Publications associées à Evolution of Topics and Novelty in Science

Robust machine learning for neuroscientific inference

Modern neuroscience research is generating increasingly large datasets, from recording thousands of neurons over long timescales to behavioral recordings of animals spanning weeks, months, or even years. Despite a great variety in recording setups and expe ...

EPFL2024

Robustness, replicability and scalability in topic modelling

Orion B Penner, Omar Ballester Gonzalez

Approaches for estimating the similarity between individual publications are an area of long -standing interest in the scientometrics and informetrics communities. Traditional techniques have generally relied on references and other metadata, while text mi ...

ELSEVIER2022

Sequential Domain Adaptation by Synthesizing Distributionally Robust Experts

Viet Anh Nguyen, Daniel Kuhn, Bahar Taskesen

Least squares estimators, when trained on a few target domain samples, may predict poorly. Supervised domain adaptation aims to improve the predictive accuracy by exploiting additional labeled training samples from a source distribution that is close to th ...

JMLR-JOURNAL MACHINE LEARNING RESEARCH2021

The organisation of science: topics, incentives and funding

Omar Ballester Gonzalez

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 ...

EPFL2020

Multi-scale sequential network for semantic text segmentation and localization

Jean-Marc Odobez, Olivier Canévet, Michael Villamizar

We present a novel method for semantic text document analysis which in addition to localizing text it labels the text in user-defined semantic categories. More precisely, it consists of a fully-convolutional and sequential network that we apply to the part ...

2020

Concept Discovery for The Interpretation of Landscape Scenicness

Devis Tuia

In this paper, we study how to extract visual concepts to understand landscape scenicness. Using visual feature representations from a Convolutional Neural Network (CNN), we learn a number of Concept Activation Vectors (CAV) aligned with semantic concepts ...

2020

Overview of CLEF HIPE 2020: Named Entity Recognition and Linking on Historical Newspapers

Maud Ehrmann, Matteo Romanello

This paper presents an overview of the first edition of HIPE (Identifying Historical People, Places and other Entities), a pioneering shared task dedicated to the evaluation of named entity processing on historical newspapers in French, German and English. ...

Springer2020

Extended Overview of CLEF HIPE 2020: Named Entity Processing on Historical Newspapers

Maud Ehrmann, Matteo Romanello

This paper presents an extended overview of the first edition of HIPE (Identifying Historical People, Places and other Entities), a pioneering shared task dedicated to the evaluation of named entity processing on historical newspapers in French, German and ...

CEUR-WS2020

Introducing the CLEF 2020 HIPE Shared Task: Named Entity Recognition and Linking on Historical Newspapers

Maud Ehrmann, Matteo Romanello

Since its introduction some twenty years ago, named entity (NE) processing has become an essential component of virtually any text mining application and has undergone major changes. Recently, two main trends characterise its developments: the adoption of ...

Springer International Publishing2020

Joint Learning of Semantic Alignment and Object Landmark Detection

Seungryong Kim

Convolutional neural networks (CNNs) based approaches for semantic alignment and object landmark detection have improved their performance significantly. Current efforts for the two tasks focus on addressing the lack of massive training data through weakly ...

IEEE2019

Crosslingual Document Embedding as Reduced-Rank Ridge Regression

Martin Jaggi, Robert West, Martin Josifoski, Ivan Paskov

There has recently been much interest in extending vector-based word representations to multiple languages, such that words can be compared across languages. In this paper, we shift the focus from words to documents and introduce a method for embedding doc ...

2019

Text Similarity in Vector Space Models: A Comparative Study

Omid Shahmirzadi, Kenneth Younge, Adam Lugowski

Automatic measurement of semantic text similarity is an important task in natural language processing. In this paper, we evaluate the performance of different vector space models to perform this task. We address the real-world problem of modeling patent-to ...

2018

Simple Unsupervised Keyphrase Extraction using Sentence Embeddings

Kamil Bennani-Smires, Claudiu-Cristian Musat, Martin Jaggi

Keyphrase extraction is the task of automatically selecting a small set of phrases that best describe a given free text document. Keyphrases can be used for indexing, searching, aggregating and summarizing text documents, serving many automatic as well as ...

2018

Unleashing the power of semantic text analysis: a complex systems approach

Andrea Martini

In the present information era, a huge amount of machine-readable data is available regarding scientific publications. Such unprecedented wealth of data offers the opportunity to investigate science itself as a complex interacting system by means of quanti ...

EPFL2018

Word Embeddings for Natural Language Processing

Rémi Philippe Lebret

Word embedding is a feature learning technique which aims at mapping words from a vocabulary into vectors of real numbers in a low-dimensional space. By leveraging large corpora of unlabeled text, such continuous space representations can be computed for c ...

EPFL2016

Distribution-Matching Embedding for Visual Domain Adaptation

Mathieu Salzmann

Domain-invariant representations are key to addressing the domain shift problem where the training and test examples follow different distributions. Existing techniques that have attempted to match the distributions of the source and target domains typical ...

2016

Data Summarization with Social Contexts

Karl Aberer, Xia Hu, Tian Guo, Hao Zhuang, Rameez Rahman

While social data is being widely used in various applications such as sentiment analysis and trend prediction, its sheer size also presents great challenges for storing, sharing and processing such data. These challenges can be addressed by data summariza ...

Assoc Computing Machinery2016

Rehabilitation of Count-based Models for Word Vector Representations

Ronan Collobert, Rémi Philippe Lebret

Recent works on word representations mostly rely on predictive models. Distributed word representations (aka word embeddings) are trained to optimally predict the contexts in which the corresponding words tend to appear. Such models have succeeded in captu ...

Springer International Publishing2015

Similarity Learning Over Large Collaborative Networks

Majid Yazdani

In this thesis, we propose novel solutions to similarity learning problems on collaborative networks. Similarity learning is essential for modeling and predicting the evolution of collaborative networks. In addition, similarity learning is used to perform ...

EPFL2013

Computing text semantic relatedness using the contents and links of a hypertext encyclopedia

Majid Yazdani, Andrei Popescu-Belis

We propose a method for computing semantic relatedness between words or texts by using knowledge from hypertext encyclopedias such as Wikipedia. A network of concepts is built by filtering the encyclopedia's articles, each concept corresponding to an artic ...

Elsevier Science Bv2013