Neural Decipherment via Minimum-Cost Flow: from Ugaritic to Linear B
This addresses the challenge of deciphering ancient scripts for historians and linguists, representing a novel method rather than an incremental improvement.
The paper tackles the problem of automatic decipherment of lost languages like Ugaritic and Linear B, achieving a 5.5% absolute improvement over state-of-the-art for Ugaritic and correctly translating 67.3% of cognates for Linear B.
In this paper we propose a novel neural approach for automatic decipherment of lost languages. To compensate for the lack of strong supervision signal, our model design is informed by patterns in language change documented in historical linguistics. The model utilizes an expressive sequence-to-sequence model to capture character-level correspondences between cognates. To effectively train the model in an unsupervised manner, we innovate the training procedure by formalizing it as a minimum-cost flow problem. When applied to the decipherment of Ugaritic, we achieve a 5.5% absolute improvement over state-of-the-art results. We also report the first automatic results in deciphering Linear B, a syllabic language related to ancient Greek, where our model correctly translates 67.3% of cognates.