Capturing rich response relationships with small-data neural networks

A non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause a computer system to:

• receive an input sentence comprising a plurality of words;
• determine a part of speech for each word of the plurality of words;
• determine, by a response classification neural network, a response classification label for each word of the plurality of words based on the determined parts of speech for each word of the plurality of words, wherein the response classification neural network associates word-agnostic vectors comprising parts of speech;
• and
• present, to a user, a target portion and an opinion portion of the input sentence based on the response classification label determined for each word of the plurality of words from the input sentence.

A method comprising:

• receiving a training dataset comprising a plurality of sentences, each sentence associated with a plurality of words;
• generating word-agnostic vectors for each word of the plurality of words associated with each sentence of the plurality of sentences based on:
• a part of speech label assigned to each word of the plurality of words;
• a dependency label assigned to each word of the plurality of words;
• and
• a response classification label assigned to each word of the plurality of words;
• training a response classification neural network based on the word-agnostic vectors for each word of the plurality of words associated with each sentence of the plurality of sentences;
• determining parts of speech for one or more words in an input sentence;
• based on the parts of speech for the one or more words, determining, by the trained response classification neural network, a response classification label for each of the one or more words from the input sentence;
• and
• providing a target portion and an opinion portion of the input sentence based on the response classification label determined for each word of the one or more words from the input sentence.