Concept
Source text
Publications associées (18)
Gospel of the Marseille Docker - Nicholas Derybolsky from 1952
This text, accompanied by a ‘gospel’ that I made by montaging the US-recorded captions, is an attempt for re-narrating Marshall Plan’s discourse on the working class, aka the so-called ‘free labor’ of the US against the ‘communist labor’ of the “Soviet thr ...
EPFL Press2023Inventory of Problems: The Genesis of the Rotterdam Kunsthal by OMA/Rem Koolhaas, 1987-1992
The Kunsthal in Rotterdam is a key work in the oeuvre of OMA/Rem Koolhaas that marks the threshold between the firmâs architectural production of the decades before and after 1990. This doctoral thesis aims at a deeper and comprehensive understanding of ...
EPFL2021Cross-lingual Automatic Speech Recognition Exploiting Articulatory Features
Articulatory features (AFs) provide language-independent attribute by exploiting the speech production knowl-edge. This paper proposes a cross-lingual automatic speechrecognition (ASR) based on AF methods. Various neural network(NN) architectures are explo ...
2019The Intellectual Organisation of History
A tradition of scholarship discusses the characteristics of different areas of knowledge, in particular after modern academia compartmentalized them into disciplines. The academic approach is often put to question: are there two or more cultures? Is an eve ...
EPFL2018Word Sense Consistency in Statistical and Neural Machine Translation
Different senses of source words must often be rendered by different words in the target language when performing machine translation (MT). Selecting the correct translation of polysemous words can be done based on the contexts of use. However, state-of-th ...
EPFL2018Big Data of the Past
Frédéric Kaplan, Isabella Di Lenardo
Big Data is not a new phenomenon. History is punctuated by regimes of data acceleration, characterized by feelings of information overload accompanied by periods of social transformation and the invention of new technologies. During these moments, private ...
2017Kamusi Pre:D – Lexicon-based source-side predisambiguation for MT and other text processing applications
Kamusi has been developing a system to analyze texts on the source side and present users with sense-specified dictionary options. Similarly to spellcheck, the user selects the intended meaning. We then use a multilingual lexical database to bridge to matc ...
ENeL2016Investigating Cross-lingual Multi-level Adaptive Networks: The Importance of the Correlation of Source and Target Languages
Petr Motlicek, Philip Neil Garner
The multi-level adaptive networks (MLAN) technique is a cross-lingual adaptation framework where a bottleneck (BN) layer in a deep neural network (DNN) trained in a source lan- guage is used for producing BN features to be exploited in a second DNN in a ta ...
2016On Mining Citations to Primary and Secondary Sources in Historiography
Frédéric Kaplan, Giovanni Colavizza
We present preliminary results from the Linked Books project, which aims at analysing citations from the histo- riography on Venice. A preliminary goal is to extract and parse citations from any location in the text, especially footnotes, both to primary a ...
2015Discourse-level features for statistical machine translation
Machine Translation (MT) has progressed tremendously in the past two decades. The rule-based and interlingua approaches have been superseded by statistical models, which learn the most likely translations from large parallel corpora. System design does not ...
EPFL2015