Computational Linguistics, Volume 44, Issue 2 - June 2018
- Anthology ID:
- Cambridge, MA
- MIT Press
Computational Linguistics, Volume 44, Issue 2 - June 2018
A Dependency Perspective on RST Discourse Parsing and Evaluation
Mathieu Morey | Philippe Muller | Nicholas Asher
Computational text-level discourse analysis mostly happens within Rhetorical Structure Theory (RST), whose structures have classically been presented as constituency trees, and relies on data from the RST Discourse Treebank (RST-DT); as a result, the RST discourse parsing community has largely borrowed from the syntactic constituency parsing community. The standard evaluation procedure for RST discourse parsers is thus a simplified variant of PARSEVAL, and most RST discourse parsers use techniques that originated in syntactic constituency parsing. In this article, we isolate a number of conceptual and computational problems with the constituency hypothesis. We then examine the consequences, for the implementation and evaluation of RST discourse parsers, of adopting a dependency perspective on RST structures, a view advocated so far only by a few approaches to discourse parsing. While doing that, we show the importance of the notion of headedness of RST structures. We analyze RST discourse parsing as dependency parsing by adapting to RST a recent proposal in syntactic parsing that relies on head-ordered dependency trees, a representation isomorphic to headed constituency trees. We show how to convert the original trees from the RST corpus, RST-DT, and their binarized versions used by all existing RST parsers to head-ordered dependency trees. We also propose a way to convert existing simple dependency parser output to constituent trees. This allows us to evaluate and to compare approaches from both constituent-based and dependency-based perspectives in a unified framework, using constituency and dependency metrics. We thus propose an evaluation framework to compare extant approaches easily and uniformly, something the RST parsing community has lacked up to now. We can also compare parsers’ predictions to each other across frameworks. This allows us to characterize families of parsing strategies across the different frameworks, in particular with respect to the notion of headedness. Our experiments provide evidence for the conceptual similarities between dependency parsers and shift-reduce constituency parsers, and confirm that dependency parsing constitutes a viable approach to RST discourse parsing.
Unrestricted Bridging Resolution
Yufang Hou | Katja Markert | Michael Strube
In contrast to identity anaphors, which indicate coreference between a noun phrase and its antecedent, bridging anaphors link to their antecedent(s) via lexico-semantic, frame, or encyclopedic relations. Bridging resolution involves recognizing bridging anaphors and finding links to antecedents. In contrast to most prior work, we tackle both problems. Our work also follows a more wide-ranging definition of bridging than most previous work and does not impose any restrictions on the type of bridging anaphora or relations between anaphor and antecedent. We create a corpus (ISNotes) annotated for information status (IS), bridging being one of the IS subcategories. The annotations reach high reliability for all categories and marginal reliability for the bridging subcategory. We use a two-stage statistical global inference method for bridging resolution. Given all mentions in a document, the first stage, bridging anaphora recognition, recognizes bridging anaphors as a subtask of learning fine-grained IS. We use a cascading collective classification method where (i) collective classification allows us to investigate relations among several mentions and autocorrelation among IS classes and (ii) cascaded classification allows us to tackle class imbalance, important for minority classes such as bridging. We show that our method outperforms current methods both for IS recognition overall as well as for bridging, specifically. The second stage, bridging antecedent selection, finds the antecedents for all predicted bridging anaphors. We investigate the phenomenon of semantically or syntactically related bridging anaphors that share the same antecedent, a phenomenon we call sibling anaphors. We show that taking sibling anaphors into account in a joint inference model improves antecedent selection performance. In addition, we develop semantic and salience features for antecedent selection and suggest a novel method to build the candidate antecedent list for an anaphor, using the discourse scope of the anaphor. Our model outperforms previous work significantly.
Spurious Ambiguity and Focalization
Glyn Morrill | Oriol Valentín
Spurious ambiguity is the phenomenon whereby distinct derivations in grammar may assign the same structural reading, resulting in redundancy in the parse search space and inefficiency in parsing. Understanding the problem depends on identifying the essential mathematical structure of derivations. This is trivial in the case of context free grammar, where the parse structures are ordered trees; in the case of type logical categorial grammar, the parse structures are proof nets. However, with respect to multiplicatives, intrinsic proof nets have not yet been given for displacement calculus, and proof nets for additives, which have applications to polymorphism, are not easy to characterize. In this context we approach here multiplicative-additive spurious ambiguity by means of the proof-theoretic technique of focalization.
The Influence of Context on the Learning of Metrical Stress Systems Using Finite-State Machines
Cesko Voeten | Menno van Zaanen
Languages vary in the way stress is assigned to syllables within words. This article investigates the learnability of stress systems in a wide range of languages. The stress systems can be described using finite-state automata with symbols indicating levels of stress (primary, secondary, or no stress). Finite-state automata have been the focus of research in the area of grammatical inference for some time now. It has been shown that finite-state machines are learnable from examples using state-merging. One such approach, which aims to learn k-testable languages, has been applied to stress systems with some success. The family of k-testable languages has been shown to be efficiently learnable (in polynomial time). Here, we extend this approach to k, l-local languages by taking not only left context, but also right context, into account. We consider empirical results testing the performance of our learner using various amounts of context (corresponding to varying definitions of phonological locality). Our results show that our approach of learning stress patterns using state-merging is more reliant on left context than on right context. Additionally, some stress systems fail to be learned by our learner using either the left-context k-testable or the left-and-right-context k, l-local learning system. A more complex merging strategy, and hence grammar representation, is required for these stress systems.
Tree Structured Dirichlet Processes for Hierarchical Morphological Segmentation
Burcu Can | Suresh Manandhar
This article presents a probabilistic hierarchical clustering model for morphological segmentation. In contrast to existing approaches to morphology learning, our method allows learning hierarchical organization of word morphology as a collection of tree structured paradigms. The model is fully unsupervised and based on the hierarchical Dirichlet process. Tree hierarchies are learned along with the corresponding morphological paradigms simultaneously. Our model is evaluated on Morpho Challenge and shows competitive performance when compared to state-of-the-art unsupervised morphological segmentation systems. Although we apply this model for morphological segmentation, the model itself can also be used for hierarchical clustering of other types of data.
Domain-Sensitive Temporal Tagging By Jannik Strötgen, Michael Gertz