From ontology verbalisation to language learning exercises

I’m aware that to most people ‘playing with’ (investigating) ontologies and isiZulu does not sound particularly useful on the face of it. Yet, there’s the some long-term future music, like eventually being able to generate patient discharge notes in one’s own language, which will do its bit to ameliorate the language barrier in healthcare in South Africa so that patients at least will adhere to the treatment instructions a little better, and therewith receive better quality healthcare. But benefits in the short-term might serve something as well. To that end, I proposed an honours project last year, which has been completed in the meantime, and one of the two interesting outcomes has made it into a publication already [1]. As you may have guessed from the title, it’s about automation for language learning exercises. The results will be presented at the 6th Workshop on Controlled Natural Language, in Maynooth, Ireland in about 2 weeks time (27-28 August). In the remainder of this post, I highlight the main contributions described in the paper.

First, regarding the post’s title, one might wonder what ontology verbalisation has to do with language learning. Nothing, really, except that we could reuse the algorithms from the controlled natural language (CNL) for ontology verbalisation to generate (computer-assisted) language learning exercises whose answers can be computed and marked automatically. That is, the original design of the CNL for things like pluralising nouns, verb conjugation, and negation that is used for verbalising ontologies in isiZulu in theory [2] and in practice [3], was such that the sentence generator is a detachable module that could be plugged in elsewhere for another task that needs such operations.

Practically, the student who designed and developed the back-end, Nikhil Gilbert, preferred Java over Python, so he converted most parts into Java, and added a bit more, notably the ‘singulariser’, a sentence scrabble, and a sentence generator. Regarding the sentence generator, this is used as part of the exercises & answers generator. For instance, we know that humans and the roles they play (father, aunt, doctor, etc.) are mostly in isiZulu’s noun classes 1, 2, 1a, 2a, or 3a, that those classes do not (or rarely?) have non-human nouns and generally it holds for all humans and their roles that they can ‘eat’, ‘talk’ etc. This makes it relatively easy create a noun chain and a verb chain list to mix and match nouns with verbs accordingly (hurrah! for the semantics-based noun class system). Then, with the 231 nouns and 59 verbs in the newly constructed mini-corpus, the noun chain and the verb chain, 39501 unique question sentences could be generated, using the following overall architecture of the system:

Architecture of the CNL-driven CALL system. The arrows indicate which upper layer components make use of the lower layer components. (Source: [1])

From a CNL perspective as well as the language learning perspective, the actual templates for the exercises may be of interest. For instance, when a learner is learning about pluralising nouns and their associated verb, the system uses the following two templates for the questions and answers:

Q: <prefixSG+stem> <SGSC+VerbRoot+FV>
A: <prefixPL+stem> <PLSC+VerbRoot+FV>
Q: <prefixSG+stem> <SGSC+VerbRoot+FV> <prefixSG+stem>
A: <prefixPL+stem> <PLSC+VerbRoot+FV> <prefixPL+stem>

The answers can be generated automatically with the algorithms that generate the plural noun (from ‘prefixSG’ to ‘prefixPL’) and add the plural subject concord (from ‘SGSC’ to ‘PLSC’, in agreement with ‘prefixPL’), which were developed as part of the GeNI project on ontology verbalization. This can then be checked against what the learner has typed. For instance, a generated question could be umfowethu usula inkomishi and the correct answer generated (to check the learner’s response against) is abafowethu basula izinkomishi. Another example is generation of the negation from the positive, or, vv.; e.g.:

Q: <PLSC+VerbRoot+FV>
A: <PLNEGSC+VerbRoot+NEGFV>

For instance, the question may present batotoba and the correct answer is then abatotobi. In total, there are six different types of sentences, with two double, like the plural above, hence a total of 16 templates. It is not a lot, but it turned out it is one of the very few attempts to use a CNL in such way: there is one paper that also will be presented at CNL’18 in the same session [4], and an earlier one [5] uses a fancy grammar system (that we don’t have yet computationally for isiZulu). This is not to be misunderstood as that this is one of the first CNL/NLG-based system for computer-assisted language learning—e.g., there’s assistance in essay writing, grammar concept question generation, reading understanding question generation—but curiously very little on CNLs or NLG for the standard entry-level type of questions to learn the grammar. Perhaps the latter is considered ‘boring’ for English by now, given all the resources. However, thousands of students take introduction courses in isiZulu each year, and some automation can alleviate the pressure of routine activities from the lecturers. We have done some evaluations with learners—with encouraging results—and plan to do some more, so that it may eventually transition to actual use in the courses; that is: TBC…

 

References

[1] Gilbert, N., Keet, C.M. Automating question generation and marking of language learning exercises for isiZulu. 6th International Workshop on Controlled Natural language (CNL’18). IOS Press. Co. Kildare, Ireland, 27-28 August 2018. (in print)

[2] Keet, C.M., Khumalo, L. Toward a knowledge-to-text controlled natural language of isiZulu. Language Resources and Evaluation, 2017, 51(1): 131-157.

[3] Keet, C.M. Xakaza, M., Khumalo, L. Verbalising OWL ontologies in isiZulu with Python. The Semantic Web: ESWC 2017 Satellite Events, Blomqvist, E. et al. (eds.). Springer LNCS vol. 10577, 59-64.

[4] Lange, H., Ljunglof, P. Putting control into language learning. 6th International Workshop on Controlled Natural language (CNL’18). IOS Press. Co. Kildare, Ireland, 27-28 August 2018. (in print)

[5] Gardent, C., Perez-Beltrachini, L. Using FB-LTAG Derivation Trees to Generate Transformation-Based Grammar Exercises. Proc. of TAG+11, Sep 2012, Paris, France. pp117-125, 2012.

Advertisements

An Ontology Engineering textbook

My first textbook “An Introduction to Ontology Engineering” (pdf) is just released as an open textbook. I have revised, updated, and extended my earlier lecture notes on ontology engineering, amounting to about 1/3 more new content cf. its predecessor. Its main aim is to provide an introductory overview of ontology engineering and its secondary aim is to provide hands-on experience in ontology development that illustrate the theory.

The contents and narrative is aimed at advanced undergraduate and postgraduate level in computing (e.g., as a semester-long course), and the book is structured accordingly. After an introductory chapter, there are three blocks:

  • Logic foundations for ontologies: languages (FOL, DLs, OWL species) and automated reasoning (principles and the basics of tableau);
  • Developing good ontologies with methods and methodologies, the top-down approach with foundational ontologies, and the bottom-up approach to extract as much useful content as possible from legacy material;
  • Advanced topics that has a selection of sub-topics: Ontology-Based Data Access, interactions between ontologies and natural languages, and advanced modelling with additional language features (fuzzy and temporal).

Each chapter has several review questions and exercises to explore one or more aspects of the theory, as well as descriptions of two assignments that require using several sub-topics at once. More information is available on the textbook’s page [also here] (including the links to the ontologies used in the exercises), or you can click here for the pdf (7MB).

Feedback is welcome, of course. Also, if you happen to use it in whole or in part for your course, I’d be grateful if you would let me know. Finally, if this textbook will be used half (or even a quarter) as much as the 2009/2010 blogposts have been visited (around 10K unique visitors since posting them), that would mean there are a lot of people learning about ontology engineering and then I’ll have achieved more than I hoped for.

UPDATE: meanwhile, it has been added to several open (text)book repositories, such as OpenUCT and the Open Textbook Archive, and it has been featured on unglue.it in the week of 13-8 (out of its 14K free ebooks).

Ontology pub quiz questions of ISAO 2016 and JOWO 2017

In 2016 when I was a PC chair of the International School for Applied Ontology (ISAO 2016), the idea of organising a contest for the participants turned into a pub quiz somehow. The lecturers provided one or more questions on the topics they’d be teaching and I added a few as well. This set of ISAO16 ontology pub quiz questions is now finally online. It comes with the warning that it is biased toward the topics covered at ISAO 2016, and it turned out that there were a few questions not well formulated and/or not everyone agreed with the answer.

Notwithstanding, it was deemed sufficiently ok as idea in that the general chair of the Joint Ontology Workshops (JOWO 2017) wanted one for JOWO 2017 as well. Several questions were thrown out of the ISAO16 set for various reasons and more general Ontology questions made their way in, as well as a few ‘fun’ and trivia ones in the hope to add some more entertainment to the ontology pub quiz. The JOWO17 pub quiz question set with answers is now also online to play with, which, in my opinion, is a nicer set than the ISAO16 one. Here are a few questions to give you a taste of it:

  • Where/when can a pointless theory be relevant?
  • What is the goal of guerrilla ontology?
  • No Italian pizza has fruit as topping. Which of the following is (an)/are Italian pizza(s)? Pizza Hawaii, Pizza margherita, Pizza bianca romana (‘white roman pizza’)
  • When was the earliest published occurrence of the word “ontology”?

It turned out that it still was not entirely free of debate. If you disagree with one of the answers now, then let me paraphrase Stefano Borgo, who co-ran the JOWO17 pub quiz at the Irish pub in Bolzano on 23 September: maybe there’s something there to write up and submit a paper to FOIS 2018 :-). Or you can write it in the blog post comments section below, so that those questions will/should not be recycled and I can add longer answers to the questions.

Orchestrating 28 logical theories of mereo(topo)logy

Parts and wholes, again. This time it’s about the logic-aspects of theories of parthood (cf. aligning different hierarchies of (part-whole) relations and make them compatible with foundational ontologies). I intended to write this post before the Ninth Conference on Knowledge Capture (K-CAP 2017), where the paper describing the new material would be presented by my co-author, Oliver Kutz. Now, afterwards, I can add that “Orchestrating a Network of Mereo(topo) logical Theories” [1] even won the Best Paper Award. The novelties, in broad strokes, are that we figured out and structured some hitherto messy and confusing state of affairs, showed that one can do more than generally assumed especially with a new logics orchestration framework, and we proposed first steps toward conflict resolution to sort out expressivity and logic limitations trade-offs. Constructing a tweet-size “tl;dr” version of the contents is not easy, and as I have as much space here on my blog as I like, it ended up to be three paragraphs here: scene-setting, solution, and a few examples to illustrate some of it.

 

Problems

As ontologists know, parthood is used widely in ontologies across most subject domains, such as biomedicine, geographic information systems, architecture, and so on. Ontology (the philosophers) offer a parthood relation that has a bunch of computationally unpleasant properties that are structured in a plethora of mereologicial and meretopological theories such that it has become hard to see the forest for the trees. This is then complicated in practice because there are multiple logics of varying expressivity (support more or less language features), with the result that only certain fragments of the mereo(topo)logical theories can be represented. However, it’s mostly not clear what can be used when, during the ontology authoring stage one may want to have all those features so as to check correctness, and it’s not easy to predict what will happen when one aligns ontologies with different fragments of mereo(topo)logy.

 

Solution

We solved these problems by specifying a structured network of theories formulated in multiple logics that are glued together by the various linking constructs of the Distributed Ontology, Model, and Specification Language (DOL). The ‘structured network of theories’-part concerns all the maximal expressible fragments of the KGEMT mereotopological theory and five of its most well-recognised sub-theories (like GEM and MT) in the seven Description Logics-based OWL species, first-order logic, and higher order logic. The ‘glued together’-part refers to relating the resultant 28 theories within DOL (in Ontohub), which is a non-trivial (understatement, unfortunately) metalanguage that has the constructors for the glue, such as enabling one to declare to merge two theories/modules represented in different logics, extending a theory (ontology) with axioms that go beyond that language without messing up the original (expressivity-restricted) ontology, and more. Further, because the annoying thing of merging two ontologies/modules can be that the merged ontology may be in a different language than the two original ones, which is very hard to predict, we have a cute proof-of-concept tool so that it assists with steps toward resolution of language feature conflicts by pinpointing profile violations.

 

Examples

The paper describes nine mechanisms with DOL and the mereotopological theories. Here I’ll start with a simple one: we have Minimal Topology (MT) partially represented in OWL 2 EL/QL in “theory8” where the connection relation (C) is just reflexive (among other axioms; see table in the paper for details). Now what if we add connection’s symmetry, which results in “theory4”? First, we do this by not harming theory8, in DOL syntax (see also the ESSLI’16 tutorial):

logic OWL2.QL
ontology theory4 =
theory8
then
ObjectProperty: C Characteristics: Symmetric %(t7)

What is the logic of theory4? Still in OWL, and if so, which species? The Owl classifier shows the result:

 

Another case is that OWL does not let one define an object property; at best, one can add domain and range axioms and the occasional ‘characteristic’ (like aforementioned symmetry), for allowing arbitrary full definitions pushes it out of the decidable fragment. One can add them, though, in a system that can handle first order logic, such as the Heterogeneous toolset (Hets); for instance, where in OWL one can add only “overlap” as a primitive relation (vocabulary element without definition), we can take such a theory and declare that definition:

logic CASL.FOL
ontology theory20 =
theory6_plus_antisym_and_WS
then %wdef
. forall x,y:Thing . O(x,y) <=> exists z:Thing (P(z,x) /\ P(z,y)) %(t21)
. forall x,y:Thing . EQ(x,y) <=> P(x,y) /\ P(y,x) %(t22)

As last example, let me illustrate the notion of the conflict resolution. Consider theory19—ground mereology, partially—that is within OWL 2 EL expressivity and theory18—also ground mereology, partially—that is within OWL 2 DL expressivity. So, they can’t be the same; the difference is that theory18 has parthood reflexive and transitive and proper parthood asymmetric and irreflexive, whereas theory19 has both parthood and proper parthood transitive. What happens if one aligns the ontologies that contain these theories, say, O1 (with theory18) and O2 (with theory19)? The Owl classifier provides easy pinpointing and tells you the profile: OWL 2 full (or: first order logic, or: beyond OWL 2 DL—top row) and why (bottom section):

Now, what can one do? The conflict resolution cannot be fully automated, because it depends on what the modeller wants or needs, but there’s enough data generated already and there are known trade-offs so that it is possible to describe the consequences:

  • Choose the O1 axioms (with irreflexivity and asymmetry on proper part of), which will make the ontology interoperable with other ontologies in OWL 2 DL, FOL or HOL.
  • Choose O2’s axioms (with transitivity on part of and proper part of), which will facilitate linking to ontologies in OWL 2 RL, 2 EL, 2 DL, FOL, and HOL.
  • Choose to keep both sets will result in an OWL 2 Full ontology that is undecidable, and it is then compatible only with FOL and HOL ontologies.

As serious final note: there’s still fun to be had on the logic side of things with countermodels and sub-networks and such, and with refining the conflict resolution to assist ontology engineers better. (or: TBC)

As less serious final note: the working title of early drafts of the paper was “DOLifying mereo(topo)logy”, but at some point we chickened out and let go of that frivolity.

 

References

[1] Keet, C.M., Kutz, O. Orchestrating a Network of Mereo(topo)logical Theories. Ninth International Conference on Knowledge Capture (K-CAP’17), Austin, Texas, USA, December 4-6, 2017. ACM Proceedings.

Part-whole relations and foundational ontologies

Part-whole relations seem like a never-ending story—and it still doesn’t bore me. In this case, the ingredients were the taxonomy of part-whole relations [1] and a couple of foundational ontologies and the aim was to link the former to the latter. But what started off with the intention to write just a short workshop note, for seemingly clear and just in need of actually doing it, turned out to be not so straightforward after all. The selected foundational ontologies were not as compatible as assumed, and creating the corresponding orchestration of OWL files was a ‘non-trivial exercise’.

What were (some of) the issues? On the one hand, there are multiple part-whole relations, which are typically named differently when they have a specific domain or range. For instance, to relate a process to a sub-process (e.g., eating involves chewing), to relate a region to a region it contains, relating portions of stuff, and so on. Those relations are fairly well established in the literature. What they do demand for, however, is clarity as to what those categories really are. For instance, with the process example, is that to be understood as Process as meant in the DOLCE ontology, or, say, Process in BFO? What if a foundational ontology does not have a category needed for a commonly used part-whole relation?

The first step to answer such questions was to assess several foundational ontologies on 1) which of the part-whole relations they have now, and which categories are present that are needed for the domain and range declarations for those common part-whole relations. I assessed that for DOLCE, BFO, GFO, SUMO, GIST, and YAMATO. This foundational ontology comparison is summarised in tables 1 and 2 in the paper that emanated from the assessment [2], entitled “A note on the compatibility of part-whole relations with foundational ontologies” that I recently presented at FOUST-II: 2nd Workshop on Foundational Ontology, Joint Ontology Workshops 2017 in Bolzano, Italy. In short: none fits perfectly for various reasons, but there are more and less suitable ontologies for a possible alignment. DOLCE and SUMO were evaluated to have the best approximations. It appeared at the workshops presentation’s Q&A session, where two of the DOLCE developers were present, that the missing Collective was an oversight, or: the ontology is incomplete and it was not an explicit design choice to exclude it. This, then, would make DOLCE the best/easiest fit.

I’ll save you the trials and tribulations creating the orchestrated OWL files. The part-whole relations, their inverses, and their proper parthood versions were manually linked to modules of DOLCE and SUMO, and automatically linked to BFO and GFO. That was an addition of 49 relations (OWL object properties) and 121 logical axioms, which were then extended further with another 11 mereotopological relations and its 16 logical axioms. These files are accessible online directly here and also listed with brief descriptions.

While there is something usable now and, by design at least, these files are reusable as well, what it also highlighted is that there are still some outstanding questions, as there already were for the top-level categories of previously aligned foundational ontologies [3]. For instance, some categories seem the same, but they’re in ‘incompatible’ parts of the taxonomy (located in disjoint branches), so then either not the same after all, or this happened unintentionally. Only GIST has been updated recently, and it may be useful if the others foundational ontologies were to be as well, so as to obtain clarity on these issues. The full interaction of part-whole relations with classical mereology is not quite clear either: there are various extensions and deviations, such as specifically for portions [4,5], but one for processes may be interesting as well. Not that such prospective theories would be usable as-is in OWL ontology development, but there are more expressive languages that start having tooling support where it could be an interesting avenue for future work. I’ll write more about the latter in an upcoming post (covering the K-CAP 2017 paper that was recently accepted).

On a last note: the Joint Ontology Workshops (JOWO 2017) was a great event. Some 100 ontologists from all over the world attended. There were good presentations, lively conversations, and it was great to meet up again with researchers I had not seen for years, finally meet people I knew only via email, and make new connections. It will not be an easy task to surpass this event next year at FOIS 2018 in Cape Town.

 

References

 

[1] Keet, C.M., Artale, A. Representing and Reasoning over a Taxonomy of Part-Whole Relations. Applied Ontology, 2008, 3(1-2):91-110.

[2] Keet, C.M. A note on the compatibility of part-whole relations with foundational ontologies. FOUST-II: 2nd Workshop on Foundational Ontology, Joint Ontology Workshops 2017, 21-23 September 2017, Bolzano, Italy. CEUR-WS Vol. (in print)

[3] Khan, Z.C., Keet, C.M. Foundational ontology mediation in ROMULUS. Knowledge Discovery, Knowledge Engineering and Knowledge Management: IC3K 2013 Selected Papers. A. Fred et al. (Eds.). Springer CCIS vol. 454, pp. 132-152, 2015. preprint

[4] Donnelly, M., Bittner, T. Summation relations and portions of stuff. Philosophical Studies, 2009, 143, 167-185.

[5] Keet, C.M. Relating some stuff to other stuff. 20th International Conference on Knowledge Engineering and Knowledge Management (EKAW’16). Blomqvist, E., Ciancarini, P., Poggi, F., Vitali, F. (Eds.). Springer LNAI vol. 10024, 368-383. 19-23 November 2016, Bologna, Italy.

Figuring out the verbalisation of temporal constraints in ontologies and conceptual models

Temporal conceptual models, ontologies, and their logics are nothing new, but that sort of information and knowledge representation still doesn’t gain a lot of traction (cf. say, formal methods for verification). This is in no small part because modelling temporal information is not easy. Several conceptual modelling languages do have various temporal extensions, but most modellers don’t even use all of the default language features yet [1]. How could one at least reduce the barrier to adoption of temporal logics and modelling languages? The two principle approaches are visualisation with a diagrammatic language and rendering it in a (pseudo-)natural language. One of my postgraduate students looked at the former, trying to figure out what would be the best icons and such, which showed there was still a steep learning curve [2]. Before examining whether that could be optimised, I wondered whether the natural language option might be promising. The problem was, that no-one had yet tried to determine what the natural language counterpart of the temporal constraints were supposed to be, let alone whether they be ‘adequate’ or the ‘best’ way of rendering the temporal constraints in tolerable natural language sentences. I wanted to know that badly enough that I tried to find out.

Given that using templates is a tried-and-tested relatively successful approach for atemporal conceptual models and ontologies (e.g., for ORM, the ACE system), it makes sense to do something similar, but then for some temporal extension. As temporal conceptual modelling language I used one that has a Description Logics foundation (DLRUS [3,4]) for that easily links to ontologies as well, added a few known temporal constraints (like for relationships/DL roles, mandatory) and removing others (some didn’t seem all that interesting), which resulted in 34 constraints, still. For each one, I tried to devise more and less reasonable templates, resulting in 101 templates overall. Those templates were evaluated on semantics and preference by three temporal logic experts and five ‘mixed experts’ (experts in natural language generation, logic, or modelling). This resulted in a final set of preferred templates to verbalise the temporal constraints. The remainder of this post first describes a bit about the templates and then the results of which I think they are most interesting.

Templates

The basic idea of a template—in the context of the verbalisation of conceptual models and ontologies—is to have some natural language for the constraint where then the vocabulary gets slotted in at runtime. Take, for instance, simple named class subsumption in an ontology, C \sqsubseteq D, for which one could define a template “Each [C] is a(n) [D]”, so that with some axiom Manager \sqsubseteq Employee, it would generate the sentence “Each Manager is an Employee”. One also could have devised the template “All [C] are [D]” and then it would have generated “All Managers are Employees”. The choice between the two templates in this case is just taste, for in both cases, the semantics is the same. More complex axioms are not always that straightforward. For instance, for the axiom type C \sqsubseteq \exists R.D, would “Each [C] [R] some [D]” be good enough, or would perhaps “Each [C] must [R] at least one [D]” be better? E.g., “Each Professor teaches some Course” vs “Each Professor must teach at least one Course”.

The same can be done for the temporal constraints. To get there, I did a bit of a linguistic detour that informed the template design (described in the paper [5]). Let us take as first example for templates temporal class that has a semantics of o \in C^{\mathcal{I}(t)} \rightarrow \exists t' \neq t. o \notin C^{\mathcal{I}(t')}; for instance, UndergraduateStudent (assuming they graduate and end up as alumni or as drop outs, and weren’t undergrads from birth):

  1. If an object is an instance of entity type [C], then there is some time where it is not a(n) [C].
  2. [C] is an entity type whose objects are, for some time in their existence, not instances of [C].
  3. [C] is an entity type of which each object is not a(n) [C] for some time during its existence.
  4. All instances of entity type [C] are not a(n) [C] for some time.
  5. Each [C] is not a(n) [C] for some time.
  6. Each [C] is for some time not a(n) [C].

Which one(s) do you think captures the semantics, and which one(s) do you prefer?

A more elaborate constraint for relationships is ‘dynamic extension for relationships, past, mandatory], which is formalised as \langle o , o' \rangle \in \mbox{{\sc RDexM}-}_{R_1,R_2}^{\mathcal{I}(t)} \rightarrow (\langle o , o' \rangle \in{\tt R_1}^{\mathcal{I}(t)} \rightarrow \exists t'<t. \langle o , o' \rangle \in \mbox{{\sc RDex}}_{R_1,R_2}^{\mathcal{I}(t')} where \langle o , o' \rangle \in \mbox{{\sc RDex}}_{R_1,R_2}^{\mathcal{I}(t)} \rightarrow ( \langle o , o' \rangle \in{\tt R_1}^{\mathcal{I}(t)} \rightarrow    \exists t'>t. \langle o , o' \rangle \in {\tt R_2}^{\mathcal{I}(t')}).; e.g., every passenger who boards a flight must have checked in for that flight. Two options could be:

  1. Each ..C_1.. ..R_1.. ..C_2.. was preceded by ..C_1.. ..R_2.. ..C_2.. some time earlier.
  2. Each ..C_1.. ..R_1.. ..C_2.. must be preceded by ..C_1.. ..R_2.. ..C_2.. .

I’m not saying they are all correct; they were some of the options given, which the participants could choose from and comment on. The full list of constraints and template options are available in the supplementary material, which also contains a file where you can fill in your own answers, see what the (anonymised) participants said, and it has the final list of ‘best’ constraints.

Results

The main aggregate quantitative results are shown in the following table.

Many observations can be made from the data (see the paper for details). Some of the salient aspects are that there was low inter-annotator agreement among the experts, despite that they know each other (temporal logics is a small community) and that the ‘mixed group’ deemed many sentences correct that the experts deemed wrong in the sense of not properly capturing the semantics of the constraint. Put differently, it looks like the mixed experts, as a group, did not fully grasp some subtle distinction in the temporal constraints.

With respect to the templates, the preferred ones don’t follow the structure of the logic, but are, in a way, a separate rendering, or: there’s no neat 1:1 mapping between axiom type and template structure. That said, that doesn’t mean that they always chose the shortest template: the experts definitely did not, while the mixed experts leaned a bit toward preferring templates with fewer words even though they were surely not always the semantically correct option.

It may not look good that the experts preferred different templates, but in a follow-up interview with one of the experts, the expert noted that it was not really a problem “for there is the logic that does have the precise meaning anyway” and thus “resolves any confusion that may arise from using slightly different terminology”. The temporal logic expert does have a point from the expert’s view, fair enough, but that pretty much defeats my aim with the experiment. Asking more non-experts may not be a good strategy either, for they are, on average, too lenient.

So, for now, we do have a set of, relatively, ‘best’ templates to verbalise temporal constraints in temporal conceptual models and ontologies. The next step is to compare that with the diagrammatic representation. This we did [6], and I’ll describe those results informally in a next post.

I’ll present more details at the upcoming CREOL: Contextual Representation of Events and Objects in Language Workshop that is part of the Joint Ontology Workshops 2017, which will be held next week (21-23 September) in Bolzano, Italy. As the KRDB group at FUB in Bolzano has a few temporal logic experts, I’m looking forward to the discussions! Also, I’d be happy if you would be willing to fill in the spreadsheet with your preferences (before looking at the answers given by the participants!), and send them to me.

 

References

[1] Keet, C.M., Fillottrani, P.R. An analysis and characterisation of publicly available conceptual models. 34th International Conference on Conceptual Modeling (ER’15). Johannesson, P., Lee, M.L. Liddle, S.W., Opdahl, A.L., Pastor López, O. (Eds.). Springer LNCS vol 9381, 585-593. 19-22 Oct, Stockholm, Sweden.

[2] T. Shunmugam. Adoption of a visual model for temporal database representation. M. IT thesis, Department of Computer Science, University of Cape Town, South Africa, 2016.

[3] A. Artale, E. Franconi, F. Wolter, and M. Zakharyaschev. A temporal description logic for reasoning about conceptual schemas and queries. In S. Flesca, S. Greco, N. Leone, and G. Ianni, editors, Proceedings of the 8th Joint European Conference on Logics in Artificial Intelligence (JELIA-02), volume 2424 of LNAI, pages 98-110. Springer Verlag, 2002.

[4] A. Artale, C. Parent, and S. Spaccapietra. Evolving objects in temporal information systems. Annals of Mathematics and Artificial Intelligence, 50(1-2):5-38, 2007.

[5] Keet, C.M. Natural language template selection for temporal constraints. CREOL: Contextual Representation of Events and Objects in Language, Joint Ontology Workshops 2017, 21-23 September 2017, Bolzano, Italy. CEUR-WS Vol. (in print).

[6] Keet, C.M., Berman, S. Determining the preferred representation of temporal constraints in conceptual models. 36th International Conference on Conceptual Modeling (ER’17). Springer LNCS. 6-9 Nov 2017, Valencia, Spain. (in print)

Aligning different relations: the case of part-whole relations—LDK2017

Despite the best intentions, I did not get around to writing a post on the paper that I presented last week at the First International Conference on Language, Data and Knowledge 2017, 19-20 June, Galway, Ireland, and now Paul Groth also ‘beat’ me to it writing a nice conference report of it. On the bright side, it is an opportunity to say upfront I really enjoyed the conference and look forward to the next edition in 2019. The ESWC’17 organisers might be slightly disappointed that there was no special track on the multilingual semantic web after all, but I did get the distinct impression that the LDK17 authors might just all have gambled on LDK17—an opportunity to binge two days on all things natural language & Semantic Web—rather than on one track at an overpriced conference (despite the allure of it being A-rated).

So, what was my paper about that could have been submitted to either? I ended up struggling—and solving—an issue with aligning OWL object properties that were not simple 1:1 mappings, in a similar scope as our ESWC17 paper (introduced here) [4], but then with too many complications. Complications were due to the different conceptualisations of part-whole relations and that one of the requirements was to solve what to do with an object property (relation, relationship) that does not have a neat, single, label, and therewith neither fitting with the common OWL modelling paradigm nor with the recently agreed-upon ontolex-lemon model for linguistic annotations.

The start of all this sounded nice and doable: we need to generate natural language for healthcare, using, e.g., SNOMED CT, in local languages in South Africa, focussing on the largest one, being isiZulu. Medical terminologies are riddled with part-whole relations, so we sought to address that one (simple existentials already having been solved), availing of a standard list of part-whole relations (e.g. [1]). That turned out to be a non-trivial exercise, but doable eventually [2]. What wasn’t addressed in [2] was that some ‘common’ part-whole relations, such as membership and containment, weren’t like that in isiZulu, at all. Moreover, it wasn’t just a language issue, but ontological as well. The LDK17 paper “Representing and aligning similar relations: parts and wholes in isiZulu vs English” [3] describes this in some detail.

Here’s a (simplified) list of (assumed to be) common part-whole relations, which takes into account both transitivity differences and domain and range:

Now here’s the one based on the isiZulu language and some ontological analysis of that:

That is: there are both generalisations—some distinctions are not being made—and specialisations—some distinctions are made here but not elsewhere. For instance, ‘musician is part of some orchestra’ and ‘heart is part of some human’ (or vv.) is all done and described in the same way (ingxenye ‘part of’ and SC+CONJ for ‘has part’ [more about that below]). Yet, there is a difference between an individual (e.g., a voter) participating in some process and a collective (e.g., the electorate) participating in a process, or vv. The paper describes this more precisely, going into some detail regarding the differences in categories of domain and range and into the consequences on transitivity of mereological parthood.

The other ‘odd thing’—cf. current multilingual Semantic Web assumptions and technologies, that is—is that while the conceptualisation of ‘has part’ exists, it does not have a single label as in English (or in several other languages, such as heeft as deel), but it is dependent on the noun class of the noun of the class that play the part and play the whole in the relation. It combines the subject concord (~conjugation) of the noun class of the noun that plays the whole with a conjunction that is phonologically conditioned based on the first letter of the noun that plays the part; with verbalisation in the plural and three phonological cases, there are 18 possible strings all denoting ‘has part’. This still could be sorted with a language with inverses, provided the part-of direction has a name, like the ingxenye. This is not the case for containment, however. Instead of the relation (object property) having a name—be this a verb like ‘contained in’ or some noun phrase—it is the noun that plays the whole (the container, if you will) that gets modified. For instance, imvilophu ‘envelope’ and emvilophini denoting ‘contained in the envelope’, or, for individuals and locations, the city iTheku ‘Durban’ and eThekwini meaning ‘located in Durban’ (no typo—there’s some phonological conditioning I’m brushing over). While I have gotten used to such constructions, it generated some surprise among several attendees that one can have notions, concepts, views on or interpretations or descriptions of reality, that exist but do not have even one single string of text throughout to refer to regardless the context it is used.

The naming issue was solved by adding some arbitrary string as ‘name’ of the object property, and relating that to the function that verbalises that specific part-whole relation. The former issue, i.e., not all the same part-whole relations, required a bit more work, using ontology pattern alignments, by extending one correspondence pattern from the ODP catalogue and introducing a new one (see paper for the formal details), using the same broad framework of formalisation as proposed in [4].

All this was then implemented and aligned, and verified to not result in some unsatisfiable classes, object properties, or inconsistency (files). This also works in the isiZulu verbalisation tool we demo-ed at ESWC17 (described in the previous post) [5], all as part of the NRF-funded GeNI project.

Now, ideally, I already would have had the time to read the papers I flagged in my LDK17 conference notes with “check paper”. I haven’t yet due to end-of-semester tasks. So, on the basis of just a positive-seeming presentation, here are a few that are on the top of my list to check out first, for quite different reasons:

  • Interaction between natural language reading capabilities and math education, focusing on language production (i.e., ‘can you talk about it?’) [6], mainly because math education in South Africa faces a lot of problems. It also generated a lively discussion in the Q&A session.
  • The OnLiT ontology for linguistic [7] and LLODifying linguistic glosses [8] terminology (also: one of the two also won the best paper award).
  • Deep text generation, for it was looking at trying to address skewed or limited data to learn from [9], which is an issue we face when trying to do some NLP with most South African languages.

 

References

[1] Keet, C.M., Artale, A. Representing and Reasoning over a Taxonomy of Part-Whole Relations. Applied Ontology, 2008, 3(1-2):91-110.

[2] Keet, C.M., Khumalo, L. On the verbalization patterns of part-whole relations in isiZulu. 9th International Natural Language Generation conference (INLG’16), September 5-8, 2016, Edinburgh, UK. ACL.

[3] Keet, C.M. Representing and aligning similar relations: parts and wholes in isiZulu vs English. In: Gracia J., Bond F., McCrae J., Buitelaar P., Chiarcos C., Hellmann S. (eds) Language, Data, and Knowledge LDK 2017. Springer LNAI vol 10318, 58-73.

[4] Fillottrani, P.R., Keet, C.M. Patterns for Heterogeneous TBox Mappings to Bridge Different Modelling Decisions. 14th Extended Semantic Web Conference (ESWC’17). Springer LNCS. Portoroz, Slovenia, May 28 – June 2, 2017.

[5] Keet, C.M. Xakaza, M., Khumalo, L. Verbalising OWL ontologies in isiZulu with Python. 14th Extended Semantic Web Conference (ESWC’17). Springer LNCS. Portoroz, Slovenia, May 28 – June 2, 2017. (demo paper)

[6] Crossley, S., Kostyuk, V. Letting the genie out of the lamp: using natural language processing tools to predict math performance. In: Gracia J., Bond F., McCrae J., Buitelaar P., Chiarcos C., Hellmann S. (eds) Language, Data, and Knowledge LDK 2017. Springer LNAI vol 10318, 330-342.

[7] Klimek, B., McCrae, J.P., Lehmann, C., Chiarcos, C., Hellmann, S. OnLiT: and ontology for linguistic terminology. In: Gracia J., Bond F., McCrae J., Buitelaar P., Chiarcos C., Hellmann S. (eds) Language, Data, and Knowledge LDK 2017. Springer LNAI vol 10318, 42-57.

[8] Chiarcos, C., Ionov, M. Rind-Pawlowski, M., Fäth, C., Wichers Schreur, J., Nevskaya. I. LLODifying linguistic glosses. In: Gracia J., Bond F., McCrae J., Buitelaar P., Chiarcos C., Hellmann S. (eds) Language, Data, and Knowledge LDK 2017. Springer LNAI vol 10318, 89-103.

[9] Dethlefs N., Turner A. Deep Text Generation — Using Hierarchical Decomposition to Mitigate the Effect of Rare Data Points. In: Gracia J., Bond F., McCrae J., Buitelaar P., Chiarcos C., Hellmann S. (eds) Language, Data, and Knowledge LDK 2017. Springer LNAI vol 10318, 290-298.