Text-to-Diagram Conversion: A Method for Formal Representation of Natural Language Geometry Problems

2013 ◽  
Author(s):  
Anirban Mukherjee ◽  
Sarbartha Sengupta ◽  
Dipanjan Chakraborty ◽  
Anirban Sen ◽  
Utpal Garain
Keyword(s):  
Natural Language ◽  
Formal Representation

scholarly journals Transformers as Soft Reasoners over Language

2020 ◽  
Author(s):  
Peter Clark ◽  
Oyvind Tafjord ◽  
Kyle Richardson
Keyword(s):  
Natural Language ◽  
Test Data ◽  
Question Answering ◽  
Major Obstacle ◽  
General Knowledge ◽  
Formal Representation ◽  
Counterfactual Reasoning ◽  
Probabilistic Representation ◽  
Modern Approach ◽  
Empirical Demonstration

Beginning with McCarthy's Advice Taker (1959), AI has pursued the goal of providing a system with explicit, general knowledge and having the system reason over that knowledge. However, expressing the knowledge in a formal (logical or probabilistic) representation has been a major obstacle to this research. This paper investigates a modern approach to this problem where the facts and rules are provided as natural language sentences, thus bypassing a formal representation. We train transformers to reason (or emulate reasoning) over these sentences using synthetically generated data. Our models, that we call RuleTakers, provide the first empirical demonstration that this kind of soft reasoning over language is learnable, can achieve high (99%) accuracy, and generalizes to test data requiring substantially deeper chaining than seen during training (95%+ scores). We also demonstrate that the models transfer well to two hand-authored rulebases, and to rulebases paraphrased into more natural language. These findings are significant as it suggests a new role for transformers, namely as limited "soft theorem provers" operating over explicit theories in language. This in turn suggests new possibilities for explainability, correctability, and counterfactual reasoning in question-answering.

RCM-extractor: an automated NLP-based approach for extracting a semi formal representation model from natural language requirements

2021 ◽  
Vol 29 (1) ◽  
Author(s):  
Aya Zaki-Ismail ◽  
Mohamed Osama ◽  
Mohamed Abdelrazek ◽  
John Grundy ◽  
Amani Ibrahim
Keyword(s):  
Natural Language ◽  
Formal Representation ◽  
Representation Model ◽  
Natural Language Requirements

scholarly journals Formal Representation of Temporal Expressions

10.29007/fdnj ◽  
2019 ◽  
Author(s):  
Svetlana P. Timoshenko
Keyword(s):  
Natural Language ◽  
Formal System ◽  
Formal Representation ◽  
Interval Algebra ◽  
Verb Forms ◽  
Temporal Expressions ◽  
The Right ◽  
The Way

In this paper we address the semantics of temporal expressions in natural language (such as vchera,’yesterday’, shestnadcatogo maja, ’on the 16th of May’, tri dnja ’three days’) and the way they interact with some other manifestations of temporality (such as functioning of prepositions and aspectual verb forms). A formal and constituent description of heterogeneous temporal expressions is proposed. We consider the interval algebra presented by James Allen to be the right basis for such a description. The new formal system is compared with the known TimeML project. The latter has weak spots - the meaning of some temporal expressions simply can not be represented in terms of TimeML. We discuss such cases and show how to analyze them in our formal system.

Interpreting Natural Language

1987 ◽  
Vol 32 (1) ◽  
pp. 33-34
Author(s):  
Greg N. Carlson
Keyword(s):  
Natural Language

A Change in Focus: How Readers Process Natural Language Quantifiers

2014 ◽  
Author(s):  
Sri Siddhi Upadhyay ◽  
Celia Klin
Keyword(s):  
Natural Language

Abstraction in Natural Language Categories

2012 ◽  
Author(s):  
Loes Stukken ◽  
Wouter Voorspoels ◽  
Gert Storms ◽  
Wolf Vanpaemel
Keyword(s):  
Natural Language

Conversational re-prompting in natural language dialog

2004 ◽  
Author(s):  
Harry E. Blanchard ◽  
Osamuyimen T. Stewart
Keyword(s):  
Natural Language
Sign in / Sign up

Export Citation Format

Share Document