Transition-based Spinal Parsing
نویسندگان
چکیده
We present a transition-based arc-eager model to parse spinal trees, a dependencybased representation that includes phrasestructure information in the form of constituent spines assigned to tokens. As a main advantage, the arc-eager model can use a rich set of features combining dependency and constituent information, while parsing in linear time. We describe a set of conditions for the arc-eager system to produce valid spinal structures. In experiments using beam search we show that the model obtains a good trade-off between speed and accuracy, and yields state of the art performance for both dependency and constituent parsing measures.
منابع مشابه
An improved joint model: POS tagging and dependency parsing
Dependency parsing is a way of syntactic parsing and a natural language that automatically analyzes the dependency structure of sentences, and the input for each sentence creates a dependency graph. Part-Of-Speech (POS) tagging is a prerequisite for dependency parsing. Generally, dependency parsers do the POS tagging task along with dependency parsing in a pipeline mode. Unfortunately, in pipel...
متن کاملArc-Standard Spinal Parsing with Stack-LSTMs
We present a neural transition-based parser for spinal trees, a dependency representation of constituent trees. The parser uses Stack-LSTMs that compose constituent nodes with dependency-based derivations. In experiments, we show that this model adapts to different styles of dependency relations, but this choice has little effect for predicting constituent structure, suggesting that LSTMs induc...
متن کاملTransition-Based Parsing
Transition-based models for dependency parsing use a factorization defined in terms of a transition system, or abstract state machine. In this lecture, I will introduce the arc-eager and arcstandard transition systems for dependency parsing (§1) and discuss two different approaches to learning and decoding with these models: greedy classifier-based parsing (§2) and beam search and structured le...
متن کاملLTAG-spinal and the Treebank a new resource for incremental, dependency and semantic parsing
Abstract. We introduce LTAG-spinal, a novel variant of traditional Lexicalized Tree Adjoining Grammar (LTAG) with desirable linguistic, computational and statistical properties. Unlike in traditional LTAG, subcategorization frames and the argument-adjunct distinction are left underspecified in LTAG-spinal. LTAG-spinal with adjunction constraints is weakly equivalent to LTAG. The LTAG-spinal for...
متن کاملComparing Classifiers for (a special case of) Transition-Based Parsing
Transition-based parsing has proven to be very competitive. Part of the reason for this is that with respect to machine learning the parsing reduces to multi-class classification. This allows the use of very powerful machine learning algorithms such as Support Vector Machines. If we can find an even better classifier we would expect better parsing results. We will therefore try out different cl...
متن کامل