🤖 AI Summary
This paper addresses online dependency parsing by proposing a word-by-word, real-time parsing algorithm aligned with human linguistic cognition. The method dynamically constructs a dependency tree incrementally, assigning each input token its head immediately upon arrival—without backtracking or global reanalysis. Built upon a dynamic programming framework, the algorithm has a theoretical worst-case time complexity of O(n³); however, empirical evaluation shows this bound is attained only for extremely short sentences (n ≤ 15), while for typical sentence lengths (n > 20), practical runtime scales nearly linearly. Its primary contribution lies in unifying cognitive plausibility—specifically, incremental attachment and zero backtracking—with provably polynomial time complexity within a single algorithmic framework. This design substantially improves both accuracy and robustness over conventional greedy online parsers. Moreover, it furnishes a linguistically interpretable and formally verifiable syntactic foundation for neuro-symbolic language processing models.
📝 Abstract
This paper presents a fundamental algorithm for parsing natural language sentences into dependency trees. Unlike phrase-structure (constituency) parsers, this algorithm operates one word at a time, attaching each word as soon as it can be attached, corresponding to properties claimed for the parser in the human brain. Like phrase-structure parsing, its worst-case complexity is $O(n^3)$, but in human language, the worst case occurs only for small $n$.