WS 2019

Facebook FAIR's WMT19 News Translation Task Submission

WS 2019 pytorch/fairseq

This paper describes Facebook FAIR's submission to the WMT19 shared news translation task.

MACHINE TRANSLATION

A Repository of Conversational Datasets

WS 2019 PolyAI-LDN/conversational-datasets

Progress in Machine Learning is often driven by the availability of large datasets, and consistent evaluation metrics for comparing modeling approaches.

CONVERSATIONAL RESPONSE SELECTION DIALOGUE UNDERSTANDING

ScispaCy: Fast and Robust Models for Biomedical Natural Language Processing

WS 2019 allenai/scispacy

Despite recent advances in natural language processing, many statistical models for processing text perform extremely poorly under domain shift.

Racial Bias in Hate Speech and Abusive Language Detection Datasets

WS 2019 t-davidson/hate-speech-and-offensive-language

Technologies for abusive language detection are being developed and applied with little consideration of their potential biases.

What Does BERT Look At? An Analysis of BERT's Attention

WS 2019 clarkkev/attention-analysis

Large pre-trained neural networks such as BERT have had great recent success in NLP, motivating a growing body of research investigating what aspects of language they are able to learn from unlabeled data.

LANGUAGE MODELLING

Augmenting Neural Response Generation with Context-Aware Topical Attention

WS 2019 nouhadziri/THRED

Our model is built upon the basic Seq2Seq model by augmenting it with a hierarchical joint attention mechanism that incorporates topical concepts and previous interactions into the response generation.

SEMANTIC SIMILARITY SEMANTIC TEXTUAL SIMILARITY

Effective Dimensionality Reduction for Word Embeddings

WS 2019 vyraun/Half-Size

Pre-trained word embeddings are used in several downstream applications as well as for constructing representations for sentences, paragraphs and documents.

DIMENSIONALITY REDUCTION WORD EMBEDDINGS

Look Again at the Syntax: Relational Graph Convolutional Network for Gendered Ambiguous Pronoun Resolution

WS 2019 ianycxu/RGCN-with-BERT

Our work significantly improves the snippet-context baseline F1 score on GAP dataset from 66. 9% to 80. 3%.