Laboratoire d'Histoire des Sciences et des Techniques
Laboratoire
Publications associées (41)
Graph Chatbot
Chattez avec Graph Search
Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.
AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.
We discuss some properties of generative models for word embeddings. Namely, (Arora et al., 2016) proposed a latent discourse model implying the concentration of the partition function of the word vectors. This concentration phenomenon led to an asymptotic ...
Recent breakthroughs in deep learning often rely on representation learning and knowledge transfer. In recent years, unsupervised and self-supervised techniques for learning speech representation were developed to foster automatic speech recognition. Up to ...
EUROPEAN ASSOC SIGNAL SPEECH & IMAGE PROCESSING-EURASIP2021
In this article, I focus on digital scientific archives which are made up of the leftovers of science, such as drafts, obsolete instruments, photographs, documentation, etc. The artifacts exhibited in such collections were neither meant to be representatio ...
The United States patent system is unique in that it requires applicants to cite documents they know to be relevant to the examination of their patent applications. Lampe (2012) presents evidence that applicants strategically withhold 21-33% of relevant ci ...
Ever since the links between the development of new technologies and economic growth became evident, researchers have attempted to study how the creation of knowledge fosters progress. If pushing the frontier of knowledge has an impact on progress and well ...
Modern patent systems are slow, inefficient, expensive, and may result in outcomes that actively harm technological progress. This paper proposes a substantive re-think of these systems and lays a foundation upon which practical solutions can be built. Man ...
Inventions of foreign origin are about ten percentage points less likely to be granted a U.S. patent than domestic inventions. An empirical analysis of 1.5 million U.S. patent applications identifies three systematic differences between foreign and domesti ...
Pre-trained word vectors are ubiquitous in Natural Language Processing applications. In this paper, we show how training word embeddings jointly with bigram and even trigram embeddings, results in improved unigram embeddings. We claim that training word em ...
2019
In matters of patents of invention, Switzerland was a unique case in the nineteenth century. After a brief experiment between 1801 and 1803, the country remained without a patent system until 1888. Not only was this situation exceptional in Europe and espe ...
2019
, ,
Large datasets on natural language inference are a potentially valuable resource for inducing semantic representations of natural language sentences. But in many such models the embeddings computed by the sentence encoder goes through an MLP-based interact ...
