Massive Exploration of Neural Machine Translation Architectures

EMNLP 2017 • google/seq2seq •

Neural Machine Translation (NMT) has shown remarkable progress over the past few years with production systems now being deployed to end-users.

MACHINE TRANSLATION

ParlAI: A Dialog Research Software Platform

EMNLP 2017 • facebookresearch/ParlAI •

We introduce ParlAI (pronounced "par-lay"), an open-source software platform for dialog research implemented in Python, available at http://parl. ai.

VISUAL QUESTION ANSWERING

Supervised Learning of Universal Sentence Representations from Natural Language Inference Data

EMNLP 2017 • facebookresearch/InferSent •

Many modern NLP systems rely on word embeddings, previously trained in an unsupervised manner on large corpora, as base features.

CROSS-LINGUAL NATURAL LANGUAGE INFERENCE SEMANTIC TEXTUAL SIMILARITY TRANSFER LEARNING WORD EMBEDDINGS

NeuroNER: an easy-to-use program for named-entity recognition based on neural networks

EMNLP 2017 • Franck-Dernoncourt/NeuroNER •

Named-entity recognition (NER) aims at identifying entities of interest in a text.

NAMED ENTITY RECOGNITION

Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm

EMNLP 2017 • bfelbo/deepmoji •

NLP tasks are often limited by scarcity of manually annotated data.

SARCASM DETECTION SENTIMENT ANALYSIS

Reporting Score Distributions Makes a Difference: Performance Study of LSTM-networks for Sequence Tagging

EMNLP 2017 • UKPLab/emnlp2017-bilstm-cnn-crf •

In this paper we show that reporting a single performance score is insufficient to compare non-deterministic approaches.

Recurrent Attention Network on Memory for Aspect Sentiment Analysis

EMNLP 2017 • songyouwei/ABSA-PyTorch •

We propose a novel framework based on neural networks to identify the sentiment of opinion targets in a comment/review.

ASPECT-BASED SENTIMENT ANALYSIS FEATURE ENGINEERING

End-to-end Neural Coreference Resolution

EMNLP 2017 • kentonl/e2e-coref •

We introduce the first end-to-end coreference resolution model and show that it significantly outperforms all previous work without using a syntactic parser or hand-engineered mention detector.

COREFERENCE RESOLUTION

DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning

EMNLP 2017 • xwhan/DeepPath

We study the problem of learning to reason in large scale knowledge graphs (KGs).

KNOWLEDGE GRAPH EMBEDDING KNOWLEDGE GRAPH EMBEDDINGS KNOWLEDGE GRAPHS

Fast and Accurate Entity Recognition with Iterated Dilated Convolutions

EMNLP 2017 • iesl/dilated-cnn-ner •

Today when many practitioners run basic NLP on the entire web and large-volume traffic, faster methods are paramount to saving time and energy costs.

NAMED ENTITY RECOGNITION STRUCTURED PREDICTION