• Publications
  • Influence
From Frequency to Meaning: Vector Space Models of Semantics
TLDR
We present a survey of VSMs and their relation with the distributional hypothesis as an approach to representing some aspects of natural language semantics. Expand
  • 2,483
  • 165
  • PDF
Representing Text for Joint Embedding of Text and Knowledge Bases
TLDR
We propose a convolutional neural network model that captures the compositional structure of textual relations, and jointly optimizes entity, knowledge base, and textual relation representations. Expand
  • 331
  • 69
  • PDF
DIRT @SBT@discovery of inference rules from text
TLDR
In this paper, we propose an unsupervised method for discovering inference rules from text, such as "X is author of Y ≈ X wrote Y", "X solved Y ≋ X found a solution to Y", and "X caused Y≈ Y is triggered by X". Expand
  • 555
  • 60
  • PDF
Espresso: Leveraging Generic Patterns for Automatically Harvesting Semantic Relations
TLDR
We proposed a weakly-supervised, generalpurpose, and accurate algorithm, called Espresso, for harvesting binary semantic relations from raw text. Expand
  • 632
  • 59
  • PDF
Automatically Assessing Review Helpfulness
TLDR
In this paper, we investigate the task of automatically predicting review helpfulness using a machine learning approach. Expand
  • 463
  • 56
  • PDF
VerbOcean: Mining the Web for Fine-Grained Semantic Verb Relations
TLDR
We present a semi-automatic method for extracting fine-grained semantic relations between verbs using lexicosyntactic patterns over the Web. Expand
  • 485
  • 56
  • PDF
Discovering word senses from text
TLDR
We present a clustering algorithm called CBC (Clustering By Committee) that automatically discovers word senses by clustering words according to their distributional similarity. Expand
  • 721
  • 48
  • PDF
DIRT – Discovery of Inference Rules from Text
In this paper, we propose an unsupervised method for discovering inference rules from text, such as “X is author of Y  X wrote Y”, “X solved Y  X found a solution to Y”, and “X caused Y  Y isExpand
  • 485
  • 45
  • PDF
Discovery of inference rules for question-answering
TLDR
In this paper, we present an unsupervised algorithm for discovering inference rules from text based on an extended version of Harris’ Distributional Hypothesis. Expand
  • 598
  • 44
  • PDF
Randomized Algorithms and NLP: Using Locality Sensitive Hash Functions for High Speed Noun Clustering
TLDR
In this paper, we explore the power of randomized algorithm to address the challenge of working with very large amounts of data. Expand
  • 231
  • 26
  • PDF