CONLL 2018

Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction

CONLL 2018 elbayadm/attn2d

Current state-of-the-art machine translation systems are based on encoder-decoder architectures, that first encode the input sequence, and then generate an output sequence based on the input encoding.

MACHINE TRANSLATION

NLP-Cube: End-to-End Raw Text Processing With Neural Networks

CONLL 2018 adobe/NLP-Cube

We introduce NLP-Cube: an end-to-end Natural Language Processing framework, evaluated in CoNLL{'}s {``}Multilingual Parsing from Raw Text to Universal Dependencies 2018{''} Shared Task.

LEMMATIZATION TOKENIZATION

Simple Unsupervised Keyphrase Extraction using Sentence Embeddings

CONLL 2018 swisscom/ai-research-keyphrase-extraction

EmbedRank achieves higher F-scores than graph-based state of the art systems on standard datasets and is suitable for real-time processing of large amounts of Web data.

SENTENCE EMBEDDINGS

End-to-End Neural Entity Linking

CONLL 2018 dalab/end2end_neural_el

Entity Linking (EL) is an essential task for semantic text understanding and information extraction.

ENTITY DISAMBIGUATION ENTITY EMBEDDINGS ENTITY LINKING

The Lifted Matrix-Space Model for Semantic Composition

CONLL 2018 NYU-MLL/spinn

Tree-structured neural network architectures for sentence encoding draw inspiration from the approach to semantic composition generally seen in formal linguistics, and have shown empirical improvements over comparable sequence models by doing so.

SEMANTIC COMPOSITION WORD EMBEDDINGS

Improving Response Selection in Multi-Turn Dialogue Systems by Incorporating Domain Knowledge

CONLL 2018 SmartDataAnalytics/AK-DE-biGRU

Building systems that can communicate with humans is a core problem in Artificial Intelligence.

Evolutionary Data Measures: Understanding the Difficulty of Text Classification Tasks

CONLL 2018 Wluper/edm

In this paper we analyse exactly which characteristics of a dataset best determine how difficult that dataset is for the task of text classification.

TEXT CLASSIFICATION

Semi-Supervised Neural System for Tagging, Parsing and Lematization

CONLL 2018 360er0/COMBO

This paper describes the ICS PAS system which took part in CoNLL 2018 shared task on Multilingual Parsing from Raw Text to Universal Dependencies.

DEPENDENCY PARSING LEMMATIZATION MACHINE TRANSLATION QUESTION ANSWERING SENTIMENT ANALYSIS