3

You might be referring to Semantic role labeling. SRL is the task of assigning labels to words or phrases in a sentence that shows their semantic role in that sentence. In your example CV was hit by IV, the task is to identify the verb "hit" carried out by the actor "CV" affected "IV" the recipient. Note: If you're only interested in the syntactic ...


3

This is still a research topic in linguistics. A quick google search brings up a couple of papers that might be useful: Identifying Metaphor Hierarchies in a Corpus Analysis of Finance Articles Metaphor Identification in Large Texts Corpora However, you probably won't get an off-the-shelf tool that recognises metaphors for you. UPDATE: since I got a ...


3

This is basically the problem of commonsense knowledge. It is AI-complete. If we knew how to solve it, Siri and Cortana wouldn't be as limited as they are.


2

In grammar, a predicate-argument relationship is one which is implied from text but not expressed in the syntactic structure. (Asher S) Predicate logic or first order logic is a collection of formal systems used in mathematics, philosophy, linguistics and computer science. The NLP community is interested in recognizing, representing and classifying ...


2

Metaphors are a literary device corresponding to an analogy, which is a cognitive device. Since human cognition has not been achieved in AI, recognition of metaphors in natural language is not yet feasible. The first example given can be used to illustrate the challenge. His words cut deeper than a knife. We have the following linguistic elements from ...


1

You can generally identify the mood of a verb by looking at grammatical structures; you don't need any language model for it. The three major moods in English are declarative, interrogative, and imperative. Assuming English is the language you will be working with, here are some questions: Does he like coffee? Is this a piece of chocolate? When did you go ...


1

The LSTM seq2seq model typically used for language translation actually can output multiple variations, and does in many implementations. The decoder stage outputs confidence/probabilities for each word, and it is possible to run the decoder multiple times, taking different samples on each run. Not only is it possible, but this is actually done by ...


1

This seems not easy for NLP. I doubt that state-of-the-art NLP tools can reliably determine the correct hierarchical structure of independent clauses. Examples below. The Berkeley parser gets it basically right in the sense that it can put its late and I'm tired on parallel, and they together on parallel with the weekend. But still not perfect (the weekend ...


1

your question is a very similar to "turing-test". you could narrate a simple story and ask questions based on that , considering the state-of-art algorithms in "question-answering" are still far beyond human skills.


1

Since SHRLDLU was developed, there have been several more attempts to develop natural language understanding systems. For example, there is one document that describes an implementation of a self-extending natural language user interface.


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