Publication

Word Embeddings for Natural Language Processing

Related publications (146)

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

New Multi-Keyword Ciphertext Search Method for Sensor Network Cloud Platforms

Jiyong Zhang, Yue Wang, Hongyu Yang

This paper proposed a multi-keyword ciphertext search, based on an improved-quality hierarchical clustering (MCS-IQHC) method. MCS-IQHC is a novel technique, which is tailored to work with encrypted data. It has improved search accuracy and can self-adapt ...

MDPI2018

Multilingual bottleneck features for subword modeling in zero-resource languages

Enno Hermann

How can we effectively develop speech technology for languages where no transcribed data is available? Many existing approaches use no annotated resources at all, yet it makes sense to leverage information from large annotated corpora in other languages, f ...

2018

Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Features

Martin Jaggi, Matteo Pagliardini, Prakhar Gupta

The recent tremendous success of unsupervised word embeddings in a multitude of applications raises the obvious question if similar methods could be derived to improve embeddings (i.e. semantic representations) of word sequences as well. We present a simpl ...

2017

Improving speaker turn embedding by crossmodal transfer learning from face embedding

Jean-Marc Odobez

Learning speaker turn embeddings has shown considerable improvement in situations where conventional speaker modeling approaches fail. However, this improvement is relatively limited when compared to the gain observed in face embedding learning, which has ...

2017

Template Induction over Unstructured Email Corpora

Julia Proskurnia

Unsupervised template induction over email data is a central component in applications such as information extraction, document classification, and auto-reply. The benefits of automatically generating such templates are known for structured data, e.g. mach ...

Automated Taxonomy Induction and its Applications

Amit Gupta

Machine-readable semantic knowledge in the form of taxonomies (i.e., a collection of is-a edges) has proved to be beneficial in an array of NLP tasks including inference, textual entailment, question answering and information extraction. Such widespread ut ...

EPFL2017

Comparative Study on Sentence Boundary Prediction for German and English Broadcast News

Philip Neil Garner, David Imseng, Yang Wang

We present a comparative study on sentence boundary prediction for German and English broadcast news that explores generalization across different languages. In the feature extraction stage, word pause duration is firstly extracted from word aligned speech ...

Idiap2017

Argument discovery via crowdsourcing

Karl Aberer, Quoc Viet Hung Nguyen, Thành Tâm Nguyên, Chi Thang Duong

The amount of controversial issues being discussed on the Web has been growing dramatically. In articles, blogs, and wikis, people express their points of view in the form of arguments, i.e., claims that are supported by evidence. Discovery of arguments ha ...

Springer Verlag2017

Detecting Trends in Job Advertisements

Pierre Dillenbourg, Kshitij Sharma, Khalil Mrini

We present an automatic method for trend detection in job ads. From a job-posting website, we collect job ads from 16 countries and in 8 languages and 6 job domains. We pre-process them by removing stop words, lemmatising and performing cross-domain filter ...

2017

Building Word Embeddings for Solving 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 ...

École Polytechnique Fédérale de Lausanne2016