BUCC 2017 Shared Task: a First Attempt Toward a Deep Learning Framework for Identifying Parallel Sentences in Comparable Corpora

2017-08-01WS 2017Unverified0· sign in to hype

Francis Gr{\'e}goire, Philippe Langlais

Unverified — Be the first to reproduce this paper.

Abstract

This paper describes our participation in BUCC 2017 shared task: identifying parallel sentences in comparable corpora. Our goal is to leverage continuous vector representations and distributional semantics with a minimal use of external preprocessing and postprocessing tools. We report experiments that were conducted after transmitting our results.

Tasks

Feature Engineering Language Modeling Language Modelling Machine Translation Semantic Textual Similarity Word Embeddings

BUCC 2017 Shared Task: a First Attempt Toward a Deep Learning Framework for Identifying Parallel Sentences in Comparable Corpora

Abstract

Tasks

Reproductions