My Quizz

Finite state automata may be used for:

• Scripts for conversational bots

• NP-phrase identification

• None of the other options

• Semantic analysis

• Coreference resolution

Long distance dependencies in texts may be handled with

• The bag of words approach

• Transformers

• Ontologies

• Formal grammars

• Recurrent Neural Networks

When implementing a conversational agent (for example, similar to "Siri") you might need

• A corpus of dialogs

• Knowledge graphs

• An ontology

• Frames

• Machine learning

We can say about lexical chains that:

• a.   We can use them for semantic disambiguation

• a.   If a text has several lexical chains, it surely is coherent

• a.   We can use them for the segmentation of texts.

• a.   If a text has several lexical chains it may be coherent

• a.   We can use them for discourse analysis

We may say about the sentence "Jim comforted Kevin because he was so upset" that

• a.   Coreference resolution is ambiguous.

• a.   It is not cohesive

• a.   None of the other options

• a.   It is not coherent

• a.   It is an example of a Winograd schema

What advantage has LDA as compared to LSA?

• a.   It differentiates senses of words

• a.   None of the other options

• a.   LSA does not create semantic spaces

• a.   LDA uses deep neural networks

• a.   It does not have an advantage as compared to LSA

What are illocutionary acts?

• a.   The consequence of a perlocutionary act

• a.   A way to induce an action not explicitly asked

• a.   A consequence of a locutionary act

• a.   A kind of speech acts

• a.   None of the other options

Multi-parties chat conversations, as compared to those with two participants, have these features:

• a.   Zipf's law may be applied

• a.   Turn taking strategies are changing

• a.   There are no differences

• a.   Multiple threads of discussion may appear in parallel

• a.   Speech acts cannot be identified anymore

Coreference resolution may need:

• a.   Inferences

• a.   A history list

• a.   Named Entity Recognition

• a.   Clustering

• a.   Part of Speech Tagging

We can say about the semantic distance of Rada that:

• a.   It is the simplest to compute semantic distance

• a.   It is the semantic distance with the best results

• a.   It cannot be used for WordNet

• a.   It is more suited to a semantic network than a taxonomy

• a.   It does not depend on the position where is measured in an ontology