WS 2017

Readers vs. Writers vs. Texts: Coping with Different Perspectives of Text Understanding in Emotion Annotation

WS 2017 JULIELab/EmoBank

We here examine how different perspectives of understanding written discourse, like the reader{'}s, the writer{'}s or the text{'}s point of view, affect the quality of emotion annotations.

READING COMPREHENSION

A Consolidated Open Knowledge Representation for Multiple Texts

WS 2017 vered1986/OKR

We propose to move from Open Information Extraction (OIE) ahead to Open Knowledge Representation (OKR), aiming to represent information conveyed jointly in a set of texts in an open text-based manner.

OPEN INFORMATION EXTRACTION

Character-based Neural Embeddings for Tweet Clustering

WS 2017 vendi12/tweet2vec_clustering

In this paper we show how the performance of tweet clustering can be improved by leveraging character-based neural networks.

Finding Good Conversations Online: The Yahoo News Annotated Comments Corpus

WS 2017 cnap/ynacc

This work presents a dataset and annotation scheme for the new task of identifying {``}good{''} conversations that occur online, which we call ERICs: Engaging, Respectful, and/or Informative Conversations.

The BECauSE Corpus 2.0: Annotating Causality and Overlapping Relations

WS 2017 duncanka/BECauSE

Language of cause and effect captures an essential component of the semantics of a text.

DECISION MAKING

LSDSem 2017: Exploring Data Generation Methods for the Story Cloze Test

WS 2017 UKPLab/lsdsem2017-story-cloze

The Story Cloze test is a recent effort in providing a common test scenario for text understanding systems.

Semi-Automated Resolution of Inconsistency for a Harmonized Multiword Expression and Dependency Parse Annotation

WS 2017 eltimster/HAMSTER

This paper presents a methodology for identifying and resolving various kinds of inconsistency in the context of merging dependency and multiword expression (MWE) annotations, to generate a dependency treebank with comprehensive MWE annotations.

Automated WordNet Construction Using Word Embeddings

WS 2017 mkhodak/pawn

To evaluate our method we construct two 600-word testsets for word-to-synset matching in French and Russian using native speakers and evaluate the performance of our method along with several other recent approaches.

INFORMATION RETRIEVAL MACHINE TRANSLATION WORD EMBEDDINGS WORD SENSE INDUCTION