GLR parser

Abstract: A parsing algorithm which seems to be the most efficient general context-free algorithm known is described. It is similar to both Knuth's LR(k) algorithm and the familiar top-down algorithm. It has...

Abstract: There has been much recent interest in languages whose grammar is sufficiently simple that an efficient left-to-right parsing algorithm can be mechanically produced from the grammar. In this paper, we define LR(k) grammars, which are perhaps the most general ones of this type, and they provide the basis for understanding all of the special tricks which have been used in the construction of parsing algorithms for languages with simple structure, e.g. algebraic languages. We give algorithms for deciding if a given grammar satisfies the LR(k) condition, for given k, and also give methods for generating recognizes for LR(k) grammars. It is shown that the problem of whether or not a grammar is LR(k) for some k is undecidable, and the paper concludes by establishing various connections between LR(k) grammars and deterministic languages. In particular, the LR(k) condition is a natural analogue, for grammars, of the deterministic condition, for languages.

Abstract: Transition-based dependency parsers usually use transition systems that monotonically extend partial parse states until they identify a complete parse tree. Honnibal et al. (2013) showed that greedy onebest parsing accuracy can be improved by adding additional non-monotonic transitions that permit the parser to “repair” earlier parsing mistakes by “over-writing” earlier parsing decisions. This increases the size of the set of complete parse trees that each partial parse state can derive, enabling such a parser to escape the “garden paths” that can trap monotonic greedy transition-based dependency parsers. We describe a new set of non-monotonic transitions that permits a partial parse state to derive a larger set of completed parse trees than previous work, which allows our parser to escape from a larger set of garden paths. A parser with our new nonmonotonic transition system has 91.85% directed attachment accuracy, an improvement of 0.6% over a comparable parser using the standard monotonic arc-eager transitions.

Abstract: This paper builds off recent work from Kiperwasser & Goldberg (2016) using neural attention in a simple graph-based dependency parser. We use a larger but more thoroughly regularized parser than other recent BiLSTM-based approaches, with biaffine classifiers to predict arcs and labels. Our parser gets state of the art or near state of the art performance on standard treebanks for six different languages, achieving 95.7% UAS and 94.1% LAS on the most popular English PTB dataset. This makes it the highest-performing graph-based parser on this benchmark---outperforming Kiperwasser Goldberg (2016) by 1.8% and 2.2%---and comparable to the highest performing transition-based parser (Kuncoro et al., 2016), which achieves 95.8% UAS and 94.6% LAS. We also show which hyperparameter choices had a significant effect on parsing accuracy, allowing us to achieve large gains over other graph-based approaches.