SEMEVAL 2018

NTUA-SLP at SemEval-2018 Task 3: Tracking Ironic Tweets using Ensembles of Word and Character Level Attentive RNNs

SEMEVAL 2018 cbaziotis/ntua-slp-semeval2018

In this paper we present two deep-learning systems that competed at SemEval-2018 Task 3 "Irony detection in English tweets".

WORD EMBEDDINGS

NTUA-SLP at SemEval-2018 Task 2: Predicting Emojis using RNNs with Context-aware Attention

SEMEVAL 2018 cbaziotis/ntua-slp-semeval2018

In this paper we present a deep-learning model that competed at SemEval-2018 Task 2 "Multilingual Emoji Prediction".

WORD EMBEDDINGS

Mixing Context Granularities for Improved Entity Linking on Question Answering Data across Entity Categories

SEMEVAL 2018 UKPLab/starsem2018-entity-linking

We investigate entity linking in the context of a question answering task and present a jointly optimized neural architecture for entity mention detection and entity disambiguation that models the surrounding context on different levels of granularity.

ENTITY DISAMBIGUATION ENTITY LINKING KNOWLEDGE BASE QUESTION ANSWERING

Deep Affix Features Improve Neural Named Entity Recognizers

SEMEVAL 2018 vikas95/Pref_Suff_Span_NN

We propose a practical model for named entity recognition (NER) that combines word and character-level information with a specific learned representation of the prefixes and suffixes of the word.

FEATURE ENGINEERING MORPHOLOGICAL ANALYSIS NAMED ENTITY RECOGNITION

NIHRIO at SemEval-2018 Task 3: A Simple and Accurate Neural Network Model for Irony Detection in Twitter

SEMEVAL 2018 NIHRIO/IronyDetectionInTwitter

This paper describes our NIHRIO system for SemEval-2018 Task 3 "Irony detection in English tweets".

Hypothesis Only Baselines in Natural Language Inference

SEMEVAL 2018 azpoliak/hypothesis-only-NLI

We propose a hypothesis only baseline for diagnosing Natural Language Inference (NLI).

NATURAL LANGUAGE INFERENCE

Resolving Event Coreference with Supervised Representation Learning and Clustering-Oriented Regularization

SEMEVAL 2018 kiankd/events

This work provides insight and motivating results for a new general approach to solving coreference and clustering problems with representation learning.

COREFERENCE RESOLUTION REPRESENTATION LEARNING

Fine-grained Entity Typing through Increased Discourse Context and Adaptive Classification Thresholds

SEMEVAL 2018 sheng-z/figet

Fine-grained entity typing is the task of assigning fine-grained semantic types to entity mentions.

ENTITY TYPING