemented separately (individual structural positions, functional elements, constructions, etc.). Caution.