Identifying Intensity of the Structure and Content in Tweets and the Discriminative Power of Attributes in Context with Referential Translation Machines
This work addresses incremental improvements in natural language processing for tasks like emotion analysis in tweets, but lacks broad impact or novelty.
The paper tackled the problem of identifying similarity between attributes and words, and predicting intensity of structure and content in tweets, using referential translation machines (RTMs) and machine translation performance prediction (MTPP). It reported encouraging results for tasks in English, Arabic, and Spanish, but did not provide specific numerical metrics.
We use referential translation machines (RTMs) to identify the similarity between an attribute and two words in English by casting the task as machine translation performance prediction (MTPP) between the words and the attribute word and the distance between their similarities for Task 10 with stacked RTM models. RTMs are also used to predict the intensity of the structure and content in tweets in English, Arabic, and Spanish in Task 1 where MTPP is between the tweets and the set of words for the emotion selected from WordNet affect emotion lists. Stacked RTM models obtain encouraging results in both.