Information-Processing Machines and the Access-Conscious Recognition of Common Ground Inconsistencies: A Proposal.

Abstract

In this paper, we propose a theoretical framework for the recognition of common ground inconsistencies explained through access conscious-like reasoning. Firstly, we present the theoretical background underlying the concept of access consciousness in information-processing systems. Then, we propose an example of \consciously" processing information in machines, such as the adoption of clari cation requests negotiating grounded knowledge in human-machine interaction.

Keywords

• Access-Consciousness Common Ground Clari cation Requests

Introduction

This work is aimed at proposing a theoretical-experimental reading key of information processing machines dealing with the accessibility to their internal mental-like information states and which are capable of expressing the presence of grounded knowledge inconsistencies through graph representations. Consciousness has been de ned di erently according to the scholars and disciplines dealing with it. At its simplest, it can be de ned as the state of awareness of an internal or external condition or experience. In the eld of arti cial intelligence, many debates focused on the possibility for computational systems to show consciousness. To address this topic in a speci c human-machine interaction application, we focus, in this work, not on the hard problem of consciousness, but on the weak one, represented by the concept of Access Consciousness (A-Consciousness).

A-Consciousness is described as the conscious access to a mental state in order to reason about it for rational control of action and speech [ 2 ]. In other words, it represents the availability or accessibility of the content of a mental state for verbal reports. It can be distinguished from Phenomenal Consciousness (P-Consciousness) which, conversely, is about the subject's perception of a

Copyright c 2020 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). conscious experience. Although Block's distinction is commonly accepted, it is important to mention that some other philosophers, such as Lycan [ 7 ], identi ed other possible ne-grained classi cations of consciousness, such as the distinction between organism consciousness, control consciousness (similar to Block's A-Consciousness), consciousness of, state/event consciousness, reportability, introspective consciousness, subjective consciousness, and self-consciousness.

The process involved in A-Consciousness takes place together with the information processing one. According to Block, a perceptual state is access-conscious if its content is processed via that information processing function, that is, if its content gets to the Executive System, whereby it can be used to control reasoning and behavior [ 2 ]. This Executive System is what can be modelled in order to make some process available and, therefore, a source of reasoning. This informationprocessing centre is what in our restricted case study will be called Con ict Search Graph, representing one of the possible modules of an Executive System.

In this paper, we account for an information-processing system which applies access-conscious-like processes in that it always has access to, or awareness of, its informational internal states and, moreover, produces information rather than just transmitting it, as it is capable of reasoning and acting upon its interpretation. In the next sections, we rstly describe what information-processors are, as they represent one way to explain access-consciousness in both biological and virtual systems. Afterwards, we present a speci c case study concerning the conscious processing of inconsistencies of grounded information in conversation and how these can result in speci c linguistic behaviours in human-human and, likewise, in human-machine interaction, such as the adoption of particular forms of polar questions. 2

Information-processing Systems

Any system capable of taking information in one form and processing it into another is referred to as an information-processor. Information can be de ned according to the processes that may be involved in the use of information itself. In [ 13 ], some of these processes are listed, as follows: external or internal actions triggered by information, segmenting, clustering labelling components within a structure (i.e. parsing), trying to derive new information from old (e.g. what caused this? what else is there? what might happen next? can I bene t from this?), storing information for future use (and possibly modifying it later), considering and comparing alternative plans, descriptions or explanations, interpreting information as instructions and obeying them, e.g. carrying out a plan, observing the above processes and deriving new information thereby (self-monitoring, self-evaluation, meta-management), communicating information to others (or to oneself later), checking information for consistency

Some of the aforementioned processes are here in bold, since they represent some crucial aspects of a speci c example of information-processing systems, which we are interested in. Speci cally, we can call them User Managed Tasks Applications. These applications require the user to have a leading role and the machine to have a following role. In such situations, the information given by the users is new to the receiving system. This means that such systems take information as input and store it for future use in a learning perspective, in order to carry out a plan in the future. Such information can also be modi ed later, for instance when inconsistencies between two pieces of information occur. In fact, speci c corrective actions, such as clari cation requests (see Section 2.1), can be triggered by inconsistencies in the common ground in order to overcome them, therefore producing new information as in a conscious-like process [ 8 ]. We de ne common ground, following [ 14 ], as the mutually recognised shared information in a situation. In [ 4 ], four di erent types of common ground are described local, personal, communal, specialized. Nevertheless, here we consider only the more general categories of personal and communal common ground [ 4 ]. Whereas Communal Common Ground (CCG) is de ned as the rule-based shared knowledge between individuals belonging to the same community, Personal Common Ground (PCG) refers to the fact-based knowledge built between two interlocutors, depending on the structural rules of the CCG.

Although a User Managed Task Application does not have knowledge of the desired nal state and of the steps to reach it, the system does have a) a general knowledge of which action is possible or not possible (i.e. CCG), b) and can store the given steps in the contextual knowledge (i.e. PCG), where both knowledge structures are modelled in a graph database. When inconsistencies arise because of unobserved pre-conditions and post-conditions of both Common Grounds, adequate linguistic actions can be adopted to solve the problem. This will be better described in the next section. 2.1

Common Ground Inconsistencies The term grounding refers to the acknowledgement of the level of understanding of the received information with respect to the complex system of shared or given knowledge [ 3 ]. This cognitive-pragmatic process takes place in interaction and makes use of di erent linguistic and non-linguistic strategies, such as backchannels and clari cation requests. Clari cation Requests (CRs) are a type of corrective feedback used when a problem in the processing of the previous utterance occurs [ 9 ]. In table 1, a classi cation of CRs based on corpus analysis of German and Italian map-tasks is presented [ 5 ].

Among the classes, the Information Processing one is listed. This class refers to the situation where the information received is not satisfactory for its entire understanding or the grounded information needs to be stabilised or checked via a con rmation or a control-targeted question. Concerning the PCG, the system might indeed need to complete some received information to be stored in the PCG based on the rules of the CCG by asking speci c clari cation questions,

Communication Level Problem Trigger Contact Lack of attention Perception Acoustics

Lexical Understanding Meaning, Ambiguity

Reference Reconstruction NP Reference, Deictic Reference, Action Reference Understanding Syntactic Understanding CAonoarlydtinicaatlioAnmAbmigbuiigtyu,itAy,ttEalclhipmtiecnatl AAmmbbiigguuiittyy, Logical Understanding Cause E ect

Information Processing Missing Information, Common Ground Intention IInntteennttiioonn ERveacolugantiitoionn IAngferereenincge/Disagreeing, Interest, Incredulity

Table 1. Clari cation Requests Classi cation which we call here Missing Information CRs. Commercial and academic systems are already treating this system necessity, for example through slot- lling strategies. On the other hand, when the information needs a double check before its storing in the PCG can actually occur (based on the rules of the CCG), or when the received information clashes with what we have already stored in the PCG, the system might need to use a Common Ground CR. This second class is of our interest, since it perfectly represents what an information-processing systems consciously does when checking for consistency, as mentioned in the previous sections. In the next section, more details concerning the processes and the strategies to adopt will be provided.

Questioning Grounded Knowledge: A Con ict Search Graph Studies already shown the importance of exploiting graphs to represent the dialogue information state [ 15 ]. The Executive System processing the information in a access-conscious way is, therefore, here represented by what we call the Con ict Search Graph. Our proposal is to have a graph in which the domain information (i.e. part of the CCG) is stored and whose con ict search module can be used to signalise which input does not respect the rules of the CCG and cannot, therefore, become part of the PCG. The graph is going to be built in Neo4J [ 16 ] starting from actions in the form of semantic frames, taken from FrameNet [ 1 ]. Semantic frames are de ned as conceptual structures evoked by action words in the mind of a speaker. Each frame can be linguistically expressed when the action words are syntactically combined with phrases bearing speci c semantic and syntactic roles, i.e. the frame elements. In order to represent the rules, which may be useful to link di erent actions in the graph in a possible instantiation of a course of actions in the dialogue, each frame element can be enriched with additional information, that is i) pre-conditions, such as the initial state of an item before the action is taking place, and ii) post-conditions, such as the nal state of an item after the action occurred (see [ 11, 12 ] for more information about pre- and post- conditions in the dialogue management for cognitive systems). When the same item is used within di erent frames with di erent semantic roles, if the states do not correspond to what expected according to the rules of the CCG, actions cannot be performed. In other words, for each argument of a predicate evoking a speci c instantiated semantic frame (k ), when pre-conditions or postconditions of the semantic role of that argument (condi) are compliant with its current state (statei-k), no con icts arise and the information can be accepted as part of the PCG. More formally,

D k condi ^ statei-k ñ K (1) If a con ict occurs, it must be corrected or the current action cannot be performed. The fact that pre- and post- conditions are explicitly reported in the graph is not only useful to nd the con ict, but also to explain why an action is not possible. This explanation can indirectly be expressed by means of a Common Ground CR.

The nature of the con ict expressed by this inconsistency is between a positive original bias of the system towards speci c post-conditions of a previous action and pre-conditions of the current action and the negative contextual evidence of the current input clashing with that presupposed knowledge. As shown in [ 5 ], Common Ground CRs are mostly uttered in the form of polar questions. Furthermore, in [ 6 ] is demonstrated that this speci c type of con ict between positive bias and negative evidence mostly occurs in the form of high negation polar questions. For this reason, we expect the system to recognise the type of con ict and generate the appropriate question to solve it. 3

Conclusions

This work is intended to be a theoretical overview of information-processing machines and a proposal of how to manage the production of linguistic behaviours derived from recognised common ground inconsistencies. As future work, we plan to examine the capability of the system to recognise such informational con icts within the graph representation and how to express this linguistically. In fact, principles like robustness will be investigated, in that such signals can be exploited to make the human interlocutor aware of the internal state of the system (observability) in order to recover the con ict through dialogue (recoverability).

References

1. Baker , C. F. , Fillmore , C. J. , and Lowe , J. B.: \ The berkeley framenet project." In: 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics , Volume 1 ( 1998 ).

2. Block , N. J.: \ On a Confusion About the Function of Consciousness." In: Behavioral and Brain Sciences 18 : 227 - 247 ( 1995 ). Reprinted in Block et al. ( 1997 ).

3. Clark , H. H. : Using language . Cambridge university press ( 1996 ).

4. Clark , E.V. : \Common ground" . In: The Handbook of Language Emergence . Wiley, Chichester, UK ( 2015 ): 328 { 353 .

5. Di Maro , M. , Buschmeier , H. , Kopp , S. , Cutugno , F.: \Clari cation Requests Negotiating Personal Common Ground" . In: Proceeding of XPRAG.it ( 2020 ) accepted .

6. Domaneschi , F. , Romero , M. , and Braun , B. : \Bias in polar questions: Evidence from English and German production experiments." In: Glossa: a journal of general linguistics 2 .1 ( 2017 ).

7. Lycan , W. G.: Consciousness and experience . Mit Press ( 1996 ).

8. Marchetti , G.: \Consciousness: a unique way of processing information." In: Cognitive processing 19 .3 ( 2018 ): 435 - 464 .

9. Purver , M. R. J.: The theory and use of clari cation requests in dialogue . Diss. University of London ( 2004 ).

10. Putnam , H.: \The nature of mental states" . In: Capitan and Merrill (eds.) Art, Mind and Religion, University of Pittsburgh Press ( 1967 ).

11. Romero , O. J. , Zhao , R. , and Cassell , J.: \ Cognitive-Inspired ConversationalStrategy Reasoner for Socially-Aware Agents . " In: IJCAI ( 2017 ).

12. Sklar , E. I. , and Azhar , M. Q. : \Argumentation-based dialogue games for shared control in human-robot systems." In: Journal of Human-Robot Interaction 4.3 ( 2015 ): 120 - 148 .

13. Sloman , A. , and Chrisley , R.: \ Virtual machines and consciousness." In: Journal of consciousness studies 10 .4- 5 ( 2003 ): 133 - 172 .

14. Stalnaker , R.: \ Common ground" . In: Linguistics and philosophy 25 .5/6 ( 2002 ): 701 - 721 .

15. Stoyanchev , S. , and Johnston , M.: \Knowledge-Graph Driven Information State Approach to Dialog." In: Workshops at the Thirty-Second AAAI Conference on Arti cial Intelligence ( 2018 ).

16. Webber , J.: \A programmatic introduction to neo4j." In: Proceedings of the 3rd annual conference on Systems, programming, and applications: software for humanity ( 2012 ).