IWPT

Ambiguities arising from alternations of scope in interpretations for multiply quantified sentences appear to require grammatical operations that compromise the strong assumptions of syntactic/semantic transparency and monotonicity underlying the Frege-...

We present a formal framework that generalizes a variety of monolingual and synchronous grammar formalisms for parsing and translation. Our framework is based on regular tree grammars that describe derivation trees, which are interpreted in arbitrary ...

Restricting the input or the output of a grammar-induced translation to a given set of trees plays an important role in statistical machine translation. The problem for practical systems is to find a compact (and in particular, finite) representation of ...

The problem of finding the most probable string for a distribution generated by a weighted finite automaton or a probabilistic grammar is related to a number of important questions: computing the distance between two distributions or finding the best ...

We present a simple and effective way to perform out-of-domain statistical parsing by drastically reducing lexical data sparseness in a PCFG-LA architecture. We replace terminal symbols with unsupervised word clusters acquired from a large newspaper ...

Instance-weighting has been shown to be effective in statistical machine translation (Foster et al., 2010), as well as cross-language adaptation of dependency parsers (Søgaard, 2011). This paper presents new methods to do instance-weighting in state-of-...

This paper discusses the difficulties in Chinese deep parsing, by comparing the accuracy of a Chinese HPSG parser to the accuracy of an English HPSG parser and the commonly used Chinese syntactic parsers. Analysis reveals that deep parsing for Chinese ...

We investigate the question whether an explicit feature representation for morphological features is necessary when parsing German with a fully lexicalized, statistical dependency parser. We use two morphosyntactic phenomena of German to show that while ...

This paper proposes a framework which unifies graphical model theory and formal language theory through automata theory. Specifically, we propose Bayesian Network Automata (BNAs) as a formal framework for specifying graphical models of arbitrarily large ...

In this paper, we present a model-theoretic description of Property Grammar (PG) with features. Our approach is based on previous work of Duchier et al. (2009), and extends it by giving a model-theoretic account of feature-based properties, which was ...

Using semi-supervised EM, we learn finegrained but sparse lexical parameters of a generative parsing model (a PCFG) initially estimated over the Penn Treebank. Our lexical parameters employ supertags, which encode complex structural information at the ...

In this paper, we describe and compare two statistical parsing approaches for the hybrid dependency-constituency syntactic representation used in the Quranic Arabic Treebank (Dukes and Buckwalter, 2010). In our first approach, we apply a multi-step ...

This paper proposes a direct parsing of non-local dependencies in English. To this end, we use probabilistic linear context-free rewriting systems for data-driven parsing, following recent work on parsing German. In order to do so, we first perform a ...

Among human cognitive abilities, language is singular in the diversity of its manifestations: over 6000 languages are spoken in the world today. Some of the major challenges in modelling how language is processed by the human brain thus lie in ...

The paper demonstrates how the generic parser of a minimally supervised information extraction framework can be adapted to a given task and domain for relation extraction (RE). For the experiments a generic deep-linguistic parser was employed that works ...

Prepositional phrase attachment is an important subproblem of parsing, performance on which suffers from limited availability of labelled data. We present a semi-supervised approach. We show that a discriminative lexical model trained from labelled data,...

Current successful probabilistic parsers require large treebanks which are difficult, time consuming, and expensive to produce. Some parts of these data do not contain any useful information for training a parser. Active learning strategies allow to ...

There has been a long history in combinatorial optimization of methods that exploit structure in complex problems, using methods such as dual decomposition or Lagrangian relaxation. These methods leverage the observation that complex inference problems ...

We present a novel method for the computation of prefix probabilities for linear context-free rewriting systems. Our approach streamlines previous procedures to compute prefix probabilities for context-free grammars, synchronous context-free grammars ...

We present a matrix encoding of context-free grammars, motivated by hardware-level efficiency considerations. We find efficiency gains of 2.5--9x for exhaustive inference and approximately 2x for pruned inference, resulting in high-accuracy parsing at ...

Low-latency solutions for syntactic parsing are needed if parsing is to become an integral part of user-facing natural language applications. Unfortunately, most state-of-the-art constituency parsers employ large probabilistic context-free grammars for ...

We present a deterministic HPSG parser capable of processing text incrementally with very fast parsing times. Our system demonstrates an efficient data-driven approach that achieves a high level of precision. Through a series of experiments in different ...

We present a novel corpus-driven approach towards grammar approximation for a linguistically deep Head-driven Phrase Structure Grammar. With an unlexicalized probabilistic context-free grammar obtained by Maximum Likelihood Estimate on a large-scale ...

Radically different approaches have been proved to be effective for phrase-structure and dependency parsers in the last decade. Here, we aim to exploit the divergence in these approaches and show the utility of features extracted from the automatic ...

We compare the use of edited text in the form of newswire and unedited text in the form of discussion forum posts as sources for training material in a self-training experiment involving the Brown reranking parser and a test set of sentences from an ...

In this paper, we give a summary of various dependency chart parsing algorithms in terms of the use of parsing histories for a new dependency arc decision. Some parsing histories are closely related to the target dependency arc, and it is necessary for ...

We present a perspective on parser evaluation in a context where the goal of parsing is to extract meaning from a sentence. Using this perspective, we show why current parser evaluation metrics are not suitable for evaluating parsers that produce ...

We consider the problem of parsing a sentence that is partially annotated with information about where phrases start and end. The application domain is interactive parse selection with probabilistic grammars. It is explained that the main obstacle is ...

To detect errors in automatically-obtained dependency parses, we take a grammar-based approach. In particular, we develop methods that incorporate n-grams of different lengths and use information about possible parse revisions. Using our methods allows ...