Friday, October 14, 2011

Computational research
on Bible's authorship attribution /

Υπολογιστική διερεύνηση
για την απόδοση συγγραφής της Βίβλου

Computer program
to reveal who wrote the Bible

One of the key features used by Bible scholars to classify different components of biblical literature is synonym choice. The underlying hypothesis is that different authorial components are likely to differ in the proportions with which alternative words from a set of synonyms (synset) are used. This hypothesis played a part in the pioneering work of Astruc (1753) on the book of Genesis – using a single synset: divine names – and has been refined by many others using broader feature sets, such as that of Carpenter and Hartford-Battersby (1900). More recently, the synonym hypothesis has been used in computational work on authorship attribution of English texts in the work of Clark and Hannon (2007) and Koppel et al. (2006). [...]

We have shown that documents can be decomposed into authorial components with very high accuracy by using a two-stage process. First, we establish a reliable partial clustering of units by using synonym choice and then we use these partial clusters as training texts for supervised learning using generic words as features.

We have considered only decompositions into two components, although our method generalizes trivially to more than two components, for example by applying it iteratively. The real challenge is to determine the correct number of components, where this information is not given. We leave this for future work.

Despite this limitation, our success on munged biblical books suggests that our method can be fruitfully applied to the Pentateuch, since the broad consensus in the field is that the Pentateuch can be divided into two main threads, known as Priestly (P) and non-Priestly (Driver 1909). (Both categories are often divided further, but these subdivisions are more controversial.) We find that our split corresponds to the expert consensus regarding P and non-P for over 90% of the verses in the Pentateuch for which such consensus exists. We have thus been able to largely recapitulate several centuries of painstaking manual labor with our automated method. We offer those instances in which we disagree with the consensus for the consideration
of scholars in the field.

In this work, we have exploited the availability of tools for identifying synonyms in biblical literature. In future work, we intend to extend our methods to texts for which such tools are unavailable.

* Moshe Koppel, Navot Akiva, Idan Dershowitz and Nachum Dershowitz,
"Unsupervised Decomposition of a Document into Authorial Components"
Ακαθοδήγητη Αποσύνταξη ενός Εγγράφου στα Συγγραφικά Συστατικά»],
49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies,
Portland, Oregon (Monday 20 June, 2011). *

No comments: