WS 2016

Semi-supervised Named Entity Recognition in noisy-text

WS 2016 napsternxg/TwitterNER

In this paper, we report on the solution [ST] we submitted to the WNUT 2016 NER shared task.

NAMED ENTITY RECOGNITION

CogALex-V Shared Task: LexNET - Integrated Path-based and Distributional Method for the Identification of Semantic Relations

WS 2016 vered1986/LexNET

The reported results in the shared task bring this submission to the third place on subtask 1 (word relatedness), and the first place on subtask 2 (semantic relation classification), demonstrating the utility of integrating the complementary path-based and distributional information sources in recognizing concrete semantic relations.

RELATION CLASSIFICATION

Path-based vs. Distributional Information in Recognizing Lexical Semantic Relations

WS 2016 vered1986/LexNET

Recognizing various semantic relations between terms is beneficial for many NLP tasks.

Kyoto University Participation to WAT 2016

WS 2016 fabiencro/knmt

We report very good translation results, especially when using neural MT for Chinese-to-Japanese translation.

MACHINE TRANSLATION SPELLING CORRECTION

A Character-level Convolutional Neural Network for Distinguishing Similar Languages and Dialects

WS 2016 boknilev/dsl-char-cnn

Discriminating between closely-related language varieties is considered a challenging and important task.

Named Entity Recognition in Swedish Health Records with Character-Based Deep Bidirectional LSTMs

WS 2016 olofmogren/biomedical-ner-data-swedish

We propose an approach for named entity recognition in medical data, using a character-based deep bidirectional recurrent neural network.

BOUNDARY DETECTION FEATURE ENGINEERING NAMED ENTITY RECOGNITION

How Document Pre-processing affects Keyphrase Extraction Performance

WS 2016 boudinfl/semeval-2010-pre

The SemEval-2010 benchmark dataset has brought renewed attention to the task of automatic keyphrase extraction.

HeLI, a Word-Based Backoff Method for Language Identification

WS 2016 tosaja/HeLI

The shared task comprised of a total of 8 tracks, of which we participated in 7.

LANGUAGE IDENTIFICATION