NAACL 2019

FLAIR: An Easy-to-Use Framework for State-of-the-Art NLP

NAACL 2019 zalandoresearch/flair

We present FLAIR, an NLP framework designed to facilitate training and distribution of state-of-the-art sequence labeling, text classification and language models.

TEXT CLASSIFICATION

Pooled Contextualized Embeddings for Named Entity Recognition

NAACL 2019 zalandoresearch/flair

We make all code and pre-trained models available to the research community for use and reproduction.

Ranked #6 on Named Entity Recognition on CoNLL 2003 (English) (using extra training data)

NAMED ENTITY RECOGNITION

fairseq: A Fast, Extensible Toolkit for Sequence Modeling

NAACL 2019 facebookresearch/fairseq-py

fairseq is an open-source sequence modeling toolkit that allows researchers and developers to train custom models for translation, summarization, language modeling, and other text generation tasks.

LANGUAGE MODELLING TEXT GENERATION

Star-Transformer

NAACL 2019 fastnlp/fastNLP

Although Transformer has achieved great successes on many NLP tasks, its heavy structure with fully-connected attention connections leads to dependencies on large training data.

NAMED ENTITY RECOGNITION NATURAL LANGUAGE INFERENCE SENTIMENT ANALYSIS TEXT CLASSIFICATION

Improved Lexically Constrained Decoding for Translation and Monolingual Rewriting

NAACL 2019 awslabs/sockeye

Lexically-constrained sequence decoding allows for explicit positive or negative phrase-based constraints to be placed on target output strings in generation tasks such as machine translation or monolingual text rewriting.

DATA AUGMENTATION MACHINE TRANSLATION NATURAL LANGUAGE INFERENCE QUESTION ANSWERING

Better Word Embeddings by Disentangling Contextual n-Gram Information

NAACL 2019 epfml/sent2vec

Pre-trained word vectors are ubiquitous in Natural Language Processing applications.

WORD EMBEDDINGS

Consistency by Agreement in Zero-shot Neural Machine Translation

NAACL 2019 google-research/language

Generalization and reliability of multilingual translation often highly depend on the amount of available parallel data for each language pair of interest.

MACHINE TRANSLATION ZERO-SHOT MACHINE TRANSLATION

Rethinking Complex Neural Network Architectures for Document Classification

NAACL 2019 castorini/hedwig

Neural network models for many NLP tasks have grown increasingly complex in recent years, making training and deployment more difficult.

DOCUMENT CLASSIFICATION LANGUAGE MODELLING

compare-mt: A Tool for Holistic Comparison of Language Generation Systems

NAACL 2019 neulab/compare-mt

In this paper, we describe compare-mt, a tool for holistic analysis and comparison of the results of systems for language generation tasks such as machine translation.

MACHINE TRANSLATION TEXT GENERATION