Papers Relation Classification

Hands-on Learning to Search for Structured Prediction

Classifying Relations by Ranking with Convolutional Neural Networks

Relation classification is an important semantic processing task for which state-ofthe-art systems still rely on costly handcrafted features. In this work we tackle the relation classification task using a convolutional …

Task-Oriented Learning of Word Embeddings for Semantic Relation Classification

We present a novel learning method for word embeddings designed for relation classification. Our word embeddings are trained by predicting words between noun pairs using lexical relation-specific features on a large unla…

Errata: Distant Supervision for Relation Extraction with Matrix Completion

The essence of distantly supervised relation extraction is that it is an incomplete multi-label classification problem with sparse and noisy features. To tackle the sparsity and noise challenges, we propose solving the c…

A Constituent-Based Approach to Argument Labeling with Joint Inference in Discourse Parsing

Exploiting Timegraphs in Temporal Relation Classification

Cross-lingual Discourse Relation Analysis: A corpus study and a semi-supervised classification system

Inducing Latent Semantic Relations for Structured Distributional Semantics

Ensemble-Based Medical Relation Classification

Relation Classification via Convolutional Deep Neural Network

Bilingual Active Learning for Relation Classification via Pseudo Parallel Corpora

Distant Supervision for Relation Extraction with Matrix Completion

Combining Word Patterns and Discourse Markers for Paradigmatic Relation Classification

Classifying Temporal Relations with Simple Features

Distributional Lexical Entailment by Topic Coherence

Discovering Implicit Discourse Relations Through Brown Cluster Pair Representation and Coreference Patterns

Experiments with Three Approaches to Recognizing Lexical Entailment

Inference in natural language often involves recognizing lexical entailment (RLE); that is, identifying whether one word entails another. For example, "buy" entails "own". Two general strategies for RLE have been propose…

Dense Event Ordering with a Multi-Pass Architecture

The past 10 years of event ordering research has focused on learning partial orderings over document events and time expressions. The most popular corpus, the TimeBank, contains a small subset of the possible ordering gr…

Simple Customization of Recursive Neural Networks for Semantic Relation Classification

A Semantic-Based Approach to Noun-Noun Compound Interpretation