Machine learning and different synthetic intelligence (AI) strategies have had immense success with scientific and technical duties equivalent to predicting how protein molecules fold and recognising faces in a crowd. However, the utility of those strategies to the humanities are but to be totally explored.
What can AI tell us about philosophy and faith, for instance? As a place to begin for such an exploration, we used deep learning AI strategies to analyse English translations of the Bhagavad Gita, an historical Hindu textual content written initially in Sanskrit.
Using a deep learning-based language mannequin referred to as BERT, we studied sentiment (feelings) and semantics (meanings) in the translations. Despite large variations in vocabulary and sentence construction, we discovered that the patterns of emotion and which means have been broadly comparable in all three.
This analysis opens a path to the use of AI-based applied sciences for evaluating translations and reviewing sentiments in a variety of texts.
An historical e book of knowledge
The Bhagavad Gita is one in every of the central Hindu sacred and philosophical texts. Written greater than 2,000 years in the past, it has been translated into greater than 100 languages and has been of curiosity to western philosophers since the 18th century.
The 700-verse poem is part of the bigger Mahabharata epic, which recounts the occasions of an historical battle believed to have occurred at Kurukshetra close to modern-day Delhi in India.
Read extra:
Indian philosophy helps us see clearly, act correctly in an interconnected world
The textual content of the Bhagavad Gita relates a dialog between the Hindu deity Lord Krishna and a prince referred to as Arjuna. They talk about whether or not a soldier ought to go to battle for ethics and obligation (or “dharma”) if they’ve shut buddies or household on the opposing facet.
The textual content has been instrumental in laying the foundations of Hinduism. Among many different issues, it’s the place the philosophy of karma (a non secular precept of trigger and impact) originates.
Scholars have additionally regarded the Bhagavad Gita as a e book of psychology, administration, management and battle decision.
Countless translations
The first of many English translations of the Bhagavad Gita was printed in 1785.
Wikimedia Commons, CC BY
There have been numerous English translations of the Bhagavad Gita, however there’s not a lot work that validates their high quality. Translations of songs and poems not solely break rhythm and rhyming patterns, however can additionally lead to the lack of semantic info.
In our analysis, we used deep learning language fashions to analyse three chosen translations of the Bhagavad Gita (from Sanskrit to English) with semantic and sentiment analyses which assist in the analysis of translation high quality.
We used a pre-trained language mannequin often known as BERT, developed by Google. We additional tuned the mannequin utilizing a human-labelled coaching dataset primarily based on Twitter posts, which captures 10 totally different sentiments.
These sentiments (optimistic, grateful, empathetic, pessimistic, anxious, unhappy, irritated, denial, shock, and joking) have been adopted from our earlier analysis into social media sentiment throughout the onset of the COVID-19 pandemic.
A schematic diagram exhibiting how the AI evaluation works.
Chandra, Author offered
Patterns of sentiment
The three translations we studied used very totally different vocabulary and syntax, however the language mannequin recognised comparable sentiments in the totally different chapters of the respective translations. According to our mannequin, optimistic, irritated and shocked sentiments are the most expressed.
Sentiments captured by our language mannequin for various translations of the Bhagavad Gita.
Chandra and Kulkarni, Author offered
Moreover, the mannequin confirmed how the total sentiment polarity modifications (from adverse to constructive) over the course of the dialog between Arjuna and Lord Krishna.
Arjuna is pessimistic in the direction of the starting and turns into optimistic as Lord Krisha imparts information of Hindu philosophy to him. The sentiments expressed by Krishna present that with philosophical information of dharma and mentorship, a troubled thoughts can get readability for making the proper choices in instances of battle.
One limitation of our mannequin is that it was skilled on information from Twitter, so it recognises “joking” as a standard sentiment. It applies this label inappropriately to some elements of the Bhagavad Gita. Humour is difficult and strongly culturally constrained, and understanding it’s an excessive amount of to ask of our mannequin at this stage.
Due to the nature of the Sanskrit language, the indisputable fact that the Bhagavad Gita is a music with rhythm and rhyme, and the assorted dates of the translations, totally different translators used totally different vocabulary to explain the similar ideas.
The desk under exhibits a few of the most semantically comparable verses from the three translations.
The makes use of of sentiment evaluation
Our analysis factors the method to the use of AI-based applied sciences for evaluating translations and reviewing sentiments in a variety of texts.
This expertise can even be prolonged to evaluation sentiments expressed in leisure media. Another potential utility is analysing motion pictures and songs to offer insights to oldsters and authorities about the suitability of content material for youngsters.
The creator want to acknowledge the invaluable contribution of Venkatesh Kulkarni to this analysis.
https://theconversation.com/ai-philosophy-and-religion-what-machine-learning-can-tell-us-about-the-bhagavad-gita-182517
