Learning Semantic Maps from Natural Language Descriptions

A framework for learning semantic maps from grounded natural language descriptions

The International Journal of Robotics Research ◽

10.1177/0278364914537359 ◽

2014 ◽

Vol 33 (9) ◽

pp. 1167-1190 ◽

Cited By ~ 18

Author(s):

Matthew R. Walter ◽

Sachithra Hemachandra ◽

Bianca Homberg ◽

Stefanie Tellex ◽

Seth Teller

Keyword(s):

Natural Language ◽

Semantic Maps

Download Full-text

Outdoors on the shores of the Baltic: gradience in the grammaticalization of the exterior-region

Eesti ja soome-ugri keeleteaduse ajakiri Journal of Estonian and Finno-Ugric Linguistics ◽

10.12697/jeful.2012.3.1.10 ◽

2012 ◽

Vol 3 (1) ◽

pp. 209-225

Author(s):

Andres Karjus

Keyword(s):

Natural Language ◽

Multidimensional Scaling ◽

Language Change ◽

Statistical Modelling ◽

Language Community ◽

Exterior Region ◽

Semantic Maps ◽

Closed Class ◽

Modelling Method ◽

The Baltic

The change of a lexical element into a grammatical (closed class) element must necessarily include intermediary stages where the element is considered gradually less lexical and more grammatical. The central assumptions in this study are the gradualness and gradience of grammaticalization, that natural language change cannot happen overnight, and that the change is driven by individual speakers of a language community (cf. Traugott and Trousdale 2010: 23, 26). Using a data sample from a questionnaire on spatial grams of the EXTERIOR-REGION (cf. Svorou 1994) in Estonian, Võro and Latvian, an attempt is made to model diachronic gradualness through synchronic gradience. The analysis and the explication thereof are carried out using multidimensional scaling, a statistical modelling method used akin to semantic maps.

Download Full-text

Deep learning in design workflows: The elusive design pixel

International Journal of Architectural Computing ◽

10.1177/1478077118800888 ◽

2018 ◽

Vol 16 (4) ◽

pp. 328-340 ◽

Cited By ~ 1

Author(s):

Ranjeeth Mahankali ◽

Brian R Johnson ◽

Alex T Anderson

Keyword(s):

Deep Learning ◽

Natural Language Processing ◽

Natural Language ◽

Language Processing ◽

General Question ◽

Data Format ◽

Semantic Maps ◽

Information Models ◽

Building Information ◽

Store Design

The recent wave of developments and research in the field of deep learning and artificial intelligence is causing the border between the intuitive and deterministic domains to be redrawn, especially in computer vision and natural language processing. As designers frequently invoke vision and language in the context of design, this article takes a step back to ask if deep learning’s capabilities might be applied to design workflows, especially in architecture. In addition to addressing this general question, the article discusses one of several prototypes, BIMToVec, developed to examine the use of deep learning in design. It employs techniques like those used in natural language processing to interpret building information models. The article also proposes a homogeneous data format, provisionally called a design pixel, which can store design information as spatial-semantic maps. This would make designers’ intuitive thoughts more accessible to deep learning algorithms while also allowing designers to communicate abstractly with design software.

Download Full-text