EMNLP 2018

Semi-Supervised Sequence Modeling with Cross-View Training

EMNLP 2018 tensorflow/models

We therefore propose Cross-View Training (CVT), a semi-supervised learning algorithm that improves the representations of a Bi-LSTM sentence encoder using a mix of labeled and unlabeled data.

CCG SUPERTAGGING DEPENDENCY PARSING MACHINE TRANSLATION MULTI-TASK LEARNING NAMED ENTITY RECOGNITION (NER) UNSUPERVISED REPRESENTATION LEARNING

Understanding Back-Translation at Scale

EMNLP 2018 pytorch/fairseq

An effective method to improve neural machine translation with monolingual data is to augment the parallel training corpus with back-translations of target language sentences.

MACHINE TRANSLATION

Loss in Translation: Learning Bilingual Word Mapping with a Retrieval Criterion

EMNLP 2018 facebookresearch/MUSE

Continuous word representations learned separately on distinct languages can be aligned so that their words become comparable in a common space.

Non-Adversarial Unsupervised Word Translation

EMNLP 2018 facebookresearch/MUSE

We present a novel method that first aligns the second moment of the word distributions of the two languages and then iteratively refines the alignment.

Unsupervised Statistical Machine Translation

EMNLP 2018 artetxem/vecmap

While modern machine translation has relied on large parallel corpora, a recent line of work has managed to train Neural Machine Translation (NMT) systems from monolingual corpora only (Artetxe et al., 2018c; Lample et al., 2018).

LANGUAGE MODELLING UNSUPERVISED MACHINE TRANSLATION

Improving the Transformer Translation Model with Document-Level Context

EMNLP 2018 thumt/THUMT

Although the Transformer translation model (Vaswani et al., 2017) has achieved state-of-the-art performance in a variety of translation tasks, how to use document-level context to deal with discourse phenomena problematic for Transformer still remains a challenge.

Bayesian Compression for Natural Language Processing

EMNLP 2018 ars-ashuha/variational-dropout-sparsifies-dnn

In natural language processing, a lot of the tasks are successfully solved with recurrent neural networks, but such models have a huge number of parameters.

Learning Named Entity Tagger using Domain-Specific Dictionary

EMNLP 2018 shangjingbo1226/AutoNER

Recent advances in deep neural models allow us to build reliable named entity recognition (NER) systems without handcrafting features.

NAMED ENTITY RECOGNITION (NER)

Linguistically-Informed Self-Attention for Semantic Role Labeling

EMNLP 2018 strubell/LISA

Unlike previous models which require significant pre-processing to prepare linguistic features, LISA can incorporate syntax using merely raw tokens as input, encoding the sequence only once to simultaneously perform parsing, predicate detection and role labeling for all predicates.

DEPENDENCY PARSING MULTI-TASK LEARNING PART-OF-SPEECH TAGGING PREDICATE DETECTION SEMANTIC ROLE LABELING (PREDICTED PREDICATES) WORD EMBEDDINGS