Two of our team members, Raquel Liceras-Garrido and Katherine Bellamy have recently completed the project ‘Pathways to understanding 16^th century Mesoamerican geographies’, funded by the ������Ƶ Department of History.

This spin-off project has used , combining interactive texts, images and maps in a series of online interactive learning resources on the history, archaeology and geography of the Mesoamerican Postclassical and Colonial period of Central Mexico, beginning in the 14^th through to the mid-16^th century. These resources are divided into three main areas:

The first of the story maps explores the history of the Mexica people, beginning with their journey to the foundation of Tenochtitlan in 1325, which would become (alongside its neighbour city to the north, Tlatelolco) the heart of the Triple Alliance. Following this, the story map shows how the Mexica began to expand, featuring the lists of conquered settlements as recorded in the Codex Mendoza. This leads up to the arrival of the Spanish, and the ultimate meeting of Moctezuma II and Hernán Cortés in 1519. It then proceeds to describe how Cortés, with considerable assistance from his indigenous allies, conquered Tenochtitlan. This story map concludes with a look at the beginning of the colonial era, exploring how the Spanish began to impose their own institutions across ‘New Spain’, with varying success due to the continuing influence of indigenous institutions across Mesoamerica.

This story map explores the nature of historic place-names across what is currently Mexico, introducing the importance of place-names and language as a tool of colonisation and empire. The story map explores how this tool was used not only by the Spanish, but also by the Mexica and the Triple Alliance (not to mention other indigenous groups), as part of their systematic colonisation of conquered settlements and people. The story map goes on to explore how indigenous place-names continued to be used, despite the processes of colonisation at the hands of both the Triple Alliance and the Spanish. In addition, it explores the meaning of Nahua toponymy in particular – demonstrating the use of suffixes such as -tepec (which means ‘inhabited place’) and showing the distribution of some of these examples. Following this are some case studies of individual place-names, explaining their meaning and how they have been depicted in the historical record. The story map concludes by giving a brief overview of colonial naming, and how indigenous influences have continued.

The final story map discusses depictions of geographic space and place. This starts with an explanation of why this is an important discussion, with particular reference to, and problematisation of, the use of Geographic Information Systems for representing historical geographies. Following this, the story map introduces the idea of representations of space, which may be unfamiliar to the modern reader, and explores the various types of pre-Hispanic Nahuatl documents, including those which represented geographies. The story map gives an introduction to the state of Spanish cartography in the sixteenth-century, before going on to discuss how the Spanish and Nahua traditions of depicting geography began to merge during the conquest of Mexico. There is considerable evidence of this merging of traditions throughout the historical record, which the story map explains, giving two specific examples.

We’re very pleased to have been awarded a Resource Development Grant to explore the annotation of a series of historic maps using . Our corpus of maps includes those produced in the sixteenth-century for the Relaciones �ұ�Dz���á�ھ������� de Nueva España��across the area which is currently Mexico.

On Monday 17th June, in collaboration with our colleagues in the at , the (ENAH), (UNAM), the (INAH), and the , we will be delivering an online workshop which will deliver training on for the annotation of the sixteenth-century maps of the Relaciones �ұ�Dz���á�ھ�������.

We will be working with 27 scholars from and , delivering training on , and presenting an introduction to the Spatial Humanities and the use of these technologies. From here, this will evolve into a citizen science project, where we will meet online every week to take part in ‘mappathons’ with all our participants, completing the annotation of our full corpus of sixteenth-century maps.

‘’
Relaciones �ұ�Dz���á�ھ������� de México y Guatemala, 1577-1585. Joaquín García Icazbalceta Manuscript Collection, University of Texas.

We will be annotating the full corpus of the (), as well as a number of maps from the and the . These maps are a unique reflection on sixteenth-century settlements in Mexico, drawn using a combination of indigenous and European techniques and ideas. This interplay of indigenous and European voices is a key part of these maps’ significance, offering a unique insight into multiple perceptions of space and place during this crucial period in Mexico’s history. The maps of the RGs contain a great variety of information, both textual and pictographic, which offer invaluable insight into the historical and geographical contexts in which these maps were produced. This information includes proper names in the form of both traditions, logographic Mesoamerican toponyms and people’s names and European alphabetic glosses.

The week before last, we organised a two-day workshop, ‘Exploring Artificial Intelligence for Humanities Research’, hosted by the in collaboration with , and funded by the ESRC IAA Business Boost.

Tagtog is an online Artificial Intelligence platform that uses Natural Language Processing and Machine Learning for the automated annotation of documents. The idea for this workshop stemmed from a collaboration between the TAP-ESRC project ‘’ (DECM) and , where tagtog is being used to assist in the annotation and extraction of information from historical documents which predominantly feature sixteenth-century Spanish, but also includes indigenous languages such as Nahuatl, Mixtec, and variants of Mayan. Natural Language Processing and Machine Learning are continually evolving fields, and humanities research which employs tools from these disciplines present new and interesting challenges.

The workshop brought together experts from numerous fields in both the humanities and computer sciences, with the aim of addressing the questions and problems that we encounter in Digital Humanities research, exploring the ways in which we can try to resolve these issues through collaborative working.

The second day was hosted by Juan Miguel Cejuela and Jorge Campos of tagtog, with a presentation exploring Machine Learning and Natural Language Processing. The slides from this presentation can be viewed . This was followed by a hands-on session which introduced participants to using the tagtog platform for automated annotation of documents, exploring the ways in which this approach could aid humanities research.

If you’re interested in using tagtog, but you’re not sure where to start, they have some on their website which give just a few examples of the ways in which their tool can be used to computationally analyse and extract data from textual information.

Find out more about tagtog: | |

These two days were a fantastic opportunity to get together with researchers in the humanities and computer sciences, exploring the different ways in which we can work together. We heard about some fascinating Digital Humanities projects and learned a great deal from Juan Miguel and Jorge at tagtog about how Machine Learning and Natural Language Processing work, as well as how best to utilise their wonderful annotation platform at .

We hope to put together some more opportunities for workshops like this – keep an eye out for ������Ƶ Digital Humanities Hub updates: |

Over the past few months, our team have been laying the groundwork for our research into the Relaciones �ұ�Dz���á�ھ������� and getting to grips with our source material. Here’s a sneak-peak of our exponentially expanding GIS place-name layers:��

The sheer size and non-standardised format of the Relaciones has meant that studying these documents has previously relied on close-reading of the texts, limiting the scope of research. Approaching this study from an interdisciplinary perspective offers us the chance to engage with innovative computational methodologies to create new opportunities for the exploration and study of these historic documents, improving accessibility and broadening the scope for research.��

Some of the key problems we aim to address include: the capability of computational methods in dealing with multilingual corpora, the ambiguous nature of many place-names mentioned within the Relaciones, and the general inaccessibility of historical texts as large and complex as this.��

We will be tackling these problems collaboratively as an interdisciplinary team, ensuring that our research contributes to the advancements of each of our fields of study. Each team brings their own expertise to the project, and by working collaboratively we are better equipped to tackle the problems posed by large historical source materials such as the Relaciones �ұ�Dz���á�ھ�������.��

One of the key challenges we face with the Relaciones �ұ�Dz���á�ھ������� is that of linguistics. This multilingual corpus features a combination of Spanish and a number of indigenous languages (predominantly Nahuatl) throughout. The excerpt below demonstrates one of the linguistic issues we face in dealing with these historic documents. “Hun 4at” and “Oxi 4ahol” are the indigenous names in Mayan Quiche for two volcanoes referenced in the ����������ó�� de Santiago ���پ��ٱ�á��.��

With Natural Language Processing systems usually being trained with modern news text, they would be unable to recognise and tag words in an indigenous language such as Quiche, especially with the unfamiliar usage of a numerical character in a place-name. Computational methods for the analysis of language are continually improving, though their use in the analysis of historical texts and non-English languages still presents many challenges. Our project aims to address these problems and improve methods for the analysis of complex historical documents such as the Relaciones �ұ�Dz���á�ھ�������.��

Feel free to leave your comments and/or . If you would like to read more about individual members of our team, please see our page.��

A considerable amount of our time on the project so far has been dedicated to GIS, and to the creation of maps which reflect geographic boundaries as they existed in sixteenth century Middle America. The work of and has been an invaluable source of information, providing detailed explorations of the historical geography of New Spain in the years following Spanish arrival.��

The maps Gerhard produced focused largely on the administrative boundaries imposed by the Spanish in the sixteenth century. We have used these maps as a starting point, creating GIS layers which reflect boundaries as depicted by Gerhard:����

��

Whilst some of these administrative units were built upon pre-existing and well-established indigenous systems of governance, they ultimately reflect a Spanish administrative geography, divided into dioceses, audiencias, and provincias, with identified place-names being the sites of Spanish alcaldia mayores and corregimientos.����

Of course, Middle America’s historical geography did not begin with the establishment of Spanish administrative units, and we aim to produce a more representative image of Middle America’s sixteenth century geography. The identification of historic place-names will be key to our understanding of��indigenous and historic geographies, and we are currently creating GIS layers which locate these place-names.����

The process for doing this has been straightforward but very time-consuming, as it could only be semi-automated. We began with the digitisation of various geographic indexes included in the works of Peter Gerhard, Mercedes de la Garza, René Acuña, Francisco del Paso y Troncoso and Alejandra Moreno Toscano. These indexes contain thousands of place-names referenced in the Relaciones �ұ�Dz���á�ھ�������. With these lists compiled, we then had the task of cross-referencing, or joining, these tables with existing location data, derived from a number of sources including historical secondary sources and .����

Of course, changes over time and variations in spelling mean that joining these sets of data cannot rely solely on a computer recognising identical matches. Our UK Research Associate, Dr Raquel Liceras-Garrido in collaboration with our Mexico Research Associate Mariana Favila-Vázquez, has been spearheading the painstaking task of locating the thousands of place-names for which there was no match with existing geographic data. Already a monumental undertaking, the process is further complicated by the fact that there are often numerous names for the same place (and these numerous names often have numerous alternative spellings!) For example, throughout the historical record, present-day Ixtacamaxtitlán in Puebla state is known variously as San Francisco Iztaquimaxtitlan, S Francisco Iztaquimaxtitlan, Istac-ymachtitlan, Estacquimestitlan, Itztaquimitztitlan and Castilblanco.����

Place names are often repeated across America (don’t get us started on San Juan) and there are numerous cases where it is not possible to determine the exact location of a place-name. The expertise of our colleagues in Mexico, Mariana Favila Vázquez and Dr Diego Jimenez-Badillo, has been invaluable in the disambiguation of hundreds of these place-names. For place-names which we have been unable to locate, our Mexican team have undertaken historical research in order to assign them coordinates. For those place-names which have managed to evade all our investigations (for now!), our Mexico team have so far been able to at least determine the region in which they lie.��

This research will also prove invaluable in our experiments conducted in collaboration with the Portuguese team on automatic multilingual Named entity Recognition and place-name linguistic and geographic disambiguation, which is the next stage in our research. ��