From "Cyclopaedia" to "Encyclopédie": Using Machine Translation and Sequence Alignment to Identify Encyclopedia Articles across Languages

paper, specified "long paper"
  1. 1. Glenn Roe

    Sorbonne University, France

  2. 2. Mark Olsen

    ARTFL Project - University of Chicago

  3. 3. Robert Morrissey

    ARTFL Project - University of Chicago

Work text
This plain text was ingested for the purpose of full-text search, not to preserve original formatting or readability. For the most complete copy, refer to the original conference program.

It is well known that the great 18th-century French 
Encyclopédie began first as a modest translation project of Ephraim Chambers’
Cyclopaedia in 1745. And, although their project grew into something much more significant, the
Enyclopédie editors (Diderot and d’Alembert) were not shy in incorporating translations of the 
Cyclopaedia as filler for their expanded work. Indeed, as Paolo Quintili remarks, ‘the they left a good part of these articles almost unchanged, or with only minor changes’ (Quintili, 1996: 75). Given the scale of the two works under consideration, however, systematic evaluation of the extent of the 
philosophes’ use of Chambers has remained, even today, a daunting task. John Lough, in 1980, framed the problem thusly:
‘So far no one has had the patience to make a detailed study of the exact relationship between the text of Diderot's 
Encyclopédie and the work of Ephraim Chambers. This would no doubt require several years of arduous toil devoted to comparing the two works article by article’ (Lough, 1980: 221).

Recent developments in machine translation and sequence alignment now offer new possibilities for the systematic comparison of digital texts across languages. This paper outlines some recent experimental work in leveraging these new techniques in an effort to reduce the ‘arduous toil’ of textual comparison through automatic translation. In essence, we aimed to generate French translations of 
Cyclopaedia articles and then use sequence alignment to identify similar passages also found in the 
Encyclopédie [1].

We examined two of the most widely-used resources in this domain, Googe Translate and DeepL. Both systems provide useful APIs as part of their respective subscription services, and both provide translations based on cutting-edge neural network language models. While DeepL provided somewhat more satisfying translations from a reader's perspective, we ultimately opted to use Google Translate for the ease of its API and its ability to parse TEI-XML. The latter is of critical importance as we wanted to keep the overall document structure of our dictionaries to allow for easy navigation between the versions.
Our objective here was
not to produce a good translation of the text, or even one that might serve as the basis for a readable edition. Rather, this machine-generated edition serves as a ‘pivot-text’ between the two corpora, allowing for an automatic comparison of the two (or three) versions using ARTFL’s highly fault-tolerant sequence alignment package, Text-PAIR [2]. In order to determine the parameters for this task, we ran a series of tests with different matching parameters on a representative selection of 100 articles where Chambers was identified as the possible source. It is important to note that even with the best parameters, which we adjusted to get favourable recall and precision results, we were only able to identify 81 of these 100 articles.

Once settled on the optimal parameters, we then used Text-PAIR to generate both an alignment database, for interactive examination, and a set of static results tables. The alignment database contains some 7,304 aligned passage pairs. The system allows queries on metadata, such as author and article title as well as words or phrases found in the aligned passages. Each aligned passage is presented as a facing page representation and the user can toggle a display of the variations between the two aligned passages. As seen below, the variations between the texts can be extensive (
fig. 1).

Figure 1. Text-PAIR interface showing differences in the article “Air”.
Text-PAIR also contextualises results back to the original document(s). For example, the following is the article “Almanach” by d'Alembert, showing the aligned passage from Chambers in blue (
fig. 2).  

Figure 2. Article “Almanach” with shared Chambers passages in blue.

In this instance, d'Alembert reused almost all of Chambers’ original article “Almanac”, with some minor variations, but does not to appear to have indicated the source of the first part of his article.  
To accumulate results and to refine their assessment, we developed an evaluation algorithm for each alignment, with parameters based on the length of the matching passages and the degree to which the headwords were close matches. This simple evaluation model eliminated a significant number of false positives, which we found were typically short text matches between articles with different headwords. The output of this algorithm resulted in two tables, one for matches that were likely to be valid and one that was less likely to be valid, based on these simple heuristics.
In all, we found some 3,778 articles in the 
Encyclopédie that upon evaluation seem highly similar in both content and structure to articles in the 1741 edition of Chambers’
Cyclopaedia. Whether or not these articles constitute real acts of historical translation is the subject for another, or several other, articles. There are simply too many outside factors at play, even in this rather straightforward comparison, to make blanket conclusions about the editorial practices of the 
encyclopédistes based on this limited experiment [3]. What we can say, however, is that of the 1,081 articles that include a ‘Chambers’ reference in the 
Encyclopédie, we only found 689 with at least one matching passage, although even here, the recall may in fact be higher than the numbers suggest, given that some citations function more like cross-references. Nonetheless, beyond testing this ground truth, we are also left with the rather astounding fact of 3,089 articles with no reference to Chambers whatsoever, all of which seem to be at least somewhat related to their English predecessor.

[1] Our two comparison datasets are the ARTFL
Encyclopédie and the recently digitised ARTFL edition of the 1741 Chambers
Cyclopaedia. See and The 1741 edition was selected as it was one of the likely sources for the translation original project and we were able to work from high quality pages images provided by the University of Chicago Library. On the possible editions of the 
Cyclopaedia used by the 
encyclopédistes, see (Passeron, 2006). On Text-PAIR, see

[2] See Clovis Gladstone, Russ Horton, and Mark Olsen, "
(Pairwise Alignment for Intertextual Relations)", ARTFL Project, University of Chicago, 2008-2021, and, more specifically, (Olsen, Horton and Roe, 2011).

[3] The question of the 
Dictionnaire de Trévoux is one such factor, as it is known that both Chambers and the 
encyclopédistes used it as a source for their own articles—so matches we find between the Chambers and 
Encyclopédie may indeed represent shared borrowings from the Trévoux and not a translation at all. Or, more interestingly, perhaps Chambers translated a Trévoux article from French to English, which a dutiful 
encyclopédiste then translated back to French for the 
Encyclopédie—in this case, which article is the 'source' and which the 'translation'? For more on these particular aspects of dictionary-making, see our previous article (Allen et al., 2010) and a response (Leca-Tsiomis, 2013).


Allen, T. et al. (2010). Plundering philosophers: identifying sources of the Encyclopédie", J
ournal of the Association for History and Computing

Leca-Tsiomis, M. (2013). The use and abuse of the digital humanities in the history of ideas: How to study the 
History of European Ideas 
39.4: 467-76.

Lough, J. (1980). The 
Encyclopédie and the Chambers' 
185: 221-24

Passeron, I. (2006). Quelle(s) édition(s) de la Cyclopœdia les encyclopédistes ont-ils utilisée(s) ? 
Recherches sur Diderot et sur l'Encyclopédie 
40-41: 287-92.

Olsen, M., Horton, R. and Roe, G. (2011). Something borrowed: Sequence alignment and the identification of similar passages in large text collections. 
Digital Studies / Le Champ numérique 

Quintili, P. (1996). D'Alembert ‘traduit’ Chambers. Les articles de mécanique de la 
Cyclopædia à l'
Recherches sur Diderot et sur l'Encyclopédie, 

If this content appears in violation of your intellectual property rights, or you see errors or omissions, please reach out to Scott B. Weingart to discuss removing or amending the materials.

Conference Info

In review

ADHO - 2022
"Responding to Asian Diversity"

Tokyo, Japan

July 25, 2022 - July 29, 2022

361 works by 945 authors indexed

Held in Tokyo and remote (hybrid) on account of COVID-19

Conference website:

Contributors: Scott B. Weingart, James Cummings

Series: ADHO (16)

Organizers: ADHO