A Frequency-Based Algorithm for Argument Extraction from Russian Treebanks
A Frequency-Based Algorithm for Argument Extraction from Russian Treebanks

Summary/Abstract: Arguments, unlike adjuncts, are typically understood as verb-specific dependents, which includesthe fact that the morphosyntactic devices used for argument encoding are determined by individualverbs. Building on this observation, we operationalize arguments as dependents whose encodingdevice occurs with a given verb at a significantly higher-than-average frequency. We apply an argumentextraction algorithm to a dataset of 132,221 verb dependents from Russian treebanks availablein the Universal Dependencies (UD) platform. To evaluate the algorithm ’ s performance, we compareits results to a manually annotated subset, informed by The Active Dictionary and a detailedsemantic understanding of argumenthood. The frequency-based algorithm achieves acceptableprecision (approx. 0.83), with particularly few false positives, making it a promising tool for crosslinguisticapplications in typologically diverse languages with UD treebanks. Theoretically, we arguethat a quantitative distributional approach to valency—originally proposed in Ju. D. Apresjan ’ s earlypioneering work—broadly aligns with the in-depth semantic analyses of individual verbs andtheir meanings found in his later works, including The Active Dictionary.

• Details
• Contents