Author pages are created from data sourced from our academic publisher partnerships and public sources.
Share This Author
Parsing Beyond Context-Free Grammars
- Laura Kallmeyer
- Computer ScienceCognitive Technologies
- 25 August 2010
This book provides an extensive overview of the formal language landscape between CFG and PTIME, moving from Tree Adjoining Grammars to Multiple Context-Free grammars and then to Range Concatenation Grammar while explaining available parsing techniques for these formalisms.
Factoring Predicate Argument and Scope Semantics: Underspecified Semantics with LTAG
It is shown that the derivation structure (and indirectly the locality of derivations) allows an appropriate amount of underspecification for quantifier scopeambiguities and related phenomena such as adjunct scope and islandconstraints.
PLCFRS Parsing of English Discontinuous Constituents
This paper uses probabilistic linear context-free rewriting systems for data-driven parsing, following recent work on parsing German, and demonstrates that by discarding information on non-local dependencies the PCFG model loses important information on syntactic dependencies in general.
Flexible Composition In Ltag: Quantifier Scope and Inverse Linking
In sum, even though (83a) in the text has an ∃∀ reading, the authors need example (84a) to ensure that true inverse scope is available in the grammar, because the wide scope effect of indefinites can be obtained through a special pseudo-scoping mechanism.
Syntax-driven semantic frame composition in Lexicalized Tree Adjoining Grammars
The grammar framework presented in this paper combines Lexicalized Tree Adjoining Grammar (LTAG) with a (de)compositional frame semantics and is applied to the analysis of directed motion expressions and of the dative alternation in English, two well-known examples of the interaction between lexical and constructional meaning.
Semantic construction in feature-based TAG
A semantic construction method for Feature-Based Tree Adjoining Grammar which is based on the derived tree is proposed and compared with related proposals.
Multilingual Code-switching Identification via LSTM Recurrent Neural Networks
- Younes Samih, Suraj Maharjan, Mohammed Attia, Laura Kallmeyer, T. Solorio
- Computer ScienceCodeSwitch@EMNLP
- 1 November 2016
The HHU-UHG system introduces a novel unified neural network architecture for language identification in code-switched tweets for both SpanishEnglish and MSA-Egyptian dialect.
CogALex-V Shared Task: GHHH - Detecting Semantic Relations via Word Embeddings
- Mohammed Attia, Suraj Maharjan, Younes Samih, Laura Kallmeyer, T. Solorio
- Computer ScienceCogALex@COLING
- 1 December 2016
This paper describes the system submission to the CogALex-2016 Shared Task on Corpus-Based Identification of Semantic Relations, and finds that linear regression performs better in the binary classification (Task-1), while CNNs have better performance in the multi-class semantic classification ( Task-2).
Scope and Situation Binding in LTAG Using Semantic Unification
This paper sets up a framework for Lexicalized Tree Adjoining Grammar (LTAG) semantics that brings together ideas from different recent approaches addressing some shortcomings of LTAG semantics based…
Data-Driven Parsing with Probabilistic Linear Context-Free Rewriting Systems
This paper presents the first efficient implementation of a weighted deductive CYK parser for Probabilistic Linear Context-Free Rewriting Systems (PLCFRSs), and shows that data-driven LCFRS parsing is feasible and yields output of competitive quality.