University Centre, School of Computing

The conversational software agent (CSA) framework investigates the integration, intersection and interface of the language, knowledge, and speech act constructions (SAC), with belief desires and intention (BDI) model and dialogue management (DM) for natural language processing (NLP). A long-standing issue within NLP CSA systems is refining the accuracy of the interpretation of meaning to provide a realistic dialogue to support the human-to-computer communication. The hypothesis is that Role and Reference Grammar (RRG) can underpin the linguistic model of a CSA. We investigate how the BDI mental model is characterised with RRG at the intersection of knowledge and language. We also investigate how knowledge representation (KR) and planning interface with the CSA. The CSA (LING-CSA) will be constrained to the food and cooking domain. A CSA conceptual framework is proposed with three phase models: (1) RRG language model (LM); (2) Agent Cognitive model (ACM) with two inner models of: (a) knowledge model; (b) planning model; (3) Agent dialogue model (ADM). RRG is a mature, functional linguistic theory that facilitates the extraction of the meaning from sentences from a computational viewpoint. The CSA must respond appropriately to the user's utterance via three phases – (a) interpretation (b) DM to manage the conversation, and (c) generation of a response in the target language, English. For KR it will employ conceptual graphs (CG), further serialised into RDF/XML mapped into RDF triples forming the CSA's belief base. The application of the BDI model of cognitive states to language is explicitly achieved via the act of uttering a sentence, in the form of SA performatives. The CSA will identify the properties of illocutionary acts, deduced from the speaker's and hearer's mental states, particularly their beliefs, intentions and the shared knowledge between communicating parties for the allocation of a plan, and the fulfilment of the intention as per the conversation. The contributions of this research study include: (i) extending the theoretical and computational adequacy of the RRG; (ii) integrating the RRG LM with SAC; (iii) motivating an agent framework with a LM based on RRG, an ACM with a KR, ADM, implemented as a proof-of-concept; (4) addressing the KR within the RRG LM at the language/knowledge interface. The innovation of this research study is the combination of these models and their interoperability. The research provides new insights into the interface between language and knowledge.

This paper proposes a linguistically orientated model of a conversational software agent (CSA) (Panesar, 2017) framework sensitive to natural language processing (NLP) concepts and the levels of adequacy of a functional linguistic theory. We discuss the relationship between natural language processing and knowledge representation (KR), and connect this with the goals of a linguistic theory (Van Valin and LaPolla, 1997), in particular Role and Reference Grammar (RRG) (Van Valin Jr, 2005a). We discuss the advantages of RRG and fitness-for-purpose for computational implementation and its level of computational adequacy (Nolan, 2004). We propose a design of a computational model of the linking algorithm that utilises a speech act construction as a grammatical object (Nolan, 2014a, Nolan, 2014b) and the sub-model of belief-desire and intentions (BDI) (Rao and Georgeff, 1995). This model has been successfully implemented in software (Panesar, 2017, Pokahr et al., 2014), using conceptual graphs, and resource description framework (RDF), and we highlight some implementation issues that arose at the interface between language and knowledge representation.

This paper presents a critical evaluation framework for a linguistically orientated conversational software agent (CSA) (Panesar, 2017). The CSA prototype investigates the integration, intersection and interface of the language, knowledge, and speech act constructions (SAC) based on a grammatical object (Nolan, 2014), and the sub-model of belief, desires and intention (BDI) (Rao and Georgeff, 1995) and dialogue management (DM) for natural language processing (NLP). A long-standing issue within NLP CSA systems is refining the accuracy of interpretation to provide realistic dialogue to support the human-to-computer communication.
This prototype constitutes three phase models: (1) a linguistic model based on a functional linguistic theory – Role and Reference Grammar (RRG) (Van Valin Jr, 2005); (2) Agent Cognitive Model with two inner models: (a) knowledge representation model employing conceptual graphs serialised to Resource Description Framework (RDF); (b) a planning model underpinned by BDI concepts (Wooldridge, 2013) and intentionality (Searle, 1983) and rational interaction (Cohen and Levesque, 1990); and (3) a dialogue model employing common ground (Stalnaker, 2002).
The evaluation approach for this Java-based prototype and its phase models is a multi-approach driven by grammatical testing (English language utterances), software engineering and agent practice. A set of evaluation criteria are grouped per phase model, and the testing framework aims to test the interface, intersection and integration of all phase models and their inner models. This multi-approach encompasses checking performance both at internal processing, stages per model and post-implementation assessments of the goals of RRG, and RRG based specifics tests.
The empirical evaluations demonstrate that the CSA is a proof-of-concept, demonstrating RRG’s fitness for purpose for describing, and explaining phenomena, language processing and knowledge, and computational adequacy. Contrastingly, the evaluations identify the complexity of lower level computational mappings of NL – agent to ontology with semantic gaps, and further addressed by a lexical bridging consideration (Panesar, 2017).

This paper presents a critical evaluation framework for a linguistically motivated conversational software agent (CSA). The CSA prototype investigates the integration, intersection and interface of the language, knowledge, and speech act constructions (SAC) based on a grammatical object, and the sub-model of belief, desires and intention (BDI) and dialogue management (DM) for natural language processing (NLP). A long-standing issue within NLP CSA systems is refining the accuracy of interpretation to provide realistic dialogue to support human-to-computer communication. This prototype constitutes three phase models: (1) a linguistic model based on a functional linguistic theory-Role and Reference Grammar (RRG), (2) an Agent Cognitive Model with two inner models: (a) a knowledge representation model, (b) a planning model underpinned by BDI concepts, intentionality and rational interaction, and (3) a dialogue model. The evaluation strategy for this Java-based prototype is multi-approach driven by grammatical testing (English language utterances), software engineering and agent practice. A set of evaluation criteria are grouped per phase model, and the testing framework aims to test the interface, intersection and integration of all phase models. The empirical evaluations demonstrate that the CSA is a proof-of-concept, demonstrating RRG's fitness for purpose for describing, and explaining phenomena, language processing and knowledge, and computational adequacy. Contrastingly, evaluations identify the complexity of lower level computational mappings of NL-agent to ontology with semantic gaps, and further addressed by a lexical bridging solution.

This paper aims to demystify the hype and attention on Chatbots and its association with conversational artificial intelligence. Both are slowly emerging as a real presence in our lives from the impressive technological developments in machine learning, deep learning and natural language understanding solutions. However, what is under the hood, and how far and to what extent can Chatbots/conversational artificial intelligence solutions work-is our question. Natural language is the most easily understood knowledge representation for people, but certainly not the best for computers because of its inherent ambiguous, complex and dynamic nature. We will critique the knowledge representation of heavy statistical Chatbot solutions against linguistics alternatives. In order to react intelligently to the user, natural language solutions must critically consider other factors such as context, memory, intelligent understanding, previous experience, and personalized knowledge of the user. We will delve into the spectrum of conversational interfaces and focus on a strong artificial intelligence concept. This is explored via a text based conversational software agents with a deep strategic role to hold a conversation and enable the mechanisms need to plan, and to decide what to do next, and manage the dialogue to achieve a goal. To demonstrate this, a deep linguistically aware and knowledge aware text based conversational agent (LING-CSA) presents a proof-of-concept of a non-statistical conversational AI solution (Panesar 2019a, b, 2017).

This chapter discusses a linguistically orientated model of a conversational software agent (CSA) (Panesar 2017) framework sensitive to natural language processing (NLP) concepts and levels of adequacy of a functional linguistic theory (LT). We discuss the relationship between NLP and knowledge representation (KR), and connect this with the goals of a LT (Van Valin and LaPolla 1997), in particular Role and Reference Grammar (RRG) (Van Valin Jr 2005). We debate the advantages of RRG and consider its fitness and computational adequacy. We present a design of a computational model of the linking algorithm that utilises a speech act construction as a grammatical object (Nolan 2014, Nolan 2014) and the sub-model of belief-desire and intentions (BDI) (Rao and Georgeff 1995). This model has been successfully implemented in software, using resource description framework (RDF), and we highlight some implementation issues that arose at the interface between language and knowledge representation (Panesar 2017).

This chapter encapsulates the multi-disciplinary nature that facilitates NLP in AI and reports on a linguistically orientated conversational software agent (CSA) (Panesar 2017) framework sensitive to natural language processing (NLP), language in the agent environment. We present a novel computational approach of using the functional linguistic theory of Role and Reference Grammar (RRG) as the linguistic engine. Viewing language as action, utterances change the state of the world, and hence speakers and hearer’s mental state change as a result of these utterances. The plan-based method of discourse management (DM) using the BDI model architecture is deployed, to support a greater complexity of conversation. This CSA investigates the integration, intersection and interface of the language, knowledge, speech act constructions (SAC) as a grammatical object, and the sub-model of BDI and DM for NLP. We present an investigation into the intersection and interface between our linguistic and knowledge (belief base) models for both dialogue management and planning. The architecture has three-phase models: (1) a linguistic model based on RRG; (2) Agent Cognitive Model (ACM) with (a) knowledge representation model employing conceptual graphs (CGs) serialised to Resource Description Framework (RDF); (b) a planning model underpinned by BDI concepts and intentionality and rational interaction; and (3) a dialogue model employing common ground. Use of RRG as a linguistic engine for the CSA was successful. We identify the complexity of the semantic gap of internal representations with details of a conceptual bridging solution.

This paper aims to demystify the hype and attention on chatbots and its association with conversational artificial intelligence. Both are slowly emerging as a real presence in our lives from the impressive technological developments in machine learning, deep learning and natural language understanding solutions. However, what is under the hood, and how far and to what extent can chatbots/conversational artificial intelligence solutions work – is our question. Natural language is the most easily understood knowledge representation for people, but certainly not the best for computers because of its inherent ambiguous, complex and dynamic nature. We will critique the knowledge representation of heavy statistical chatbot solutions against linguistics alternatives. In order to react intelligently to the user, natural language solutions must critically consider other factors such as context, memory, intelligent understanding, previous experience, and personalized knowledge of the user. We...

This paper presents a critical evaluation framework for a linguistically motivated conversational software agent (CSA). The CSA prototype investigates the integration, intersection and interface of the language, knowledge, and speech act constructions (SAC) based on a grammatical object, and the sub-model of belief, desires and intention (BDI) and dialogue management (DM) for natural language processing (NLP). A long-standing issue within NLP CSA systems is refining the accuracy of interpretation to provide realistic dialogue to support human-to-computer communication. This prototype constitutes three phase models: (1) a linguistic model based on a functional linguistic theory – Role and Reference Grammar (RRG), (2) an Agent Cognitive Model with two inner models: (a) a knowledge representation model, (b) a planning model underpinned by BDI concepts, intentionality and rational interaction, and (3) a dialogue model. The evaluation strategy for this Java-based prototype is multi-appro...

Natural Language Processing (NLP) technology has the potential to provide a non-invasive, cost-effective method using a timely intervention for detecting early-stage language and cognitive decline in individuals concerned about their memory. The proposed pre-screening language and cognition assessment model (PST-LCAM) is based on the functional linguistic model Role and Reference Grammar (RRG) to analyse and represent the structure and meaning of utterances, via a set of language production and cognition parameters. The model is trained on a Dementia TalkBank dataset with markers of cognitive decline aligned to the global deterioration scale (GDS). A hybrid approach of qualitative linguistic analysis and assessment is applied, which includes the mapping of participants´tasks of speech utterances and words to RRG phenomena. It uses a metric-based scoring with resulting quantitative scores and qualitative indicators as pre-screening results. This model is to be deployed in a user-centred conversational assessment platform.