Constituency vs Dependency Parsing: What is more effective for Sentiment Analysis?

0

Parsing is often used to understand the sentiment of complex sentences filled with double negations or very articulated.

There are two main ways of parsing a sentence: Constituency and Dependency Parsing. What is the most successful application for Sentiment Analysis?

Leevo

Posted 2020-06-22T08:07:05.110

Reputation: 4 928

Answers

2

Both approaches have been used for sentiment analysis in the literature. From a quick search, we can find these results:

It seems to me that constituency parsing has been used more than dependency parsing. My sample, however, is very small and focused on the English language. I think this may change in languages with more complex (and more non-projective) syntax.

That been said, I think currently neither of them are considered to be state of the art in sentiment analysis. If we take a look at the leaderboards of sentiment analysis tasks from paperswithcode, all of the leading approaches (BERT, RoBERTa, M5) handle text as a mere sequence of tokens. While these results are from only a

noe

Posted 2020-06-22T08:07:05.110

Reputation: 10 494

Yeah, BERT and all the Transformer-based family is SOTA, and parsing is no longer hot. I just need a parsing model to make some "NLP experiments" with the syntactic structures. Something that, as you explained, is not done by Transformers. – Leevo – 2020-06-22T21:39:57.587