查看更多>>摘要:By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Investigators publish new report on ar tificial intelligence. According to news originating from Haifa, Israel, by News Rx correspondents, research stated, “The authenticity of classical Arabic poetry has long been challenged by claims that some part of the pre-Islamic poetic her itage should not be attributed to this era. According to these assertions, some of this legacy was produced after the advent of Islam and ascribed, for differen t reasons, to pre-Islamic poets.” The news reporters obtained a quote from the research from University of Haifa: “As pre-Islamic poets were illiterate, medieval Arabic literature devotees relie d on Bedouin oral transmission when writing down and collecting the poems about two centuries later. This process left the identity of the real poets who compos ed these poems and the period in which they worked unresolved. In this work, we seek to answer the questions of how and to what extent we can identify the perio d in which classical Arabic poetry was composed, where we exploit modern-day aut omatic text processing techniques for this aim. We consider a dataset of Arabic poetry collected from the diwans (‘collections of poems’) of thirteen Arabic poe ts that corresponds to two main eras: the pre- Abbasid era (covering the period between the 6th and the 8th centuries CE) and the Abbasid era (starting in the y ear 750 CE). Some poems in each diwan are considered ‘original’; i.e., poems tha t are attributed to a certain poet with high confidence. The diwans also include , however, an additional section of poems that are attributed to a poet with res ervations, meaning that these poems might have been composed by another poet and /or in another period. We trained a set of machine learning algorithms (classifi ers) in order to explore the potential of machine learning techniques to automat ically identify the period in which a poem had been written. In the training pha se, we represent each poem using various types of features (characteristics) des igned to capture lexical, topical, and stylistic aspects of this poetry. By trai ning and assessing automatic models of period prediction using the ‘original’ po etry, we obtained highly encouraging results, measuring between 0.73-0.90 in ter ms of F1 for the various periods. Moreover, we observe that the stylistic featur es, which pertain to elements that characterize Arabic poetry, as well as the ot her feature types, are all indicative of the period in which the poem had been w ritten.”