Archaeology, Alexa and NLP

Hello everyone,

this post regards some test we are doing in these weeks about the application of NLP (Natural Language Processing) to archaeology. This research is conducted by our friend Andres Reyes (Arc-Team), an expert in this field.

Among the many possibilities of NLP in CH (Cultural Heritage), we decided to start with something particular and probably not so easy, but very useful for everyday work: a project manager for archaeology. The video below shows a preview of the system (how the system finds an old project).

 

To understand what I mean, I have to explain very fast why this tool would be a great help in our field. In Professional Archaeology (or, if you prefer Commercial Archaeology) projects can be divided in 4 main categories: excavations (probably the 70% of the work), surveys (and explorations in general), Cultural Heritage Enhancement (Valorization) and studies (mainly researches on specific archaeological and historical topics). From a logistical point of view, the most critical projects are the ones related with excavation and surveys, especially if performed in extreme conditions (Glacial Archaeology, High Mountain Archaeology, Underwater Archaeology, Speleoarchaeology, etc...), since in most cases the office (and all its comforts) is far away. Even if assisted by the strong computerization of the last 15 - 20 years, field operations can end up with errors, especially if many people work simultaneously to the same project from different area (for instance, a common mistake is giving the same code to different layers or artefacts).

A way to try to avoid errors is to use DBMSs (DataBase Management Systems) and GIS directly on the field, but this solution has some weakness, mainly related with the devices on which these software runs and with the necessity to find a comfortable location to insert the data (even if temporary). Thanks to the wider and wider coverage of internet and the new generation's smart-phones it is now simpler and faster to insert data into a main server trough a DBMS with a well designed interface (for GIS it is still better to work with a rugged laptop). Nevertheless these operations are still time consuming and keeps the archaeologist busy for a while, with all the difficulties coming from the use of a small touch-screen (gloves, dirty hands, rain, etc...). For this reason a Project Manager based on vocal commands could improve the work on the field, avoiding the main errors deriving by some of the most common stress factors (short time-table, weather conditions, several people working simultaneously, etc...).

Despite our decision to work with FLOSS, for this first experiment with NLP we decided to start with Amazon Alexa virtual assistant, for several reasons: the great effort of Amazon in developing the system, its strong diffusion among users and the good support in Italian (the language of our firts prototype). Nevertheless, as soon as we will have a first prototype, we plan to test and develop also open source solution, like Microft. BTW all our code will be released ASAP, with open source licenses, in this public repository on GitLab.

Currently our prototype is in a very early stage, but we already modified it a couple of time, with sensible changes in our strategy. For instance, in order to keep everything simple, at the beginning we based on shared google doc spreadsheets. This solution was more than enough to manage the list of codes related with US (Unità Stratigrafice, EN Stratigraphical Units), artefacts, samplings, documentations (in 3D and 2D), with also the possibility to keep controlled the budget and the working hours. soon we changed this strategy to have a more performing DBMS, based on the FLOSS PostgreSQL. Currently we are developing more options, like the possibility to ask to the Project Manager in which project we worked during a specific month.

I hope this post will be useful. If you want to collaborate to the project, please contact us. Have a nice day!

Digital Archaeology at Lund University

This year, as usual since 2011, +Alessandro Bezzi and me taught some lessons during the course "Archaeology and Ancient History: Digital Archaeology, GIS in Archaeology" at Lund University, held by +nicolò dell'unto. We used the opportunity to update the presentation with which we always start the first lecture. Here below you can see its last version, done with impress.js (just click on the first slide and us the spacebar to navigate).

For a better view, click here

The main topic is digital archeology (or "computational archeology", as it is also known in Italy). 

Initially we define five main operations that are common to any archaeological project: data acquisition, processing, management, analysis and sharing. The first three steps refer to the documentation work-flow, while the last three actions are related with the real research process (of course data management is in common with both of the phases).

Thereafter we analyze each step, starting with data acquisition, which is mainly based on hardware devices. During this operation are normally registered two elements, points and pictures, in order to virtually recover what the archaeological excavation is destroying. With points and pictures it is possible to document objects (artifacts and ecofacts) and actions (basically the archaeological samplings), and their elaboration or, in some cases combination, allows the researchers to record lines, polygon, 3d surfaces and real volumes, to register also the most complex elements of the archaeological record (layers, structures, etc...).

On the contrary of what happen with data acquisition, data processing is mainly based on software. Nowadays it can be divided into two orders of operations: standard procedures (raw coordinates elaboration, 2D photomapping, 2D vector archaeological drawing) and advanced techniques (3D restitution, volume calculation and 3D modeling). The very first and basic step to visualize recorded data is to elaborate the raw coordinates, registered with a total station or a RTK GPS, into a GIS readable code (e.g. CVS or WTK). Combining points and pictures is also possible to create georeferenced photomosaic, using a photomapping techniques (e.g. the metodo Aramus, the Khovle method or the newest Corte Inferiore method). Once obtained a complete georeferenced photomosaic it is possible to use a GIS to draw over the raster level, using one or more vector layers and to connect them with a database. Advanced techniques of documentation are more directly related with 3D and can be based on different methodology to extract morphological, topological and metric informations from one or more pictures (e.g. SvR, SfM, IBM, 3D photogrammetry, etc...). With these informations it is possible to calculate the real volumes of the elements of the archaeological records and use this data to reconstruct the depositional and post-depositional processes, using, when necessary, 3D modeling. Normally, during the different work-flows that can be involved in data processing, many kind of informations are elaborated with raster, vector and voxel graphic in 2 (x,y), 3 (x,y,z) or 4 (x,y,z,t) dimensions. The final aim is to set up a system which is able to handle such a variety of data and this system is the GIS.
In fact GIS software, combined with DBMS, are extremely useful during the data management phase, exactly for their capacity to handle different kind of informations (as many as are the disciplines or sciences which help archeology in its task). The use of such instruments helps to optimize the research, especially in comparison with the traditional techniques, not only during data management, but also during the more delicate stage of data analysis (when most of the cognitive processes are involved).
Among other things, in this fourth step, it is more evident the importance of using open source software and tools to maintain a continuous control on every single process of a study that can lead to the elaboration of new theories. Of course, not all the the analysis are equally sensitive under this aspect: for the simplest researches (anastylosis, building techniques, basic geomorphology, etc...) it is not strictly mandatory to know the source code of the applications, also because in these cases the main examinations are done directly by humans. On the other hand, for more complex studies (landscape archeology and Cost Surface Analysis, statistics, advanced geomorphology, etc...), it is very important to have a complete access to  the formulas and algorithms used by the software in order to keep an human control and do not completely delegate to the computer, among difficult quantitative calculations, also more delicate qualitative investigations (in which the human operator is still essential). In this way it is possible to correctly study all the different informations collected during the archaeological research, considering, at the same time, future integrations (GIS is an open system under a temporal point of view). The last goal of data analysis is to share results with the (scientific and non) community, which is the best way to improve the archaeological discipline itself, especially exploiting the potential of internet.
This lead us to the final step of an archaeological project (data sharing), which can follow different channels, like traditional publication, e-publication (e.g. webgis), exhibitions, etc... The most important thing, at least for scientific disclosure, is to grant a public access to all the informations used for the study (not only the filtered data, but also the raw data), in order to propose new hypothesis and (at the same time) give the all the necessary elements to verify them (no dogma, no authority principle).
To summarize the meaning of this contribution, considering archeology as a science (empiric approach) and a humanity (speculative approach), we can see how computational archeology helps to improve the scientific (empiric) approach, which is often underestimated, granting a more objective data acquisition and processing respects traditional techniques, especially during the critical phase of the archaeological excavation. In fact, unlike scientific experiments, the archaeological excavation is unrepeatable, being the most destructive approach of the discipline (and, at the same time, the most important).

PS

All the screenshots were done with ArcheOS. Some of them are related with really old projects, slowly we will replace them with more updated images...