Showing papers by "Nathan Schneider published in 2019"

Preparing SNACS for Subjects and Objects

Abstract: Research on adpositions and possessives in multiple languages has led to a small inventory of general-purpose meaning classes that disambiguate tokens. Importantly, that work has argued for a principled separation of the semantic role in a scene from the function coded by morphosyntax. Here, we ask whether this approach can be generalized beyond adpositions and possessives to cover all scene participants—including subjects and objects—directly, without reference to a frame lexicon. We present new guidelines for English and the results of an interannotator agreement study.

Semantically Constrained Multilayer Annotation: The Case of Coreference

Abstract: We propose a coreference annotation scheme as a layer on top of the Universal Conceptual Cognitive Annotation foundational layer, treating units in predicate-argument structure as a basis for entity and event mentions. We argue that this allows coreference annotators to sidestep some of the challenges faced in other schemes, which do not enforce consistency with predicate-argument structure and vary widely in what kinds of mentions they annotate and how. The proposed approach is examined with a pilot annotation study and compared with annotations from other schemes.

Tense and Aspect Semantics for Sentential AMR

Abstract: Many English tense and aspect semantic contrasts are not currently captured within Abstract Meaning Representation (AMR) annotations. The proposed framework augments the representation of finite predications in AMR to include a four-way temporal distinction (event time before, up to, at, or after speech time) and several aspectual distinctions (including static vs. dynamic, habitual vs. episodic, and telic vs. atelic). We validate this approach with a small annotation study of sentences from The Little Prince and report details of ongoing discussion to refine the framework. This will enable AMR to be used for NLP tasks and applications that require sophisticated reasoning about time and event structure. The Abstract Meaning Representation (AMR) is a readable and compact framework for broadcoverage semantic annotation of English sentences (Banarescu et al., 2013).1 AMR aims to abstract away from syntactic idiosyncrasies such that sentences with the same basic meaning are represented by the same AMR graph. This paper extends existing AMR to include a coarse-grained representation of tense and aspect. Figure 1 shows a sentence with its annotation from the existing AMR corpus with our proposed additions for tense (in blue) and aspect (in purple). Existing annotation in figure 1 specifies entities and propositional structure2 but notably omits the present time meaning of the copula and the future meaning of “going to.” It also does not specify whether these eventualities3 are stative (temporary http://amr.isi.edu/; data released at https://amr.isi.edu/download/ amr-bank-struct-v1.6.txt (Little Prince) and https://catalog.ldc.upenn.edu/LDC2017T10 This includes both the PropBank frameset last-01 and the AMR-specific frameset be-located-at-91. We understand eventualities to include all kinds of events: states, activities, achievements, accomplishments, and processes. (a / and :op1 (b / be-located-at-91 :stable :time (n2 / now)

Semantically Constrained Multilayer Annotation: The Case of Coreference

Abstract: We propose a coreference annotation scheme as a layer on top of the Universal Conceptual Cognitive Annotation foundational layer, treating units in predicate-argument structure as a basis for entity and event mentions. We argue that this allows coreference annotators to sidestep some of the challenges faced in other schemes, which do not enforce consistency with predicate-argument structure and vary widely in what kinds of mentions they annotate and how. The proposed approach is examined with a pilot annotation study and compared with annotations from other schemes.

Made for Each Other: Broad-Coverage Semantic Structures Meet Preposition Supersenses

Abstract: Universal Conceptual Cognitive Annotation (UCCA; Abend and Rappoport, 2013) is a typologically-informed, broad-coverage semantic annotation scheme that describes coarse-grained predicate-argument structure but currently lacks semantic roles. We argue that lexicon-free annotation of the semantic roles marked by prepositions, as formulated by Schneider et al. (2018), is complementary and suitable for integration within UCCA. We show empirically for English that the schemes, though annotated independently, are compatible and can be combined in a single semantic graph. A comparison of several approaches to parsing the integrated representation lays the groundwork for future research on this task.

An Improved Approach for Semantic Graph Composition with CCG

Abstract: This paper builds on previous work using Combinatory Categorial Grammar (CCG) to derive a transparent syntax-semantics interface for Abstract Meaning Representation (AMR) parsing. We define new semantics for the CCG combinators that is better suited to deriving AMR graphs. In particular, we define relation-wise alternatives for the application and composition combinators: these require that the two constituents being combined overlap in one AMR relation. We also provide a new semantics for type raising, which is necessary for certain constructions. Using these mechanisms, we suggest an analysis of eventive nouns, which present a challenge for deriving AMR graphs. Our theoretical analysis will facilitate future work on robust and transparent AMR parsing using CCG.

Made for Each Other: Broad-coverage Semantic Structures Meet Preposition Supersenses

Abstract: Universal Conceptual Cognitive Annotation (UCCA; Abend and Rappoport, 2013) is a typologically-informed, broad-coverage semantic annotation scheme that describes coarse-grained predicate-argument structure but currently lacks semantic roles. We argue that lexicon-free annotation of the semantic roles marked by prepositions, as formulated by Schneider et al. (2018b), is complementary and suitable for integration within UCCA. We show empirically for English that the schemes, though annotated independently, are compatible and can be combined in a single semantic graph. A comparison of several approaches to parsing the integrated representation lays the groundwork for future research on this task.

An Improved Approach for Semantic Graph Composition with CCG

Abstract: This paper builds on previous work using Combinatory Categorial Grammar (CCG) to derive a transparent syntax-semantics interface for Abstract Meaning Representation (AMR) parsing. We define new semantics for the CCG combinators that is better suited to deriving AMR graphs. In particular, we define relation-wise alternatives for the application and composition combinators: these require that the two constituents being combined overlap in one AMR relation. We also provide a new semantics for type raising, which is necessary for certain constructions. Using these mechanisms, we suggest an analysis of eventive nouns, which present a challenge for deriving AMR graphs. Our theoretical analysis will facilitate future work on robust and transparent AMR parsing using CCG.