Hello Denny,

sounds very good for me!

I'll also put the references I collected on the Wiki when there will be a page for that.

Best regards,
Louis Lecailliez


De : Abstract-Wikipedia <abstract-wikipedia-bounces@lists.wikimedia.org> de la part de Denny Vrandečić <dvrandecic@wikimedia.org>
Envoyé : mercredi 15 juillet 2020 03:54
À : General public mailing list for the discussion of Abstract Wikipedia (aka Wikilambda) <abstract-wikipedia@lists.wikimedia.org>
Objet : Re: [Abstract-wikipedia] NLP issues severely overlooked (Amir E. Aharoni)
 
Hi Louis,

OK, here's a suggestion for the paper: I will finish the v2 - I hope this month or the next - and then make the sources available as a git repository, and then anyone who wants to work on it, can do so.

Does this sound good?

Cheers,
Denny


On Thu, Jul 9, 2020 at 5:22 AM Louis Lecailliez <louis.lecailliez@outlook.fr> wrote:
Hi Denny,

yes, the main problem of most of the systems presented in research papers (UNL or not) is that they are locked in the institutions that made them. A lot of UNL webpages went down since last time I checked (recently), and the system was in fact designed in a way it could work over the web while not letting third-parties access code and data. This is of course the exact reverse of the technical and philosophical approach taken here, and very sad as decade of accumulated knowledge is lost; the papers are far from sufficient to re-create even of fraction of the said systems

There is also, I guess, a lot of interesting work that is not translated in English at all (notably in linguistics), as making an academic career in the national language was an option in a lot of places until very recently.

> So, would you be willing to work on that?

Yes, of course, I wouldn't have posted in the mailing list otherwise. I like the dual, concurrent approach of linguistic/theory you are proposing. Note though that I'm not an expert be any mean in natural language generation, it just happens I stumbled upon UNL recently and it has too much in common on the abstract representation/NLG with this project not to mention it. I also had some researchers name in mind as I met some who worked on the referenced works.

Concerning the paper authorship, I understand your stance, and yes I'm willing to work more and write about previous works with those interested. Just to have an idea, what it is expected timeframe for a revision?

Lexicographic data in Wikidata totally flew under my radar. This is indeed something that will be needed in the future, and where I can directly contribute too! As mentioned by [1] the license seems to be an issue notably for importing existing resources, is there any “fix” planned for that?

All in all, I'm very pleased to see lot of aspects are more planned than it I assumed to be from reading the paper alone, and I’m more confident in the success now.

Best regards,
Louis Lecailliez



De : Abstract-Wikipedia <abstract-wikipedia-bounces@lists.wikimedia.org> de la part de Denny Vrandečić <dvrandecic@wikimedia.org>
Envoyé : mercredi 8 juillet 2020 22:37
À : General public mailing list for the discussion of Abstract Wikipedia (aka Wikilambda) <abstract-wikipedia@lists.wikimedia.org>
Objet : Re: [Abstract-wikipedia] NLP issues severely overlooked (Amir E. Aharoni)
 
Hi Louis, all,

Louis, thanks for raising that important issue!

I have been looking in a number of related NLG systems, and one thing I noticed is a pattern of many of these projects being developed very much in isolation from each other, and also often without much concern for ongoing linguistic research. That is what I tried to capture in the research paper by stating that there is no consensus on this, and that it seems too early to commit to a specific solution.

I had given a quick look to UNL, but the project looked pretty stale to me - I could not see any activity in the last decade. Furthermore, the page didn't provide access to the source code and instead mentioned that part of the technology is under patents, which is quite a red flag for me, and I usually don't look into something like that any further, in order to honestly be able to say that I didn't get any ideas from those patents. If I am mistaken, and there is a freely usable write-up or implementation, I'd be happy to come back and read up more.

Thank you for the annotated bibliography! That is super useful.

But I did look into detail into a (small) number of other, similar systems, such as Grammatical Framework or KPML. Tiago mentioned FrameNet, and I learned a lot about that too. To get an overview of the whole field has been a rather frustrating experience, especially since the major textbook in that area - Dale & Reiter - doesn't cover these systems, nor the 2018 update to that book by Gatt & Krahmer, and it seems that research work in that area often omits these practical systems. Accordingly, when I talk with the professors and researchers in this area, also about the proposal here, they are more focussed on specific issues, and don't know that much about the concrete systems (which is understandable - the flow from research to practical systems is a more established flow in many areas). Never mind that when you get to the linguistic side of it, instead of the computer science part, there are even more competing theories, many of which are aimed toward much more encompassing goals and are about covering the whole of language and natural language understanding, which we want to be shying away from.

The goal of the paper was never meant to be a comprehensive account of the state of the art in natural language generation. That's what Dale & Reiter and Gatt & Krahmer have aimed for, and their works are hundreds of pages. I had the feeling my paper was already too long, and putting in an overview of the state of the art would have made it at least double the length.

So, given that (and other reasons, as lined out in the paper), it seems that a system which could support any of these approaches seemed a more promising way. So far, for my own prototype, I have been mostly following Grammatical Framework (because it has a very accessible book, the software is free, the community was friendly, etc.), and it worked good enough to leave me convinced that the whole thing is worth trying out. But I don't know whether that's the best approach.

As mentioned by Chris Cooley, the goal will be to create a new wiki, a library of functions, that can support any of these approaches. My dream would be - and I see that Chris had already suggested that - that experts like you and your colleagues create an overview of the state of the art that will be accessible to the community and that will allow us to make a well-informed decision when the time comes as to which path to explore first. In a parallel track, we will be creating the function wiki, and then, when the time is ripe we can bring these two strands of work together. So, would you be willing to work on that?

How does this sound for a plan?



Some further points:

>> This is way easier to implement, test and deliver than to implement 10 different backends with various progress in implementation, incompatibilities and runtime characteristics.

Regarding your point about evaluation environments: I agree, it would be a huge task if the WMF core team were to develop all these different environments. But that's not the plan. The goal is really that *others* will hopefully build these :) All we need to do is to make sure that's possible and encouraged and simple enough. But yeah, not the core team.

>> The paper presents AW as sitting on top on WL. Both are big projects. Sitting a big project on top of another one is really risky, as it means a significant milestone must first be reached in the dependency (here WL), which would likely took some years, before even starting the work on the other project.

Yes, that's correct. That is exactly the time that allows us do the appropriate state of the art analysis. I hope it won't take us years, but that we will be faster.

>> AW can be realised with current tools and engineering practices.

Only if you commit to a specific implementation, which I am hesitant to do.

>> [English is an obstacle to programming] This strong affirmation needs to be sourced.


>> As I spend a significant time (~10 hours) gathering references and writing this email (which is 5 pages long in Word), I would like to be mentioned as co-author in the final paper if any idea or references presented here is used in it.

Thank you for your detailed comments, which will certainly improve the second version of the paper. I am happy to mention you in the acknowledgments. For co-authorship, I usually go for a more substantial engagement ;) If you're willing to write up the "Previous work" section along the lines you mentioned above (maybe with Tiago? Maybe with others to join?), but for a comprehensive overview of existing systems, then I am open to talk about co-authorship :)

>> For French, the gender of every noun entity *must* be present ... For Chinese and Japanese, classifier information must be present for all noun, in case one must be enumerated.

That's exactly the goal of the lexicographic project on Wikidata, as was pointed out:


You'll find plenty of Lexemes with their classifiers, forms, etc. The lexicographic project was started with the Abstract Wikipedia in mind, knowing that exactly that will be needed.

>> Yet, the use of any existing formalism is dismissed, which mean all the situations I illustrated in this email will need to be dealt with in an ad hoc fashion.

No, not at all it doesn't have to be ad-hoc, that's exactly what we can start working on now, long before we get to the point that we need to make that ad-hoc decision. I hope you'll join us to figure out the best way!


Thanks to Charles, Amir, Tiago, Christopher, Arthur, and Adam for your beautiful answers, who raised a number of great replies much better than I ever could. And thanks to Louis for starting this more than interesting thread! Let's continue in this vein!

Cheers,
Denny




On Sun, Jul 5, 2020 at 9:49 PM Adam Sobieski <adamsobieski@hotmail.com> wrote:

Brainstorming: resembling what the document object model (DOM) [1] is for XML and attributed trees, perhaps we could create and specify an object model for sets of attributed predicate calculus expressions.

 

With an attributed predicate calculus object model (e.g. “APCOM”) for sets of attributed predicate calculus expressions:

 

{

  r1.@a1(o1(icl>domain1).@a2, o2(icl>domain2).@a3).@a4

  r2.@a5(o3(icl>domain3).@a6, o4(icl>domain4).@a7).@a8

  r3.@a9(o5(icl>domain5).@a10, o6(icl>domain6).@a11, o7(icl>domain7).@a12).@a13

}.@a14

 

developers could more conveniently utilize sets of attributed predicate calculus expressions from JavaScript and Lua.

 

Drawing from XML, we can consider that objects, relations, attributes could be, instead of plain text strings, uniform resource identifiers (URI’s). “r1” could be a URI, “a1” could be a URI, “o1” could be a URI, and so forth.

 

We can also consider that the attributes in a model could have values:

 

{

  r1.[@a1=v1](o1(icl>domain1).[@a2=v2], o2(icl>domain2).[@a3=v3]).[@a4=v4]

  r2.[@a5=v5](o3(icl>domain3).[@a6=v6], o4(icl>domain4).[@a7=v7]).[@a8=v8]

  r3.[@a9=v9](o5(icl>domain5).[@a10=v10], o6(icl>domain6).[@a11=v11], o7(icl>domain7).[@a12=v12]).[@a13=v13]

}.[@a14=v14]

 

We can consider creating a scripting API (e.g. “APCOM”) for a semantic model to convenience developers. We can also consider adding attribute-value pairs to a semantic model.

 

 

Best regards,

Adam

 

[1] https://en.wikipedia.org/wiki/Document_Object_Model

 

From: Tiago Timponi Torrent
Sent: Sunday, July 5, 2020 9:06 PM
To: General public mailing list for the discussion of Abstract Wikipedia (aka Wikilambda)
Subject: Re: [Abstract-wikipedia] NLP issues severely overlooked (Amir E. Aharoni)

 

That’s a good idea, but I think you would need more than that. Take FrameNet, for example, but now departing from verbs instead of nouns. FrameNet has a very detailed model for dealing with verbs, their semantic arguments and the way they surface in morphosyntax. Nonetheless, to apply such a model in a text comprehension and/or generation task, you need more than that. You need to know prototypical fillers for the positions, which, in turn, are associated to other frames and, therefore, participate in other clusters of the network of frames. Moreover, you’d want those prototypical fillers to function as departing points for analogical extensions in the model, since not every sentence is a prototypical combination of words. In other words, the collection of attributes and relations you refer to should be defined in a way that they can be analogically extended to other collections not originally assigned to the item you’re looking at.

 

Cheers

 

Tiago 

 

Em dom, 5 de jul de 2020 às 20:03, Arthur Smith <arthurpsmith@gmail.com> escreveu:

Yes, thank you for the UNL background, that is extremely helpful. I've been reading some of the articles Louis provided as references, and it seems to me from just this perhaps naive point of view, that a lot of the complexity is associated with disambiguation of meaning - for nouns I think Wikidata items (and their relations to lexeme senses) solve that problem, but we are still missing I think a lot of the detail needed to do the same with adjectives and verbs (at least). So there is definitely some room for finding better ways to model - but maybe Wikidata could be expanded to handle the adjective/verb cases too. In general the concept of a single meaning associated with a Wikidata item as its identifier and a collection of attributes and relationships attached to that item is a powerful one that could resolve many such issues.

 

 

   Arthur

 

On Sun, Jul 5, 2020 at 6:55 PM Adam Sobieski <adamsobieski@hotmail.com> wrote:

Louis,

 

Thank you for the information about the Universal Networking Language [1] and the World Atlas of Language Structures [2].

 

Semantic Modeling

 

Do you opine that adding attributes to objects, relations and expressions enhances expressiveness for various features of natural language?

 

r.@a1.@a2(o1(icl>domain1).@a3.@a4, o2(icl>domain2).@a5.@a6).@a7.@a8

 

I wonder whether there exist mappings or workarounds with which to obtain such expressiveness for models such as Wikidata’s.

 

Scripting Environments for Natural Language Generation

 

Supposing that Wikilambda could be JavaScript / WebAssembly based, and observing that Lua / WebAssembly solutions exist, we can note that scripting engines such as V8 are easy to use and to add global objects and API to. Resembling how Web browsers provide scripting environments and API for functions, we can envision providing scripting environments and API for natural language generation functions.

 

I wonder what you might think about scripting environments and API for natural language generation scenarios?

 

 

Best regards,

Adam

 

[1] https://en.wikipedia.org/wiki/Universal_Networking_Language

[2] https://wals.info/

 

From: Louis Lecailliez
Sent: Saturday, July 4, 2020 2:10 PM
To: abstract-wikipedia@lists.wikimedia.org
Subject: Re: [Abstract-wikipedia] NLP issues severely overlooked (Amir E. Aharoni)

 

Hi Amir,

 

I understand the process is different that usual research. In fact I've seen Wikipedia grown from an unknown website to the biggest encyclopedia it is now. I use it daily in multiple languages and love it. I know what crowd sourcing could achieve.

 

> It's also possible that the mere *finding* of these stumbling blocks by such a big, diverse, open, and active community, will itself be a contribution to the scientific knowledge around this subject.

 

I disagree here. It would be contribution to scientic knowledge if and only if it wasn't discovered before. My email was precisely about that: capitalizing on the knowledge that has already been discovered, to avoid making the same mistake them again. It would not matter for a small project, but this one is really ambitious. We are speaking of 40 years of work by a horde of talented and very knowledgeable people, so this isn't to be dismissed easily.

 

This thing is, my previous email was a bit abstract, because it were a review of the paper, not of the project itself. I should have made more examples to illustrate where the problem lies.

 

Let's start with a simple example, in English, with corresponding Wikidata entities in-between parenthesis. I'm also using pseudo-turtle notation with made up relationships.

 

France (Q142) is a country (Q6256).

<Q142> <rel_is> <Q6256> .

 

Creating the English sentence is straightforward with the naive approach presented in the paper.

 

What is the French equivalent?

La France est un pays.

 

More information is required in the abstract representation: the text generator needs to know about the gender of both nouns (France and pays). So we need to extend the model as such:

 

<Q142> <rel_gender> <Q1775415> .

<Q6256> <rel_gender> <Q499327> .

 

Fine! Now what about Chinese?

法國是一個國家。

 

What we have in the middle of the sentence is a classifier (). The model needs the following update:

 

<Q499327> <rel_use_classifier> <Q63153> .

 

To handle these 3 languages, the model has already 3 additional triples just for accounting for linguistic facts occuring in these languages. Wikipedia exists in more than 300 languages, and the world has about 6000 of them, each of them having particularities that must be taken into account. Fortunately they recoup themselves in-between languages. Nonetheless the World Atlas Language Structures (https://wals.info/chapter/s1) count 144 distinct language features. Some are related to speech, but this means there is probably something like a hundred features that must be taken into account in the data model to produce valid natural language sentence.

Note that in the Chinese example, there is also a number (, one) showing up. This is a phenomenon that must be taken into account; and it's not always appearing when using  (to be). How complex the "lambda" system will be just to deal with this issue? Hint: very much. It also needs to be compatible with dozen of other phenomena.

 

Then each of those features require extensive and complete data. For French, the gender of every noun entity *must* be present, otherwise there is half a chance of producing a wrong sentence each time a noun entity is encountered. For Chinese and Japanese, classifier information must be present for all noun, in case one must be enumerated. Where does the project will get the data from? (we are speaking of millions of item, most not referenced in existing dictionaries) How will this be encoded? Those are real questions that must be answered.

 

Suppose now we have done the work for "renderers" in these three languages. They both use the more or less similar A X B structure where X is a verb meaning "to be".

 

What would be the Japanese equivalent?

The more natural structure would be like:

フランスは国()

 

What is a play here is a topicalization (Q63105) of France, followed by a predicate (it's a country). This is very different from the previous structure, which, not surprisingly enough, needs it's own representation. To make situation more difficult, the previous (A be B) structure can also exists in Japanese, but would lead to a totally different sentence if used.

 

The paper states that Figure 1 and 2 are examples that will be more complex in real life. Yet, the use of any existing formalism is dismissed, which mean all the situations I illustrated in this email will need to be dealt with in an ad hoc fashion. Moreover, changing formalism (be it ad hoc or not) will require to change every piece of code/data using it. This will happen everytime a language with unsupported feature(s) is added to the project. It's not hard to see how this will waste a huge amount of time and goodwill from involved people. The very code focussed tone of the paper, the english-centric approach used in the examples and the lack of references shows that the complexity of the task on the NLP front is not sufficiently conceptualized.

 

Best Regards,

Louis Lecailliez

 

De : Abstract-Wikipedia <abstract-wikipedia-bounces@lists.wikimedia.org> de la part de abstract-wikipedia-request@lists.wikimedia.org <abstract-wikipedia-request@lists.wikimedia.org>
Envoyé : samedi 4 juillet 2020 15:06
À :
abstract-wikipedia@lists.wikimedia.org <abstract-wikipedia@lists.wikimedia.org>
Objet : Abstract-Wikipedia Digest, Vol 1, Issue 6

 

Send Abstract-Wikipedia mailing list submissions to
        abstract-wikipedia@lists.wikimedia.org

To subscribe or unsubscribe via the World Wide Web, visit
        https://lists.wikimedia.org/mailman/listinfo/abstract-wikipedia
or, via email, send a message with subject or body 'help' to
        abstract-wikipedia-request@lists.wikimedia.org

You can reach the person managing the list at
        abstract-wikipedia-owner@lists.wikimedia.org

When replying, please edit your Subject line so it is more specific
than "Re: Contents of Abstract-Wikipedia digest..."


Today's Topics:

   1. Re: NLP issues severely overlooked (Charles Matthews)
   2. Use case: generation of short description (Jakob Voß)
   3. Re: NLP issues severely overlooked (Amir E. Aharoni)


----------------------------------------------------------------------

Message: 1
Date: Sat, 4 Jul 2020 14:05:09 +0100 (BST)
From: Charles Matthews <charles.r.matthews@ntlworld.com>
To: "General public mailing list for the discussion of Abstract
        Wikipedia (aka Wikilambda)" <abstract-wikipedia@lists.wikimedia.org>
Subject: Re: [Abstract-wikipedia] NLP issues severely overlooked
Message-ID: <2126327926.39940.1593867909152@mail2.virginmedia.com>
Content-Type: text/plain; charset="utf-8"

It is interesting to be on a list where one can hear about software issues, and then computational linguistic problems. I'm not an expert in either area.

I do have 17 years of varied Wikimedia experience (and I use my real name there).

> On 04 July 2020 at 12:25 Louis Lecailliez <louis.lecailliez@outlook.fr> wrote:
>

<snip>

>      Nothing precise is said about linguistic resources in the AW paper except for "These function finally can call the lexicographic knowlegde stored in Wikidata.", which is not very convincing: first because Wiktionary projects themselves severely lacks content and structure for those who has some content at all, secondly since specialized NLP ressources are missing there too (note: I'm not familiar with Wikidata so I could be wrong, however I never saw it cited for the kind of NLP resources I'm talking about).
>

I can comment about this. Besides Wiktionary, there is the "lexeme" namespace of Wikidata. It is a relatively new part of Wikidata, dealing with verbal forms.


>To finish on a positive note, I would like to highlight the points I really like in the paper. First, its collaborative and open nature, like all Wikimedia projects, gives him a much higher chance of success than its predecessors.

It is worth saying, for context, that there is a certain style or philosophy coming from the wiki side: more precisely, from the wikis before Wikipedia. There is the slogan "what is the simplest thing that would actually work?" You might argue, plausibly, that Wikipedia at nearly 20 years old, shows that there is a bit more to engineering than that.

On the other hand, looking at Wikidata at seven years old, there is some point to the comment. It has a rather simple approach to linked structured data, compared to the Semantic Web environment. (Really, just write a very large piece of JSON and try to cope with it!) But the number of binary relations used (8K, if you count the "external links" handling) is now quite large, and has grown organically. The data modelling is in a sense primitive, sometimes non-existent. But the range of content handled really is encyclopedic. And in an area like scientific bibliography, at a scale of tens of millions of entities, the advantages of not much ontological fussiness begin to be seen.

Wikidata started as an index of all Wikipedia articles, and is now five times the size needed for that: a very enriched "index".

I suppose the NLP required to code up, for example, 50K chemistry articles about molecules, might be a problem that could be solved, leaving aside the general problems for the moment.

In any case, there is a certain approach, neither academic nor commercial, that comes with Wikimedia and its communities, and it will be interesting to see how the issues are addressed.

Charles Matthews (in Cambridge UK)
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.wikimedia.org/pipermail/abstract-wikipedia/attachments/20200704/1113bab0/attachment-0001.html>

------------------------------

Message: 2
Date: Sat, 4 Jul 2020 08:18:56 +0200
From: Jakob Voß <jakob.voss@gbv.de>
To: <abstract-wikipedia@lists.wikimedia.org>
Subject: [Abstract-wikipedia] Use case: generation of short
        description
Message-ID: <4403bbda-040b-6c89-9cb6-6540139250dc@gbv.de>
Content-Type: text/plain; charset="utf-8"

Hi,

I want to auto-generate disambiguation description for African
politicians to be added to Wikidata, e.g. from the country Mozambique
(Q1029) the following descriptions should be generated:

Mozambican politician (en)
Mosambikanischer Politiker (de)
politico mozambicano (it)
...

This could be extended to other professions. My questions:

- Can anyone point me to data sources where to best look up country
adjectives such as "Mozambican"?

- Where/how to best store the lexical information for best reuse with
other renderers

- If a create small renderers for this short descriptions, what
architecture do you prefer for best reuse?

My just-get-it-done solution would be a set of CSV files and a few lines
of Perl code, but maybe this use case can be aligned with Abstract
Wikidata to better learn about it.

Looking forward to collaborate,
Jakob



------------------------------

Message: 3
Date: Sat, 4 Jul 2020 18:03:24 +0300
From: "Amir E. Aharoni" <amir.aharoni@mail.huji.ac.il>
To: "General public mailing list for the discussion of Abstract
        Wikipedia (aka Wikilambda)" <abstract-wikipedia@lists.wikimedia.org>
Subject: Re: [Abstract-wikipedia] NLP issues severely overlooked
Message-ID:
        <CACtNa8t6kbWe21C980h1MxiWNfUp+0eDE82vPMjDUX2UCgb2gw@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"

Hi,

Thanks a lot for the sources. I am not one of the people implementing
Wikilambda, but I am just very curious about it as a member of the wider
Wikimedia community. But there's a good chance that they will be useful to
people who do work on the implementation.

I will dare to add a little thought I have about it, however. It's possible
that the challenge of building a well-functioning natural language
generator is underestimated by the founders, and that they don't pay enough
attention to existing work (although, knowing Denny, there is a good chance
that he actually is aware of at least some of it). But there is something
that the wide Wikimedia community has that I'm not sure that the past
projects in this field did: The community itself. A big, worldwide, and
diverse group of passionate volunteers, who love the idea of spreading free
knowledge and who love their languages. Quite a lot of them also know some
programming, and in the past they proved unbelievably creative and
productive when writing code for Wikimedia projects as a community, in the
form of templates, modules, gadgets, bots, extensions, and other tools. I'm
quite sure that once the new tools become usable, this community will start
doing creative things again, and it will also start reporting bugs and
limitations.

So yes, while it's possible that along the way both the core developers and
the volunteer community will find all kinds of stumbling blocks, I'm pretty
sure that they will also have all kinds of surprising success stories. It's
also possible that the mere *finding* of these stumbling blocks by such a
big, diverse, open, and active community, will itself be a contribution to
the scientific knowledge around this subject. And don't underestimate the
"open" part—that's where we really shine. This won't be a theoretical work
in a lab, published in a paywalled and copyright-restricted academic
journal, but fully optimized for accessibility to everyone.

Yes, this whole email from me is incredibly naïve, but it's the same
attitude that got us to writing the biggest and most multilingual
encyclopedia in history, so maybe we can do something cool again :)

--
Amir Elisha Aharoni · אָמִיר אֱלִישָׁע אַהֲרוֹנִי
http://aharoni.wordpress.com
‪“We're living in pieces,
I want to live in peace.” – T. Moore


‫בתאריך שבת, 4 ביולי 2020 ב-14:26 מאת ‪Louis Lecailliez‏ <‪
louis.lecailliez@outlook.fr‏>:

> Hello,
>
> my name is Louis Lecailliez, PhD student at Kyoto University in education
> technology. I'm a Computer Science and NLP graduate. One thing I do is
> working on language learner's knowledge modelling as graphs.
>
> The Abstract Wikipedia project is really interesting. There is however two
> very concerning issues I spotted when reading the associated paper draft (
> https://arxiv.org/abs/2004.04733). The following email could be read as
> negative, but please don't take it as such: my purpose is to avoid spending
> people efforts and money for things that can (need to!) be fixed upfront.
>
> 1. Issues with NLP
>
> The main issue is that the difficulty of the NLP task of generating
> natural text from an abstract representation is severely overlooked. This
> stems from the other main problem: the paper is not based on the decades of
> previous work in that space.
>
> As I understand it, the main value proposition of Abstract Wikipedia (AW)
> is a computer representation of encyclopedic knowledge that can be
> projected into different existing natural languages, with the goal of
> supporting a huge number of them. Plus, an editor to make this happen
> easily.
>
> This is in fact surprisingly extremely close to what the Universal
> Networking Language (UNL) project, which started 20 years ago, aims to do.
> UNL provides a language agnostic representation of text that uses
> hypergraph. Software (called EnConverter) produce UNL graphs from natural
> text in a given language. Another kind of software called DeConverter do
> the reverse, that is producing natural text from the abstract
> representation. This is exactly the same function of the "renderers" in the
> AW paper. The way of doing it is also similar: by applying successive
> transformations until the final text string is produced. In general, that
> kind of abstract meaning representation is called an Interlingua, and is
> widely used in Machine Translation (MT) systems.
>
> Disregarding two decades of work, in the UNL  case, on the same problem
> space (rule-based machine translation, here from an abstract language as
> fixed source language), which was itself based on few other decades of
> work, doesn't seem to be a wise move to start a new project. For a start,
> the graph representation used in the AW will likely not be expressive
> enough to encode linguistic knowledge; this is why UNL uses hypergraphs
> instead of graphs.
>
> The problem is glaring when looking at the references list: the list is
> bloated with irrelevant references (such as those to programming languages
> [27, 37, 41, 77], Turing completeness being the worst offender [11, 17, 23,
> ...]) while containing only two references [7, 85] to the really hard part
> of the project: generating natural language from the abstract
> representation. There are few more relevant references about natural
> language generation, but this isn't enough.
>
> Interestingly, [85] is an UNL paper, but not the main one. Moreover, it is
> cited in Section 9 "Opening future research". This should be instead placed
> in a "Previous work" section which is missing from the paper.
>
> To fill a part of this section yet to be written, I propose the following
> references:
> [*1] Uchida, H., Zhu, M., & Della Senta, T. (1999). A gift for a
> millennium. IAS/UNU, Tokyo.
>
> https://www.researchgate.net/profile/Hiroshi_Uchida2/publication/239328725_A_Gift_for_a_Millennium/links/54c6953e0cf22d626a34f224/A-Gift-for-a-Millennium.pdf
> [*2] Wang-Ju Tsai (2004) La coédition langue-UNL pour partager la révision
> entre langues d'un document multilingue. [Language-UNL coedition to share
> revisions in a multilingual document] Thèse de doctorat. Grenoble.
>
> https://pdfs.semanticscholar.org/b030/ea4662e393657b9a134c006ca5b08e8a23b3.pdf?_ga=2.109286021.1099995837.1593757540-1424212949.1593757540
> [3*] Boitet, C., & Tsai, W. J. (2002). La coédition langue<—> UNL pour
> partager la révision entre les langues d'un document multilingue: un
> concept unificateur. Proc. TALN-02, Nancy, 22-26.
>
> http://www.afcp-parole.org/doc/Archives_JEP/2002_XXIVe_JEP_Nancy/talnrecital/TALN/actes_taln/articles/TALN26.pdf
> [4*] Tomokiyo, M., Mangeot, M., & Boitet, C. (2019). Development of a
> classifiers/quantifiers dictionary towards French-Japanese MT. arXiv
> preprint arXiv:1902.08061.
> https://arxiv.org/pdf/1902.08061.pdf
> [5*] Boguslavsky, I. (2005). Some controversial issues of UNL: Linguistic
> aspects. Research on Computer Science, 12, 77-100.
>
> http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.212.2058&rep=rep1&type=pdf
> [6*] Boitet, C. (2002). A rationale for using UNL as an interlingua and
> more in various domains. In Proc. LREC-02 First International Workshop on
> UNL, other Interlinguas, and their Applications, Las Palmas (pp. 26-31).
> https://www.cicling.org/2005/unl-book/Papers/003.pdf
> [7*] Dhanabalan, T., & Geetha, T. V. (2003, December). UNL deconverter for
> Tamil. In International Conference on the Convergences of Knowledge,
> Culture, Language and Information Technologies.
> http://www.cfilt.iitb.ac.in/convergence03/all%20data/paper%20032-372.pdf
> [8*] Singh, S., Dalal, M., Vachhani, V., Bhattacharyya, P., & Damani, O.
> P. (2007). Hindi generation from Interlingua (UNL). Machine Translation
> Summit XI.
>
> http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.78.979&rep=rep1&type=pdf
> [9*] Banarescu, L., Bonial, C., Cai, S., Georgescu, M., Griffitt, K.,
> Hermjakob, U., ... & Schneider, N. (2013, August). Abstract meaning
> representation for sembanking. In Proceedings of the 7th linguistic
> annotation workshop and interoperability with discourse (pp. 178-186).
> https://www.aclweb.org/anthology/W13-2322.pdf
> [10*] Berment, V., & Boitet, C. (2012). Heloise—An Ariane-G5 Compatible
> Rnvironment for Developing Expert MT Systems Online. In Proceedings of
> COLING 2012: Demonstration Papers (pp. 9-16).
> https://www.aclweb.org/anthology/C12-3002.pdf
> [11*] Berment, V. (2005). Online Translation Services for the Lao
> Language. In Proceedings of the First International Conference on Lao
> Studies. De Kalb, Illinois, USA (pp. 1-11).
>
> https://www.researchgate.net/profile/Vincent_Berment/publication/242140227_ONLINE_TRANSLATION_SERVICES_FOR_THE_LAO_LANGUAGE/links/0a85e53c5e0f021d19000000.pdf
>
> [*1] is the paper that describes UNL. [2*] is a doctoral thesis discussing
> a core problem AW is trying to address too. [3*] is a short paper done in
> the scope of [2*], even if you don't understand French you can have a look
> at the figures: two of them are about an editor similar in principe to what
> AW wants to incorporate.
> [5*] Insights about UNL expressivity issues, 10 years after the project's
> start. [6*] More UNL, with short history and context in which it is used.
>
> [4*] shows how deep natural language conversion goes: this paper addresses
> the issue of classifiers in French and Japanese. This is just one
> linguistic issue and there are dozens if not hundreds of such. An important
> point is that both of the languages involved need to be taken into account
> when modelling the abstract encoding, otherwise too much information is
> lost for producing a correct output.
>
> [7*] [8*] are very valuable examples of real world deconverter systems for
> UNL. As it's visible on [7*]'s Figure 1 and [8*]'s Figure 2, the process is
> *way* more complicated than a single "renderers" box. Moreover, there are
> very distinct identifiable steps, informed by linguistics. The AW does not
> describe any such structuration of natural text generation processing
> steps, everything is supposed to be happening in some unstructured "lambda"
> system. Also missing are the specialized resources (UNL-Hindi dictionary,
> Tamil Word dictionary, co-occurrence dictionary, etc.) required for the
> task.  Nothing precise is said about linguistic resources in the AW paper
> except for "These function finally can call the lexicographic knowlegde
> stored in Wikidata.", which is not very convincing: first because
> Wiktionary projects themselves severely lacks content and structure for
> those who has some content at all, secondly since specialized NLP
> ressources are missing there too (note: I'm not familiar with Wikidata so I
> could be wrong, however I never saw it cited for the kind of NLP resources
> I'm talking about).
>
> [10*] is a translation system built with "specialised languages for
> linguistic programming (SLLPs)" which is the service Wikilambda is supposed
> to provide for Abstract Wikipedia. [11*] gives the estimation of 2500 hours
> for the development (by a specialist) of three linguistic modules for Lao
> processing.
>
> So, in regard to the difficulty of the task, and previous work in the
> literature, the AW paper does not provide any convincing evidence that the
> technology on which it is supposed to be built can even reach the
> state-of-art. Dismissing every existing formal and software systems on the
> ground of "no consensus commiting to any specific linguistic theory" is not
> gonna work: this will result in ad hoc implementation-driven formalism that
> will have hard time fullfilling its goal.
> The NLP part (generating sentences from abstract representation) is the
> hardest of the project, yet it’s by far the least convincing one. "Abstract
> Wikipedia is indeed firmly within this tradition, and in preparation for
> this project we studied numerous predecessors." I would like to believe so,
> but the lack of corresponding reference as well as lack of previous work
> section tends to prove the contrary.
>
> While I can't advice for a switch to UNL, as I'm not specialist of it, it
> would be smart to capitalize on the work done on it by highly skilled (PhD
> level) individuals. As the UNL system is built on hypergraphs, it probably
> could be made interoperable easily with RDF knowledge graphs if named
> graphs are used. By having a UNL/RDF specification (yet to be written), the
> vision exposed in the AW paper may be reached sooner by reusing existing
> software (we are speaking of thousands man-year of work as per [11*]), and
> almost as importantly, an existing formalism that has been "debugged" for
> decades. There are probably other systems I'm unaware of that are worth
> investigating too, some like [9*] having more specialized usage. In any
> case, there is a strong need to back the paper and the project on the
> existing (huge) literature.
>
> 2. Other issues
>
> "In order to evaluate a function call, an evaluator can choose from a
> multitude of backends: it may evaluate the function
> call in the browser, in the cloud, on the servers of the Wikimedia
> Foundation, on a distributed peer-to-peer evaluation
> platform, or natively on the user’s machine in a dedicated hosting
> runtime, which could be a mobile app or a server on the
> user’s computer."
>
> This part is big technical creep. There is no reason to turn the project
> into a distributed heterogenous computing platform with a dedicated
> runtime, which could be a research project on its own, when the stated goal
> is to provide abstract multilingual encyclopedic content. All the
> computation can be done on servers (cloud is servers too) and cached. This
> is way easier to implement, test and deliver than to implement 10 different
> backends with various progress in implementation, incompatibilities and
> runtime characteristics.
>
> The paper presents AW as sitting on top on WL. Both are big projects.
> Sitting a big project on top of another one is really risky, as it means a
> significant milestone must first be reached in the dependency (here WL),
> which would likely took some years, before even starting the work on the
> other project. AW can be realised with current tools and engineering
> practices.
>
> "One obstacle in the democratization of programming has been that almost
> every programming language requires first to learn some basic English."
>
> This strong affirmation needs to be sourced. Programming languages, save
> for a few keywords, doesn't rely much on English. The vast insuccess of
> localized version of programming languages (such as French Basic) as well
> as the heavy use of existing programming language in countries that doesn't
> even use the Latin alphabet (China, Russia) tends to prove that English is
> not all a bottleneck for the democratization of programming. [53] is cited
> later in the paper but is a pop-linguistic article from an online
> newspaper, not an academic article.
>
> 3. Final words
>
> To finish on a positive note, I would like to highlight the points I
> really like in the paper. First, its collaborative and open nature, like
> all Wikimedia projects, gives him a much higher chance of success than its
> predecessors. If UNL is not too well-known, it’s not because it didn't
> yield research achievements, but because one selected institution per
> language is working on it and keep the resources and software within the
> lab walls. Secondly, there are some very welcome out-of-scope features:
> conversion from natural language, restriction to encyclopedic style text.
> This will allow for more focused effort towards the end goal, making it
> more achievable. And finally, the choice to go with symbolic/rule-based
> system with a touch of other ML where useful. This is, as said in the
> paper, a big win for explainability and using human contributions to build
> the system. This will also keep the computing cost to a more sane baseline
> than what the current deep learning models require.
>
> I think the project can succeed thanks to its openess, yet there is are
> real dangers visible in the paper: on the NLP side to reinvent a wheel that
> took 40 years to build, and on the technical side to lose time and effort
> on a project not required per se for AW to be build.
>
> As I spend a significant time (~10 hours) gathering references and writing
> this email (which is 5 pages long in Word), I would like to be mentioned as
> co-author in the final paper if any idea or references presented here is
> used in it.
>
> Best regards,
> Louis Lecailliez
>
> PS:
> 4. Typos
> * "These two projects will considerably expand the capabilities of the
> Wikimedia platform to enable every single human being to freely share share
> in the sum of all knowledge." => duplicate share
> * "The content is than turned into" => The content is then turned into
> * "[26] Charles J Fillmore, Russell Lee-Goldman, and Russell Rhodes. The
> framenet constructicon. Sign-based construction grammar, pages 309–372,
> 2012." => The framenet construction
> * "These function finally can call the lexicographic knowlegde stored in
> Wikidata." => These function finally can call the lexicographic knowledge
> stored in Wikidata
> * "[102] George Kinsley Zipf. Human Behavior and the Pirnciple of Least
> Effort. Addison-Wesley, 1949." => [102] George Kinsley Zipf. Human Behavior
> and the Principle of Least Effort. Addison-Wesley, 1949.
> * "Allowing the individual language Wikipedias to call Wikilambda has an
> addtional benefit." => Allowing the individual language Wikipedias to call
> Wikilambda has an additional benefit.
> _______________________________________________
> Abstract-Wikipedia mailing list
> Abstract-Wikipedia@lists.wikimedia.org
> https://lists.wikimedia.org/mailman/listinfo/abstract-wikipedia
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.wikimedia.org/pipermail/abstract-wikipedia/attachments/20200704/5cb85890/attachment.html>

------------------------------

Subject: Digest Footer

_______________________________________________
Abstract-Wikipedia mailing list
Abstract-Wikipedia@lists.wikimedia.org
https://lists.wikimedia.org/mailman/listinfo/abstract-wikipedia


------------------------------

End of Abstract-Wikipedia Digest, Vol 1, Issue 6
************************************************

 

_______________________________________________
Abstract-Wikipedia mailing list
Abstract-Wikipedia@lists.wikimedia.org
https://lists.wikimedia.org/mailman/listinfo/abstract-wikipedia

_______________________________________________
Abstract-Wikipedia mailing list
Abstract-Wikipedia@lists.wikimedia.org
https://lists.wikimedia.org/mailman/listinfo/abstract-wikipedia

--

Tiago Timponi Torrent

PPG-Linguística - FrameNet Brasil

Universidade Federal de Juiz de Fora

http://tiagotorrent.com

 

_______________________________________________
Abstract-Wikipedia mailing list
Abstract-Wikipedia@lists.wikimedia.org
https://lists.wikimedia.org/mailman/listinfo/abstract-wikipedia
_______________________________________________
Abstract-Wikipedia mailing list
Abstract-Wikipedia@lists.wikimedia.org
https://lists.wikimedia.org/mailman/listinfo/abstract-wikipedia