paper-with-me

홈 › Papers

Event-Related Features in Feedforward Neural Networks Contribute to Identifying Causal Relations in Discourse

2017-04-01 · WS 2017 4 · Edoardo Maria Ponti, Anna Korhonen

Causal relations play a key role in information extraction and reasoning. Most of the times, their expression is ambiguous or implicit, i.e. without signals in the text. This makes their identification challenging. We aim to improve their identification by implementing a Feedforward Neural Network with a novel set of features for this task. In particular, these are based on the position of event mentions and the semantics of events and participants. The resulting classifier outperforms strong baselines on two datasets (the Penn Discourse Treebank and the CSTNews corpus) annotated with different schemes and containing examples in two languages, English and Portuguese. This result demonstrates the importance of events for identifying discourse relations.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

PositionQuestion AnsweringText Summarization

Similar Papers 제목 키워드 기반

Automatic Classification of OSA related Snoring Signals from Nocturnal Audio Recordings

2021-02-25 · Arun Sebastian, Peter A. Cistulli, Gary Cohen, Philip de Chazal

In this study, the development of an automatic algorithm is presented to classify the nocturnal audio recording of an obstructive sleep apnoea (OSA) patient as OSA related snore, simple snore and other sounds. Recent stu…

feature selectionGeneral Classification

Cross-context News Corpus for Protest Events related Knowledge Base Construction

2020-08-01 · AKBC 2020 6 · Ali Hürriyetoğlu, Erdem Yörük, Deniz Yüret, Osman Mutlu 외

We describe a gold standard corpus of protest events that comprise of various local and international sources from various countries in English. The corpus contains document, sentence, and token level annotations. This c…

Active LearningArticlesEvent ExtractionKnowledge Base Construction+3

Can We Locate and Prevent Stereotypes in LLMs?

2026-03-26 · Alex D'Souza arxiv

Stereotypes in large language models (LLMs) can perpetuate harmful societal biases. Despite the widespread use of models, little is known about where these biases reside in the neural network. This study investigates the…

Shortcut Solutions Learned by Transformers Impair Continual Compositional Reasoning

2026-05-06 · William T. Redman, Erik C. Johnson, Brian Robinson arxiv

Identifying and exploiting common features across domains is at the heart of the human ability to make analogies, and is believed to be crucial for the ability to continually learn. To do this successfully, general and f…

Continual Learning

Improving Classification of Twitter Behavior During Hurricane Events

2018-07-01 · WS 2018 7 · Kevin Stowe, Jennings Anderson, Martha Palmer, Leysia Palen 외

A large amount of social media data is generated during natural disasters, and identifying the relevant portions of this data is critical for researchers attempting to understand human behavior, the effects of informatio…

BIG-bench Machine LearningClassificationGeneral Classification