scholarly journals Semantic Analysis of Winograd Schema No. 1

2021 ◽  
Author(s):  
Brandon Bennett
Keyword(s):  
Artificial Intelligence ◽  
Natural Language ◽  
Semantic Analysis ◽  
Decisive Role ◽  
Natural Language Understanding ◽  
Language Understanding ◽  
Reference Resolution ◽  
Commonsense Knowledge ◽  
Key Factor ◽  
General Test

The Winograd Schema Challenge is a general test for Artificial Intelligence, based on problems of pronoun reference resolution. I investigate the semantics and interpretation of Winograd Schemas, concentrating on the original and most famous example. This study suggests that a rich ontology, detailed commonsense knowledge as well as special purpose inference mechanisms are all required to resolve just this one example. The analysis supports the view that a key factor in the interpretation and disambiguation of natural language is the preference for coherence. This preference guides the resolution of co-reference in relation to both explicitly mentioned entities and also implicit entities that are required to form an interpretation of what is being described. I suggest that assumed identity of implicit entities arises from the expectation of coherence and provides a key mechanism that underpins natural language understanding. I also argue that conceptual ontologies can play a decisive role not only in directly determining pronoun references but also in identifying implicit entities and implied relationships that bind together components of a sentence.

CoreALMlib: An library translated from the Component Library

2016 ◽  
Vol 16 (5-6) ◽  
pp. 800-816 ◽  
Author(s):  
DANIELA INCLEZAN
Keyword(s):  
Natural Language ◽  
Answer Set Programming ◽  
Natural Language Understanding ◽  
Inference Engine ◽  
Lexical Resources ◽  
Language Understanding ◽  
Commonsense Knowledge ◽  
Component Library ◽  
Action Language ◽  
Answer Set

AbstractThis paper presents CoreALMlib, an $\mathscr{ALM}$ library of commonsense knowledge about dynamic domains. The library was obtained by translating part of the Component Library (CLib) into the modular action language $\mathscr{ALM}$. CLib consists of general reusable and composable commonsense concepts, selected based on a thorough study of ontological and lexical resources. Our translation targets CLibstates (i.e., fluents) and actions. The resulting $\mathscr{ALM}$ library contains the descriptions of 123 action classes grouped into 43 reusable modules that are organized into a hierarchy. It is made available online and of interest to researchers in the action language, answer-set programming, and natural language understanding communities. We believe that our translation has two main advantages over its CLib counterpart: (i) it specifies axioms about actions in a more elaboration tolerant and readable way, and (ii) it can be seamlessly integrated with ASP reasoning algorithms (e.g., for planning and postdiction). In contrast, axioms are described in CLib using STRIPS-like operators, and CLib's inference engine cannot handle planning nor postdiction.

scholarly journals Extensible Chatbot Architecture Using Metamodels of Natural Language Understanding

Electronics ◽  
2021 ◽  
Vol 10 (18) ◽  
pp. 2300
Author(s):  
Rade Matic ◽  
Milos Kabiljo ◽  
Miodrag Zivkovic ◽  
Milan Cabarkapa
Keyword(s):  
Artificial Intelligence ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Communication Channels ◽  
Natural Language Understanding ◽  
Language Understanding ◽  
Customer Services ◽  
The Right

In recent years, gradual improvements in communication and connectivity technologies have enabled new technical possibilities for the adoption of chatbots across diverse sectors such as customer services, trade, and marketing. The chatbot is a platform that uses natural language processing, a subset of artificial intelligence, to find the right answer to all users’ questions and solve their problems. Advanced chatbot architecture that is extensible, scalable, and supports different services for natural language understanding (NLU) and communication channels for interactions of users has been proposed. The paper describes overall chatbot architecture and provides corresponding metamodels as well as rules for mapping between the proposed and two commonly used NLU metamodels. The proposed architecture could be easily extended with new NLU services and communication channels. Finally, two implementations of the proposed chatbot architecture are briefly demonstrated in the case study of “ADA” and “COVID-19 Info Serbia”.

scholarly journals An Introduction to Natural Language Processing: the Main Problems

Triangle ◽  
2018 ◽  
pp. 65
Author(s):  
Veronica Dahl
Keyword(s):  
Artificial Intelligence ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Natural Language Understanding ◽  
Human Language ◽  
Language Understanding ◽  
Written Text

Natural Language Processing aims to give computers the power to automatically process human language sentences, mostly in written text form but also spoken, for various purposes. This sub-discipline of AI (Artificial Intelligence) is also known as Natural Language Understanding.

scholarly journals A chatbotok jelensége, taxonómiája, felhasználási területei, erősségei és kihívásai

2018 ◽  
Vol 18 (2) ◽  
pp. 41
Author(s):  
Zoltán Szűts ◽  
Jinil Yoo
Keyword(s):  
Artificial Intelligence ◽  
Natural Language ◽  
Instant Messaging ◽  
Critical Mass ◽  
Natural Language Understanding ◽  
Turing Test ◽  
Generative Models ◽  
Language Understanding ◽  
Online Chat ◽  
In The Beginning

A chatbotok a 2010-es évek elején jelentek meg tömegesen az üzleti intelligencia specifikus formájaként. A gyakran mesterséges intelligenciával bíró interaktív technológia utat talált az online csevegőprogramok világába, és ma már több csatornán találkozhatnak vele a felhasználók. A chatbotok nem csupán a virtuális asszisztensek részei. De számos szervezet és kormányzat is használja őket weboldalak, applikációk, illetve azonnali üzenetküldő platformok környezetében annak érdekében, hogy termékeiket, ötleteiket, szolgáltatásaikat vagy éppen az általuk fontosnak ítélt témákat promotálják. Tanulmányukban a szerzők vállalkoznak a chatbotok taxonomiájának, a fa struktúrájú és generatív modellek, nyílt és zár rendszerek bemutatására, röviden érintve a mesterséges és érzelmi intelligencia kérdését is. Ugyancsak a tanulmány tárgyát képezi annak prezentálása, hogy a technológia fejlődésével – ami alatt alapvetően a mesterséges intelligencia, a gépi tanulás és a natural language understanding magasabb szintre lépését értik – a chatbotok használata is pontosabb, sőt intuitívabb lesz. Néhány sikeresen alkalmazható terület mellett a szerzők végül a technológia kihívásaira és hátrányaira is felhívják a figyelmet. --- Taxonomy, use cases, strengths and challenges of chatbots Chatbots appeared in critical mass in the beginning of the 2010’s as a specific form of business intelligence. Interactive technology, often combined with artificial intelligence, has since then found a way onto online chat services. Chatbots are now not only part of virtual assistants, but are also used by several organizations on websites, applications, and instant messaging platforms. Their purpose is to promote products, ideas, services and topics considered to be important. In their study, the authors undertake to demonstrate the taxonomy of chatbots, tree structured and generative models, open and closed systems, briefly touching on the issue of artificial and emotional intelligence as well. The study also aims to present how the use of chatbots will be more accurate and even more intuitive with the further development of technology. This technology could be artificial intelligence, machine learning or natural language understanding. In addition to some promising areas of use, the authors also draw attention to the challenges and disadvantages of technology. Keywords: chatbots, artificial intelligence, crowdsourcing, e-government, Turing-test

scholarly journals An Annotated Corpus of Reference Resolution for Interpreting Common Grounding

2020 ◽  
Vol 34 (05) ◽  
pp. 9081-9089
Author(s):  
Takuma Udagawa ◽  
Akiko Aizawa
Keyword(s):  
Natural Language ◽  
Natural Language Understanding ◽  
Fundamental Aspect ◽  
Dialogue Systems ◽  
Referring Expressions ◽  
Language Understanding ◽  
Reference Resolution ◽  
Quantitative Analyses ◽  
Partially Observable ◽  
Partial Understandings

Common grounding is the process of creating, repairing and updating mutual understandings, which is a fundamental aspect of natural language conversation. However, interpreting the process of common grounding is a challenging task, especially under continuous and partially-observable context where complex ambiguity, uncertainty, partial understandings and misunderstandings are introduced. Interpretation becomes even more challenging when we deal with dialogue systems which still have limited capability of natural language understanding and generation. To address this problem, we consider reference resolution as the central subtask of common grounding and propose a new resource to study its intermediate process. Based on a simple and general annotation schema, we collected a total of 40,172 referring expressions in 5,191 dialogues curated from an existing corpus, along with multiple judgements of referent interpretations. We show that our annotation is highly reliable, captures the complexity of common grounding through a natural degree of reasonable disagreements, and allows for more detailed and quantitative analyses of common grounding strategies. Finally, we demonstrate the advantages of our annotation for interpreting, analyzing and improving common grounding in baseline dialogue systems.

scholarly journals Using Answer Set Programming for Commonsense Reasoning in the Winograd Schema Challenge

2019 ◽  
Vol 19 (5-6) ◽  
pp. 1021-1037
Author(s):  
ARPIT SHARMA
Keyword(s):  
Natural Language ◽  
Answer Set Programming ◽  
Natural Language Understanding ◽  
Turing Test ◽  
Subgraph Isomorphism ◽  
Commonsense Reasoning ◽  
Language Understanding ◽  
Commonsense Knowledge ◽  
Additional Constraints ◽  
Answer Set

AbstractThe Winograd Schema Challenge (WSC) is a natural language understanding task proposed as an alternative to the Turing test in 2011. In this work we attempt to solve WSC problems by reasoning with additional knowledge. By using an approach built on top of graph-subgraph isomorphism encoded using Answer Set Programming (ASP) we were able to handle 240 out of 291 WSC problems. The ASP encoding allows us to add additional constraints in an elaboration tolerant manner. In the process we present a graph based representation of WSC problems as well as relevant commonsense knowledge.

Sign in / Sign up

Export Citation Format

Share Document