Natural Language Processing (NLP) driven categorisation and detection of discourse in historical US patents
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.
A Language Model (LM) is a helpful component of a variety of Natural Language Processing (NLP) systems today. For speech recognition, machine translation, information retrieval, word sense disambiguation etc., the contribution of an LM is to provide featur ...
Because they provide exclusive property rights, patents are generally considered to be an effective way to promote intellectual discovery. Here, we propose a different compensation scheme, in which everyone holds shares in the components of potential disco ...
We first present our work in machine translation, during which we used aligned sentences to train a neural network to embed n-grams of different languages into an d-dimensional space, such that n-grams that are the translation of each other are close with ...
Patent-based indicators at the country level are frequently used to assess countries' innovation performances or efforts. Yet they are often said to reflect the propensity to patent rather than actual research productivity. The authors of this article argu ...
Contrary to an accepted wisdom, this paper shows that cross-country variations in the number of patents per researcher do not only reflect differences in the propensity to patent but also signals differences in research productivity. We put forward and tes ...
This paper introduces a new dataset and compares several methods for the recommendation of non-fiction audio-visual material, namely lectures from the TED website. The TED dataset contains 1,149 talks and 69,023 user profiles, who have made more than 100,0 ...
We propose a unified neural network architecture and learning algorithm that can be applied to various natural language processing tasks including part-of-speech tagging, chunking, named entity recognition, and semantic role labeling. This versatility is a ...
Patent statistics represent a critical tool for scholars, statisticians and policy makers interested in innovation and intellectual property rights. Many analyses are based on heterogeneous methods delineating the inventors’ or firms’ patent portfolios wit ...
Patent statistics represent a critical tool for scholars, statisticians and policy makers interested in innovation and intellectual property rights. Many analyses are based on heterogeneous methods delineating the inventors' or firms' patent portfolios wit ...
We will develop and implement new algorithms for constraint solving and apply them to construct two classes of tools: 1) bug finding and verification tools building on tools such as Java PathFinder and Jahob; 2) tools for deep semantic analysis of texts co ...
