WS 2018

Scaling Neural Machine Translation

WS 2018 facebookresearch/fairseq-py

Sequence to sequence learning models still require several days to reach state of the art performance on large benchmark datasets using a single machine.

MACHINE TRANSLATION

A Call for Clarity in Reporting BLEU Scores

WS 2018 mjpost/sacreBLEU

The field of machine translation faces an under-recognized problem because of inconsistency in the reporting of scores from its dominant metric.

MACHINE TRANSLATION TOKENIZATION

Hate Speech Dataset from a White Supremacy Forum

WS 2018 aitor-garcia-p/hate-speech-dataset

Hate speech is commonly defined as any communication that disparages a target group of people based on some characteristic such as race, colour, ethnicity, gender, sexual orientation, nationality, religion, or other characteristic.

HATE SPEECH DETECTION

Parameter Sharing Methods for Multilingual Self-Attentional Translation Models

WS 2018 DevSinghSachan/multilingual_nmt

In multilingual neural machine translation, it has been shown that sharing a single translation model between multiple languages can achieve competitive performance, sometimes even leading to performance gains over bilingually trained models.

MACHINE TRANSLATION

A Knowledge-Grounded Multimodal Search-Based Conversational Agent

WS 2018 shubhamagarwal92/mmd

Multimodal search-based dialogue is a challenging new task: It extends visually grounded question answering systems into multi-turn conversations with access to an external database.

QUESTION ANSWERING

NTUA-SLP at IEST 2018: Ensemble of Neural Transfer Methods for Implicit Emotion Classification

WS 2018 alexandra-chron/wassa-2018

In this paper we present our approach to tackle the Implicit Emotion Shared Task (IEST) organized as part of WASSA 2018 at EMNLP 2018.

EMOTION CLASSIFICATION SENTIMENT ANALYSIS TRANSFER LEARNING WORD EMBEDDINGS

A Large-Scale Test Set for the Evaluation of Context-Aware Pronoun Translation in Neural Machine Translation

WS 2018 ZurichNLP/ContraPro

We show that, while gains in BLEU are moderate for those systems, they outperform baselines by a large margin in terms of accuracy on our contrastive test set.

MACHINE TRANSLATION