League Table Of Visitors

David Rose On The Logical Analysis Of Nominal Groups As Unnecessary

David Rose replied to Beatriz Quiroz on SYSFLING on 29 Dec 2024, at 14:18:

I think you’re right that systems have to be the starting point, rather than structures.

Hence my suggestion to start from types of nom gp...naming, pronominal and non-pronominal. That was Christian’s systemic approach in his 1995 LGC, which he named individuation. He also proposed the nom gp function Facet, in place of Pre-Deictic and Pre-Numerative, realised by an embedded nom gp. That was renamed Focus in Martin, Matthiessen and Painter 2010. It replaces the need for a dual analysis of Head dissociated from Thing (which isn’t systemically motivated). That’s what I mean by simpler.

So no, ‘Head’ doesn't come into my reasoning. Simply different realisations of Thing... proper nouns specify an entity uniquely, pronouns specify by person, proximity, number, nouns need specifying... hence deixis, epithesis etc.

 

Martin, Doran and Zhang (2021) is far more than an introduction to the Word issues on nom gps. It explains all this and lots more.

Blogger Comments:

[1] To be clear, this is also the modus operandi of Systemic Functional Linguistics. Halliday & Matthiessen (2014: 49):

Being a ‘functional grammar’ means that priority is given to the view ‘from above’; that is, grammar is seen as a resource for making meaning – it is a semanticky kind of grammar. But the focus of attention is still on the grammar itself. Giving priority to the view ‘from above’ means that the organising principle adopted is that of system: the grammar is seen as a network of interrelated meaningful choices. In other words, the dominant axis is the paradigmatic one: the fundamental components of the grammar are sets of mutually defining contrastive features. Explaining something consists not in stating how it is structured but in showing how it is related to other things: its pattern of systemic relationships, or agnateness…

However, in Systemic Functional Grammar: A Next Step Into The Theory — Axial Relations (Martin 2013), Rose's mentor takes the opposite view and derives systems from structures. Evidence here.

[2] To be clear, pronominal and non-pronominal are not types of nominal group, but classes of the form that serve as the Thing of nominal groups.

[3] This is misleading, because it is the opposite of what is true. The Facet/Focus function is an element of experiential structure when the experiential Thing and logical Head do not coincide. Determining this fact requires the analysis of both logical and experiential structures, and Matthiessen (1995: 653-63) and Martin et al (2010: 169-70) provide both analyses.

[4] And vice versa 😎

[5] As previously noted, Martin, Doran & Zhang (2021: 271) create descriptive inconsistencies by misconstruing a structure marker as a structural unit, in an unranked form they invent called a 'subjacency duplex':

For the inconsistencies introduced by the notion of a subjacency duplex, and the misunderstandings on which it is based, see the very detailed review of Martin & Doran (2023):

Structure Markers: A Subjacency Duplex Analysis

David Rose On Halliday's Structure Of The Nominal Group As 'Superfluous'

David Rose replied to Bea Quiroz on SYSFLING on 29 Dec 2024, at 09:14:

I think Figure 6-9 is meant to exemplify ellipsis... ‘(look at) those two (things), (look at) those (things), which (thing)?’ 

Unfortunately this is obscured by re-labelling Deictic or Numerative as ‘Head’, as part of the argument for analysing nom gps as a hypotactic word complex, with a wandering Head. V confusing (and now superfluous*) .

 

Demonstratives as Thing are very common in English. Eg from the preceding para in IFG ‘But this is not so’, or my preceding para ‘Unfortunately this is obscured’.

 

You’re right, demonstratives are certainly not substitutes. The canonical substitute is ‘one’ which often serves as Thing... those ones, which one?  I used ‘possessive substitutes’ for personal pronouns ‘yours/mine’ etc, which always serve as Thing... those ones are mine, which one is yours? (Do these combine substitution with personal reference... my one, your one ??)

 

All this and more is why we need a description of English nom gps with Thing realised as pronoun, both personal and demonstrative. (Then you’d have something consistent to compare with Spanish.)

 

*simpler analysis first proposed by Matthiessen (1995), then Martin, Matthiessen, Painter (2010), now Martin, Doran, Zhang (2021)

Blogger Comments:

[1] To be clear, Figure 6-9 becomes less confusing, and what it is meant to exemplify becomes obvious, if the label beneath it is taken into account: 

[2] To be clear, as Figure 6-9 makes clear, in these instances, this serves as Deictic, not Thing. The misunderstanding of demonstrative pronouns as serving as Thing was introduced by Matthiessen when he misrepresented the 'Head' column in the following diagram from IFG1&2 (Halliday 1985: 295; 1994: 313):

as 'Head/Thing' in IFG3&4 (Halliday & Matthiessen 2004: 556; 2014: 629):

[3] To be clear, the possessive pronouns yours, mine etc. also serve as Deictic, not Thing. Halliday & Matthiessen 2014: 628):

[4] This is misleading, because it is the direct opposite of what is true, as demonstrated by [2] and [3] above.

[5] To be clear, on the one hand, for Matthiessen (1995: 690) also, the possessive pronouns yours, mine etc. serve as Deictic, not Thing:

and Martin, Matthiessen, Painter (2010) do not provide any analyses with pronouns as Head.

On the other hand, the 'simpler analysis' that Rose refers to involves the function termed 'Facet' in Matthiessen (1995: 655-7), and rebranded as 'Focus' in Martin et al (2010: 169-71). However, some of these analyses introduce descriptive inconsistencies. For problems with 'Facet' in Matthiessen (1995), see

• "Facet" Nominal Group
• A Thematic Test For Head/Thing Conflation
• The Symbolisation Subtype Of Facet

For problems with 'Focus' in Martin, Matthiessen & Painter (2010), see

• Problems With The 'Perspective' Subtype Of Focus
• A Serious Problem That Invalidates The 'Dimensional' Subtype Of Focus
• Serious Problems That Invalidate The 'Classifying' Subtype Of Focus
• A Problem With A Further Proposed 'Classifying' Type Of Focus
• The Problem With Exercise 5: Recognising Pre-Elements
• Problems With Exercise 4: Analysing Groups With Focus

[6] To be clear, Martin, Doran & Zhang (2021: 271) add to these inconsistencies by misconstruing a structure marker as a structural unit, in an unranked form they invent called a 'subjacency duplex':

For the inconsistencies introduced by the notion of a subjacency duplex, and the misunderstandings on which it is based, see the very detailed review of Martin & Doran (2023):

• Structure Markers: A Subjacency Duplex Analysis

David Rose Misrepresenting IFG On Nominal Groups

David Rose wrote to SYSFLING on 28 Dec 2024, 13:52:

The nom gp discussion in IFG starts off as a list of functions, from Deictic to Qualifier, including a rich description of items serving as Deictic. It’s not until the section on Thing, that we get an inkling that nom gps are orbitally structured, and that there are three types... ‘Thing is the semantic core of the nominal group. It may be realized by a common noun, proper noun or (personal) pronoun’.

What has been described to this point is the potential of nom gps with common noun as Thing. In contrast there is next to no discussion of the other types, although surely pronoun as Thing is the most frequent nom gp type in discourse?

If the chapter were organised systemically, it could start with a description of pronoun as Thing, that might be a more pedagogically friendly introduction (less dense), and would surely include demonstratives and possessive substitutes ‘yours/mine...’ as Thing. (Aren’t these types of pronouns?) As it is you have had to search the book to find scant mentions.

It could then describe noun as Thing, followed by the other functions that orbit it... perhaps a less anglocentric perspective?

and again at 17:01:

… It so happens that the systemic organisation of nom gps as naming, pronominal and non-pronominal appears to be general across lgs, as does their orbital structuring with Thing as core function.

In contrast, textual ordering from Deictic to Qualifier is a descriptive detail of English, which is strongly foregrounded by organising the nom gp description as a list of functions.

 

Blogger Comments:

[1] This is misleading. To be clear, the nominal group discussion in IFG starts off with the experiential structure of the nominal group, and because a structure is the relationships among the functions (Halliday & Matthiessen 2014: 451), it then goes on to discuss each of the functions that are related in this structure.

[2] This is very misleading indeed, and deliberately so, because it surreptitiously replaces Halliday's model of structure with Martin's misunderstanding. According to Halliday & Matthiessen (2014: 85), experiential structures are segmental (based on constituency). The orbital model is Martin's misunderstanding of experiential structure. It is a misunderstanding because the Nucleus°Satellite relation is univariate instead of multivariate, like the Head°Modifier relation in hypotactic logical structures.

[3] This is misleading. These are word classes that serve as Thing, not types of Thing. Because Thing is a function, types of Thing are types of that function, not classes of form.

[4] This is misleading. The potential of the nominal group is modelled as a system network. What has been described as 'to this point' are the functional elements that relate to the Thing in nominal group structure.

[5] This is misleading. On the one hand, proper nouns and pronouns serving as Thing are clarified on page 384. On the other hand, as it is pointed out there, proper nouns and pronouns 'usually occur without any other elements of the nominal group', and so offer limited scope for describing the structure of nominal groups.

[6] This misleading, because it repeats the misunderstanding of word classes as types of Thing; see [3] above.

[7] This is misleading. The description of English in IFG is 'anglocentric' because English is the language being described. Halliday (2002: 415):

Thus while the theory as a whole is logocentric, the description of each language is what we might call “glottocentric”: it privileges the language concerned. The description of English is anglocentric, that of Chinese sinocentric, that of French gallocentric and so on. (Note that the theory is not anglocentric; the description of English is.)

David Kellogg Misunderstanding Halliday On The Relation Between Language And Context

David Kellogg replied on sys-func on 31 Dec 2024, at 12:11:

But there are three problems that occur to me, and at least two of them stem from this very distinction [between the material-semiotic dialectic and the stratal relation between culture and language]. 

First of all, Halliday and Matthiessen note that the logico-semantic categories of elaboration, extension, and enhancement are fuzzy ones, with considerable overlap. This really must be so, not just because all language categories are fuzzy, but because we use "and", "but" and "so" to do all three: they are logico-semantic categories, viz. categories of thinking, and they won't obey the strong classification and framing that we use in lexicogrammar (and most particularly in transitivity). 

Secondly, as Chris has reiterated many times, there is a distinction between theoretical categories and descriptive ones. The categories of elaboration, extension, and enhancement are descriptive ones (and they are really designed around English, which is perhaps why they fit the simile of decorating a room, adding an annex, and enhancing the grounds that Halliday proposes in IFG so well. They are not theoretical categories, much less metaphysical ones, and when Halliday uses them to think about the grammatics, he stresses that this too is a simile.

Thirdly, and most importantly from my point of view, there are always far more things in heaven and earth than can be dreamt of even in the philosophy of language, much less the theory of experience that is encoded in the actual grammar. Birds, those "dinosaurs that learned to fly", don't really know about or obey the names we give them, and if we say that the relation between context and language is not causal, since ("because?") since cause is an enhancing relation, we are attributing to language a power over causality that it does not possess. Marx said that being determines consciousness, he meant that being got here first and consciousness was late to the party. 

Blogger Comments:

[1] To be clear, the indeterminacy here is with regard to which expansion relation is being realised by the forms and, but and so in a given instance, not with regard to the distinctions between the expansion relations themselves.

[2] This is the exact opposite of what is true. To be clear, in SFL Theory, 

• logico-semantic relations are categories of meaning, 
• thinking is a mental process that projects meaning. and 
• meaning is construed by wording, lexicogrammar.

[3] To be clear, Halliday's distinction between theoretical and descriptive categories applies to the distinction between theorising language and using the theory to describe languages. This is the opposite of using a description of English to think about a theory of language. Halliday (2002: 413-4):

But as a final step I will shift to another angle of vision and look at realisation and instantiation from inside the grammar – turning the tables by using the grammar as a way of thinking about the grammatics. …

The identifying relationship, as construed in the grammar of English, involves two particular functions, mutually defining such that one is the outward form, that by which the entity is recognised, while the other is the function the entity serves. This relationship of course takes a variety of more specific guises: form / function, occupant / role, sign / meaning, and so on. I labelled these grammatical functions “Token” and “Value”. This Token / Value relationship in the grammar is exactly one of realisation: the Token realises the Value, the Value is realised by the Token. It is thus analogous to the relationship defined in the grammatics as that holding between different strata. The grammar is modelling one of the prototypical processes of experience as constructing a semiotic relationship – precisely the one that is fundamental to the evolution of the grammar itself. …

Of course, the boot is really on the other foot: the grammatics is parasitic on the grammar, not the other way around. It is because of the existence of clause types such as those exemplified above that we are able to model the linguistic system in the way we do. The grammatics evolves (or rather one should say the grammatics “is evolved”, to suggest that it is a partially designed system) as a metaphoric transformation of the grammar itself. This is a further aspect of the special character of grammatics: while all theories are made of grammar (to the extent that they can be construed in natural language), one which is a grammar about a grammar has the distinctive metaphoric property of being a theory about itself.

[4] Here again, Kellogg confuses Halliday's notion of semiotic context, culture, with the material environment of language; see the previous post.

David Kellogg Misunderstanding Halliday On The Co-Evolution Of Language And Culture

David Kellogg reacted to a Halliday quote on sys-func on 30 Dec 2024, at 16:42:

Note that "driving" is a very narrow interpretation of causality, and "determine" is not much better. There is an obvious sense in which a virus "causes" Covid and a bacteria [sic] "causes" tuberculosis, but it is rather vacuous to say that viruses or bacteria "drive" or "determine" epidemics. 

Co-evolution involves reciprocation, but not necessarily symmetrical reciprocity. When Halliday says, for example, that every use of a word (even in private speech) will have some effect on the probabilities of a language system, he is not saying that lexical invention is on a par with grammatical regularity. The use of "he or she" instead of "he" does not prevent a single instance of rape much less shake the foundations of patriarchy; these are secured not only by language but also by organised violence (c.f. the work of Annabelle Lukin).

I think that when Halliday says that language will always have an "ideological" role, and that construals of reality will differ as we alter our condition, he is really saying that changes in productive relations do in the long run cause the way we speak, even if they do not in the short run "drive" or "determine".

Blogger Comments:

[1] The quote was Halliday (2003 [1992]: 380):

Language neither drives culture nor is driven by it; the old questions about which determines which can be set aside as irrelevant, because the relation is not one of cause and effect but rather (as Firth saw it, though not in these words) one of realisation: that is, culture and language coevolve in the same relationship as that in which, within language, meaning and expression co-evolve. Thus above and beyond the random, local variation between languages that was the subject matter of earlier typological studies, we may expect to find non-random variation realising different construals of reality across major alterations in the human condition. But given that language and culture evolve together in this kind of relationship, it is inevitable that language will take on an ideological role.

[2] To be clear, here Kellogg is disagreeing with Halliday on the basis of his misunderstanding of Halliday. Halliday is concerned with the relation between the two planes of a connotative semiotic system, where culture is semiotic content, and language is its semiotic expression. For Halliday, the relation between these two semiotic planes is realisation, which is an elaborating relation of identity (Halliday & Matthiessen 1999: 145). So the relation between culture and language is not causal, because 'cause' is an enhancing relation, not an elaborating one.

Kellogg, on the other hand, misconstrues the semiotic content that is realised in language as the material environment of language (organisms, diseases, rape, organised violence, productive practices). That is, the causal relation he proposes is between first-order material experience (phenomena) and second-order semiotic experience (metaphenomena), not between the culture as semiotic system and the language that realises it. In Halliday's terms, Kellogg is concerned with the ongoing material-semiotic dialectic, not the coevolution of culture and language. Halliday (2003: 238, 255):

The history of language, it seems to me, is part — an integral part — of human history; and this "history" is a dialectic interplay of material and semiotic processes, whose impacting engenders the complex ecosocial systems that we know as human cultures (cf. Lemke 1993 for a powerful account). …

Thus, grammar is bound up with all the other aspects of the human condition, as part of the eco-social system constituted by a human community and its environment. It takes its shape from the other strata of language with which it interfaces, from the relation of "languaging" both to other semiotic and to social and material processes, and from the nature of those processes themselves. It is the outcome of the ongoing dialectic between the material and the semiotic in human life.