NAACL 2018

Self-Attention with Relative Position Representations

NAACL 2018 tensorflow/tensor2tensor

On the WMT 2014 English-to-German and English-to-French translation tasks, this approach yields improvements of 1. 3 BLEU and 0. 3 BLEU over absolute position representations, respectively.

MACHINE TRANSLATION

Deep contextualized word representations

NAACL 2018 zalandoresearch/flair

We introduce a new type of deep contextualized word representation that models both (1) complex characteristics of word use (e. g., syntax and semantics), and (2) how these uses vary across linguistic contexts (i. e., to model polysemy).

CITATION INTENT CLASSIFICATION COREFERENCE RESOLUTION LANGUAGE MODELLING NAMED ENTITY RECOGNITION NATURAL LANGUAGE INFERENCE QUESTION ANSWERING SEMANTIC ROLE LABELING SENTIMENT ANALYSIS

Classical Structured Prediction Losses for Sequence to Sequence Learning

NAACL 2018 pytorch/fairseq

There has been much recent work on training neural attention models at the sequence-level using either reinforcement learning-style methods or by optimizing the beam.

ABSTRACTIVE TEXT SUMMARIZATION MACHINE TRANSLATION STRUCTURED PREDICTION

Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Features

NAACL 2018 epfml/sent2vec

The recent tremendous success of unsupervised word embeddings in a multitude of applications raises the obvious question if similar methods could be derived to improve embeddings (i. e. semantic representations) of word sequences as well.

SENTENCE EMBEDDINGS WORD EMBEDDINGS

Unsupervised Keyphrase Extraction with Multipartite Graphs

NAACL 2018 boudinfl/pke

We propose an unsupervised keyphrase extraction model that encodes topical information within a multipartite graph structure.

Higher-order Coreference Resolution with Coarse-to-fine Inference

NAACL 2018 kentonl/e2e-coref

We introduce a fully differentiable approximation to higher-order inference for coreference resolution.

COREFERENCE RESOLUTION

A Dataset of Peer Reviews (PeerRead): Collection, Insights and NLP Applications

NAACL 2018 allenai/PeerRead

In the first task, we show that simple models can predict whether a paper is accepted with up to 21% error reduction compared to the majority baseline.

Character-based Neural Networks for Sentence Pair Modeling

NAACL 2018 lanwuwei/SPM_toolkit

Sentence pair modeling is critical for many NLP tasks, such as paraphrase identification, semantic textual similarity, and natural language inference.

NATURAL LANGUAGE INFERENCE PARAPHRASE IDENTIFICATION SEMANTIC TEXTUAL SIMILARITY SENTENCE PAIR MODELING

Ranking Sentences for Extractive Summarization with Reinforcement Learning

NAACL 2018 shashiongithub/Refresh

In this paper we conceptualize extractive summarization as a sentence ranking task and propose a novel training algorithm which globally optimizes the ROUGE evaluation metric through a reinforcement learning objective.

DOCUMENT SUMMARIZATION