Isn't it ironic in your language?
Problem being addressed
While multilinguality has been widely investigated in information retrieval and several tasks (e.g., sentiment analysis), no one explored it for irony, which has gained relevance recently, due to its importance to extract information from texts.
The first multilingual (French, English and Arabic) and multicultural (Indo-European languages vs. less culturally close languages) irony detection system. The approach does not rely either on machine translation or parallel corpora, but rather builds on previous corpus-based studies that show that irony is a universal phenomenon and many languages share similar irony devices.
Advantages of this solution
The novel system shows that simple monolingual architectures trained separately on each language can be successfully used in a multilingual setting providing a cross-lingual word representation or basic surface features. The multilingual experiments confirmed that the door is open towards multilingual approaches for irony detection. Furthermore, the results showed that irony detection can be applied to languages that lack of annotated data.
Solution originally applied in these industries
Possible New Application of the Work
Detecting irony can produce more accurate matches of user queries, enriching information retrieval with new operators to enable the non-literal retrieval of creative expressions.
The performances of sentiment analysis systems drastically decrease when applied to ironic texts, so accurate irony detection can significantly improve the performance of chat bots and virtual assistants.
Source URL: #############