Publication

Semantic Vector Machines

Related publications (123)

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.

OdiEnCorp 2.0: Odia-English Parallel Corpus for Machine Translation

Petr Motlicek

The preparation of parallel corpora is a challenging task, particularly for languages that suffer from under-representation in the digital world. In a multi-lingual country like India, the need for such parallel corpora is stringent for several low-resourc ...

European Language Resources Association (ELRA)2020

Two degree of freedom oscillator system

Simon Nessim Henein, Mohammad Hussein Kahrobaiyan, Billy Nussbaumer

Oscillator system (1) comprising:- a substantially planar frame (3);- a first sub-oscillator (5), a second sub-oscillator (7), a third sub-oscillator (9), and a fourth sub-oscillator (11), each sub-oscillator (5, 7, 9, 11) comprising a substantially rigid ...

2020

On the Limitations of Cross-lingual Encoders as Exposed by Reference-Free Machine Translation Evaluation

Robert West, Maxime Jean Julien Peyrard, Yang Gao, Wei Zhao

Evaluation of cross-lingual encoders is usually performed either via zero-shot cross-lingual transfer in supervised downstream tasks or via unsupervised cross-lingual textual similarity. In this paper, we concern ourselves with reference-free machine trans ...

ASSOC COMPUTATIONAL LINGUISTICS-ACL2020

Assisted Specification of Discrete Choice Models

Nicola Marco Ortelli

Determining appropriate utility specifications for discrete choice models is time-consuming and prone to errors. As the number of possible functions exponentially grows with the variables under consideration, analysts need to spend increasing amounts of ti ...

2020

ODIANLP's Participation in WAT2020

Petr Motlicek

This paper describes the team (“ODI-ANLP”)’s submission to WAT 2020. We have participated in the English→HindiMultimodal task and Indic task. We have used the state-of-the-art Transformer model for the translation task and Incep-tionResNetV2 for the Hindi ...

ACL2020

Notes on functions of hyperbolic type

Nicolas Monod

Functions of hyperbolic type encode representations on real or complex hyperbolic spaces, usually infinite-dimensional. These notes set up the complex case. As applications, we prove the existence of a non-trivial deformation family of representations of S ...

BELGIAN MATHEMATICAL SOC TRIOMPHE2020

Comparison of Subword Segmentation Methods for Open-vocabulary ASR using a Difficulty Metric

Philip Neil Garner, Claudiu-Cristian Musat

We experiment with subword segmentation approaches that are widely used to address the open vocabulary problem in the context of end-to-end automatic speech recognition (ASR). For morphologically rich languages such as German which has many rare words main ...

2020

Graph-to-Graph Transformer for Transition-based Dependency Parsing

James Henderson, Alireza Mohammadshahi

We propose the Graph2Graph Transformer architecture for conditioning on and predicting arbitrary graphs, and apply it to the challenging task of transition-based dependency parsing. After proposing two novel Transformer models of transition-based dependenc ...

Association for Computational Linguistics2020

Buckling instabilities and spatio-temporal dynamics of active elastic filaments

Tobias Schneider

Biological filaments driven by molecular motors tend to experience tangential propulsive forces also known as active follower forces. When such a filament encounters an obstacle, it deforms, which reorients its follower forces and alters its entire motion. ...

ROYAL SOC2020

Evaluating and Interpreting Deep Convolutional Neural Networks via Non-negative Matrix Factorization

Edo Collins

With ever greater computational resources and more accessible software, deep neural networks have become ubiquitous across industry and academia. Their remarkable ability to generalize to new samples defies the conventional view, which holds that complex, ...

EPFL2019