Federico Sangati

Unsupervised Methods for Head Assignments

We present several algorithms for assigning heads in phrase structure trees, based on different linguistic intuitions on the role of heads in natural language syntax. Starting point of our approach is the observation that a head-annotated treebank defines a unique lexicalized tree substitution grammar. This allows us to go back and forth between the two representations, and define objective functions for the unsupervised learning of head assignments in terms of features of the implicit lexicalized tree grammars. We evaluate algorithms based on the match with gold standard head-annotations, and the comparative parsing accuracy of the lexicalized grammars they give rise to. On the first task, we approach the accuracy of hand-designed heuristics for English and inter-annotation-standard agreement for German. On the second task, the implied lexicalized grammars score 4% points higher on parsing accuracy than lexicalized grammars derived by commonly used heuristics.

A generative re-ranking model for dependency parsing

We propose a framework for dependency parsing based on a combination of discriminative and generative models. We use a discriminative model to obtain a k-best list of candidate parses, and subsequently rerank those candidates using a generative model. We show how this approach allows us to evaluate a variety of generative models, without needing different parser implementations. Moreover, we present empirical results that show a small improvement over state-of-the-art dependency parsing of English sentences.

Multiword Expression Identification with Recurring Tree Fragments and Association Measures

We present a novel approach for the identification of multiword expressions (MWEs). The methodology extracts a large set of recurring syntactic fragments from a given treebank using a Tree-Kernel method. Di erently from previous studies, the expressions underlying these fragments are arbitrarily long and can include intervening gaps. In the initial study we use these fragments to identify MWEs as a parsing task (in a supervised manner) as proposed by Green et al. (2011). Here we obtain a small improvement over previous results. In the second part, we compare various association measures in reranking the expressions underlying these fragments in an unsupervised fashion. We show how a newly defined measure (Log Inside Ratio) based on statistical parsing techniques is able to outperform classical association measures in the French data.