Glue Semantics

Glue Semantics (Glue) is a general framework for semantic composition and the syntax–semantics interface. The framework grew out of an interdisciplinary collaboration at the intersection of formal linguistics, formal logic, and computer science. Glue assumes a separate level of syntax; this can be any syntactic framework in which syntactic structures have heads. Glue uses a fragment of linear logic for semantic composition. General linear logic terms in Glue meaning constructors are instantiated relative to a syntactic parse. The separation of the logic of composition from structural syntax distinguishes Glue from other theories of semantic composition and the syntax–semantics interface. It allows Glue to capture semantic ambiguity, such as quantifier scope ambiguity, without necessarily positing an ambiguity in the syntactic structure. Glue is introduced here in relation to four of its key properties, which are used as organizing themes: resource-sensitive composition, flexible composition, autonomy of syntax, and syntax/semantics non-isomorphism. Expected final online publication date for the Annual Review of Linguistics, Volume 8 is January 2022. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

Meaning in LFG

This chapter discusses how meaning has been handled in Lexical-Functional Grammar. As well as giving a historical overview, it also argues that the modern approach, using Glue Semantics, has a number of undesirable properties: meanings do not figure at all in the architecture of the grammar, merely standing in an unspecified correspondence with semantic structures; s-structures themselves have become an enfeebled and unimportant part of the projection architecture; and meaning constructors, when written in the ‘new glue’ format, give the impression of being quite distinct from other kinds of functional annotation, making the semantic component seem out of sync with the rest of the formalism. To remedy these issues, Findlay suggests a mechanism for representing meanings explicitly in s-structures, and for integrating linear logic into the description language of LFG more generally. This has immediate benefits for the analysis of idioms and for the theory of the semantics-information structure interface.

The unrealized and the unheard

There are numerous well-known cases where syntactic theory has posited a phonologically null, unrealized/unheard morphosyntactic element. Examples include: null subjects, whether in so-called ‘pro-drop’ or as the target of equi control/raising; dropped arguments, as in non-transitive uses of semantically bivalent verbs (e.g., ‘eat’), or dropped operators, as in bare relatives; morphologically zero-marked diathesis, as demonstrated by inchoatives and inchoative-like verbs; and exceptional constituency associated with particular interpretations, as in so-called ‘constructions’, like the ‘way’-construction. This chapter first argues that null morphosyntactic elements are not necessarily precluded by LFG theory, but that they can be dispensed with, since a unified, general theory of the unrealized and the unheard is offered by templates and Glue Semantics.

Category theory

This chapter aims to introduce sufficient category theory to enable a formal understanding of the rest of the book. It first introduces the fundamental notion of a category. It then introduces functors, which are maps between categories. Next it introduces natural transformations, which are natural ways of mapping between functors. The stage is then set to at last introduces monads, which are defined in terms of functors and natural transformations. The last part of the chapter provides a compositional calculus with monads for natural language semantics (in other words, a logic for working with monads) and then relates the compositional calculus to Glue Semantics and to a very simple categorial grammar for parsing. The chapter ends with some exercises to aid understanding.

Implicit Arguments in English and Rutooro

The present study is a contrastive analysis of the syntactic behavior of verbs that are ontologically specified for objects but these objects may be left out without rendering sentences ungrammatical. The study unveils asymmetries between English and Rutooro (a Bantu language spoken in Uganda) in the (non-)omissibility of postverbal arguments, stemming from lexico-semantic and morphological factors as well as syntactic and discoursal factors. In light of the asymmetries arising from syntactic and discoursal factors, the study adopts a typology of indefinite implicit arguments that categorizes them into two: general indefinite implicit arguments and discourse-bound indefinite implicit arguments. Denotational nuances between synonyms as well as morphological specifications are also crucial linguistic ingredients that trigger variability in the syntactic behavior of synonymous verbs intralinguistically and cross-linguistically. In order to formalize the syntactic behavior of the verbs involved, the study employs the analytical tools provided by Lexical Functional Grammar (LFG). While Asudeh/Giorgolio (2012) use a combination of LFG and Glue Semantics in order to account for the occurrence of implicit arguments, this study proposes an alternative approach, by using only the LFG functional specifications in the lexical entries of the verbs under consideration without having recourse to an auxiliary framework. Using Bresnan (1978) as a point of departure and informed by proposals advanced by Nordlinger/Sadler (2007), the study posits a non-ambiguous bistructural analysis, with the postverbal argument instantiating the specification ± higher structure – a feature that caters for the (non-)omissibility of the postverbal argument.

Modification of DPs by epistemic adverbs

We examine two phenomena which, with the exception of Bogal-Allbritten & Weir (2017), have not been systematically studied together but are clearly related: (a) epistemic adverbs in ad-nominal positions modifying a DP outside of coordination and (b) epistemic adverbs modifying a DP within a coordination of DPs (Collins conjunction). Ad-nominal adverbs outside of coordinate structures have been claimed to have a strong reading giving rise to an existential entailment ("John visited maybe England" entails that John visited some place, and that place might have been England) while in Collins conjunctions, a weak reading with no existential implication has been claimed to be available ("John and perhaps Mary went to the store" means that either John went to the store, or John and Mary went to the store). We provide corpus data which show that weak and strong readings are available both inside and outside coordination, and we provide a unified analysis of both phenomena based in event semantics which allows modal adverbs to have sub-sentential scope and still target expressions of propositional type. Our analysis relies on the flexible approach to semantic composition afforded by glue semantics (Dalrymple 1999; Gotham 2018), where a functor can ‘ignore’ unsaturated positions in its arguments.

Inter- and intrasentential anaphora: the case of the Ancient Greek participle

This paper offers a formal model of the temporal behavior of Ancient Greek participles in their functions as elaborations, frames and independent rhemes. We model how they differ from each other and from main clauses, focusing in particular on the phenomenon of narrative progression. The theory integrates LFG and CDRT, using Glue semantics.

Inter- and intrasentential anaphora: the case of the Ancient Greek participle

This paper offers a formal model of the temporal behavior of Ancient Greek participles in their functions as elaborations, frames and independent rhemes. We model how they differ from each other and from main clauses, focusing in particular on the phenomenon of narrative progression. The theory integrates LFG and CDRT, using Glue semantics.