The FCG Editor: An innovative environment for engineering computational construction grammars

Trijp, Remi van; Beuls, Katrien; Eecke, Paul Van

doi:10.1371/journal.pone.0269708

Cited by 11 publications

(9 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fluid CxG provides what is probably the most advanced computational implementation of CxG to date. Access to the formalism has been recently facilitated by the release of the FCG Editor (Van Trijp et al 2022), an open-source development tool in which researchers can customize their own grammars for sentence parsing and production. Proponents of Fluid CxG have also created models of language learning and evolution using autonomous robots that play language games (Steels & Hild 2012).…”

Section: Methodsmentioning

confidence: 99%

Constructionist approaches: Past, present, future

Ungerer¹,

Hartmann²

2023

Preprint

View full text Add to dashboard Cite

Construction Grammar (CxG) has developed into a broad and highly diverse family of approaches that have in common that they see constructions, i.e. form-meaning pairs at various levels of abstraction and complexity, as the basic units of language. This “element” gives an overview of the origin and the current state of the art of constructionist approaches, focusing, on the one hand, on basic concepts like the notion of “constructions”, while at the same time offering an in-depth discussion of current research trends and open questions. We discuss the commonalities and differences between the major constructionist approaches, the organization of constructional networks as well as ongoing research on linguistic creativity, multimodality and individual differences.

show abstract

Section: Methodsmentioning

confidence: 99%

Constructionist approaches: Past, present, future

Ungerer¹,

Hartmann²

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The output of the learning process should consist in form-meaning mappings (constructions) that can be used for comprehending and producing utterances. The form-meaning mappings are represented in, and processed using, Fluid Construction Grammar (Steels, 2011;Van Eecke and Beuls, 2017;van Trijp et al, 2022).…”

Section: Methodsmentioning

confidence: 99%

Modelling Language Acquisition through Syntactico-Semantic Pattern Finding

Doumen,

Beuls,

Van Eecke

2023

Findings of the Association for Computational Linguistics: EACL 2023

View full text Add to dashboard Cite

Usage-based theories of language acquisition have extensively documented the processes by which children acquire language through communicative interaction. Notably, Tomasello (2003) distinguishes two main cognitive capacities that underlie human language acquisition: intention reading and pattern finding. Intention reading is the process by which children try to continuously reconstruct the intended meaning of their interlocutors. Pattern finding refers to the process that allows them to distil linguistic schemata from multiple communicative interactions. Even though the fields of cognitive science and psycholinguistics have studied these processes in depth, no faithful computational operationalisations of these mechanisms through which children learn language exist to date. The research on which we report in this paper aims to fill part of this void by introducing a computational operationalisation of syntactico-semantic pattern finding. Concretely, we present a methodology for learning grammars based on similarities and differences in the form and meaning of linguistic observations alone. Our methodology is able to learn compositional lexical and item-based constructions of variable extent and degree of abstraction, along with a network of emergent syntactic categories. We evaluate our methodology on the CLEVR benchmark dataset and show that the methodology allows for fast, incremental and effective learning. The constructions and categorial network that result from the learning process are fully transparent and bidirectional, facilitating both language comprehension and production. Theoretically, our model provides computational evidence for the learnability of usage-based constructionist theories of language acquisition. Practically, the techniques that we present facilitate the learning of computationally tractable, usage-based construction grammars, which are applicable for natural language understanding and production tasks.

show abstract

“…In order to operationalise the process of mapping from the MNIST Dialog questions to their semantic representations, we adopt a computational construction grammar approach [33,34,4,5]. Concretely, we extend the computational construction grammar developed by [26] for the CLEVR VQA dataset [15] so that it is able to handle constructions involving co-referential expressions.…”

Section: Mnist Dialogmentioning

confidence: 99%

Neuro-Symbolic Procedural Semantics for Reasoning-Intensive Visual Dialogue Tasks

Verheyen,

Ekila,

Nevens

et al. 2023

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

This paper introduces a novel approach to visual dialogue that is based on neuro-symbolic procedural semantics. The approach builds further on earlier work on procedural semantics for visual question answering and expands it on the one hand with neuro-symbolic reasoning operations, and on the other hand with mechanisms that handle the challenges that are inherent to dialogue, in particular the incremental nature of the information that is conveyed. Concretely, we introduce (i) the use of a conversation memory as a data structure that explicitly and incrementally represents the information that is expressed during the subsequent turns of a dialogue, and (ii) the design of a neuro-symbolic procedural semantic representation that is grounded in both visual input and the conversation memory. We validate the methodology using the reasoning-intensive MNIST Dialog and CLEVR-Dialog benchmark challenges and achieve a question-level accuracy of 99.8% and 99.2% respectively. The methodology presented in this paper responds to the growing interest in the field of artificial intelligence in solving tasks that involve both low-level perception and high-level reasoning using a combination of neural and symbolic techniques.

show abstract

The FCG Editor: An innovative environment for engineering computational construction grammars

Cited by 11 publications

References 70 publications

Constructionist approaches: Past, present, future

Constructionist approaches: Past, present, future

Modelling Language Acquisition through Syntactico-Semantic Pattern Finding

Neuro-Symbolic Procedural Semantics for Reasoning-Intensive Visual Dialogue Tasks

Contact Info

Product

Resources

About