Task 18 at SemEval 2015 defines BroadCoverage Semantic Dependency Parsing (SDP) as the problem of recovering sentence-internal predicate-argument relationships for all content words, i.e. the semantic structure constituting the relational core of sentence meaning. In this task description, we position the problem in comparison to other language analysis sub-tasks, introduce and compare the semantic dependency target representations used, and summarize the task setup, participating systems, and main results.
Task 8 at SemEval 2014 defines Broad-Coverage Semantic Dependency Parsing (SDP) as the problem of recovering sentence-internal predicate-argument relationships for all content words, i.e. the semantic structure constituting the relational core of sentence meaning. In this task description, we position the problem in comparison to other sub-tasks in computational language analysis, introduce the semantic dependency target representations used, reflect on high-level commonalities and differences between these representations, and summarize the task setup, participating systems, and main results.
Syntactic parsing requires a fine balance between expressivity and complexity, so that naturally occurring structures can be accurately parsed without compromising efficiency. In dependency-based parsing, several constraints have been proposed that restrict the class of permissible structures, such as projectivity, planarity, multi-planarity, well-nestedness, gap degree, and edge degree. While projectivity is generally taken to be too restrictive for natural language syntax, it is not clear which of the other proposals strikes the best balance between expressivity and complexity. In this paper, we review and compare the different constraints theoretically, and provide an experimental evaluation using data from two treebanks, investigating how large a proportion of the structures found in the treebanks are permitted under different constraints. The results indicate that a combination of the well-nestedness constraint and a parametric constraint on discontinuity gives a very good fit with the linguistic data.
The 2019 Shared Task at the Conference for Computational Language Learning (CoNLL) was devoted to Meaning Representation Parsing (MRP) across frameworks. Five distinct approaches to the representation of sentence meaning in the form of directed graphs were represented in the training and evaluation data for the task, packaged in a uniform graph abstraction and serialization. The task received submissions from eighteen teams, of which five do not participate in the official ranking because they arrived after the closing deadline, made use of extra training data, or involved one of the task co-organizers. All technical information regarding the task, including system submissions, official results,
We study the generalization of maximum spanning tree dependency parsing to maximum acyclic subgraphs. Because the underlying optimization problem is intractable even under an arc-factored model, we consider the restriction to noncrossing dependency graphs. Our main contribution is a cubic-time exact inference algorithm for this class. We extend this algorithm into a practical parser and evaluate its performance on four linguistic data sets used in semantic dependency parsing. We also explore a generalization of our parsing framework to dependency graphs with pagenumber at most k and show that the resulting optimization problem is NP-hard for k ≥ 2.
ForewordSince 2002, FoLLI, the Association for Logic, Language, and Information (www.folli.org), has awarded an annual prize for an outstanding dissertation in the fields of logic, language, and information. The prize is named after the well-known Dutch logician Evert Willem Beth, whose interdisciplinary interests are in many ways exemplary of the aims of FoLLI. It is sponsored by the E.W. Beth Foundation. Dissertations submitted for the prize are judged on technical depth and strength, originality, and impact made in at least two of the three fields of logic, language, and computation. Every year the competition is strong and the interdisciplinary character of the award stimulates lively debate in the Beth Prize Committee.Recipients of the award are offered the opportunity to prepare a book version of their thesis for publication in the FoLLI Publications on Logic, Language and Information. This volume is based on the PhD thesis of Marco Kuhlmann, who was a joint winner of the E.W. Beth dissertation award in 2008. We wish to quote here the Committee's motivation for co-awarding the Beth Prize to him: Marco Kuhlmann's thesis on 'Dependency Structures and Lexicalized Grammars', in the area of Language and Computation, lays new theoretical foundations for the study of non-projective dependency grammars. Such grammars have recently become increasingly important for approaches to statistical parsing in computational linguistics that deal with free word order and long-distance dependencies. Dr. Kuhlmann provides new formal tools to define and understand dependency grammars, presents two new dependency language hierarchies with polynomial parsing algorithms, establishes the practical significance of these hierarchies through corpus studies, and links his work to the phrase-structure grammar tradition through an equivalence result with tree-adjoining grammars. Dr. Kuhlmann's thesis bridges gaps between linguistics and theoretical computer science, PrefaceThis book reports the major results of roughly four years of doctoral research. Among the many people who have contributed to it, there are some to whom I owe a particularly large debt of gratitude.My first thanks goes to my supervisor, Gert Smolka. He granted me the freedom to develop my own ideas, encouraged me to strive for simplicity in their presentation, and provided guidance and advice. I also thank Manfred Pinkal and Aravind Joshi for accepting to give their expert opinion on this dissertation, and to Raimund Seidel and Tilman Becker for agreeing to join my examination committee.Guido Tack, as my office-mate, had to suffer from my meanderings on a large number of sometimes errant ideas related to this dissertation. I thank him for the patience he had with me, for his valuable feedback, and most of all, for his friendship. Mathias Möhl bore with me in endless discussions, and made essential contributions to this work. Joachim Niehren introduced me to tree automata and the algebraic perspective on formal languages. Without him, the machinery used in this diss...
An open problem in dependency parsing is the accurate and efficient treatment of non-projective structures. We propose to attack this problem using chart-parsing algorithms developed for mildly contextsensitive grammar formalisms. In this paper, we provide two key tools for this approach. First, we show how to reduce nonprojective dependency parsing to parsing with Linear Context-Free Rewriting Systems (LCFRS), by presenting a technique for extracting LCFRS from dependency treebanks. For efficient parsing, the extracted grammars need to be transformed in order to minimize the number of nonterminal symbols per production. Our second contribution is an algorithm that computes this transformation for a large, empirically relevant class of grammars.
Syntactic representations based on word-to-word dependencies have a long-standing tradition in descriptive linguistics, and receive considerable interest in many applications. Nevertheless, dependency syntax has remained somewhat of an island from a formal point of view. Moreover, most formalisms available for dependency grammar are restricted to projective analyses, and thus not able to support natural accounts of phenomena such as wh-movement and cross–serial dependencies. In this article we present a formalism for non-projective dependency grammar in the framework of linear context-free rewriting systems. A characteristic property of our formalism is a close correspondence between the non-projectivity of the dependency trees admitted by a grammar on the one hand, and the parsing complexity of the grammar on the other. We show that parsing with unrestricted grammars is intractable. We therefore study two constraints on non-projectivity, block-degree and well-nestedness. Jointly, these two constraints define a class of “mildly” non-projective dependency grammars that can be parsed in polynomial time. An evaluation on five dependency treebanks shows that these grammars have a good coverage on empirical data
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.