• Publications
  • Influence
SenticNet 3: A Common and Common-Sense Knowledge Base for Cognition-Driven Sentiment Analysis
TLDR
SenticNet 3 models nuanced semantics and sentics (that is, the conceptual and affective information associated with multi-word natural language expressions), representing information with a symbolic opacity of an intermediate nature between that of neural networks. Expand
  • 310
  • 37
  • PDF
Gated-Attention Architectures for Task-Oriented Language Grounding
TLDR
We propose an end-to-end neural architecture for task-oriented language grounding in 3D environments which assumes no prior linguistic or perceptual knowledge and requires only raw pixels from the environment and the natural language instruction as input. Expand
  • 140
  • 26
  • PDF
Generating Questions and Multiple-Choice Answers using Semantic Analysis of Texts
TLDR
This work is aimed at engaging language learners by generating multiple-choice questions which utilize specific inference steps over multiple sentences, namely coreference resolution and paraphrase detection, requiring more semantic understanding of text. Expand
  • 31
  • 6
  • PDF
A graph-based approach to commonsense concept extraction and semantic similarity detection
TLDR
We propose an approach for effective multi-word commonsense expression extraction from unrestricted English text, in addition to a semantic similarity detection technique allowing additional matches to be found for specific concepts not already present in knowledge bases. Expand
  • 72
  • 2
  • PDF
Simple and Effective Semi-Supervised Question Answering
TLDR
We present a semi-supervised QA system where the end user specifies a set of base documents and only a few labelled examples, and find it to be highly effective with very little labeled data. Expand
  • 22
  • 2
  • PDF
GECKA: Game Engine for Commonsense Knowledge Acquisition
TLDR
We propose a new GWAP concept, which we call GECKA (serious game engine for common-sense knowledge acquisition), that aims to overcome the main drawbacks of traditional data-collecting games by empowering users to create their own GWAPs. Expand
  • 16
  • 1
  • PDF
StructSum: Incorporating Latent and Explicit Sentence Dependencies for Single Document Summarization
TLDR
We use structure-aware encoders to induce latent sentence relations, and inject explicit coreferring mention graph across sentences to incorporate explicit structure. Expand
  • 3
  • 1
  • PDF
Commonsense-based topic modeling
TLDR
Topic modeling is a technique used for discovering the abstract 'topics' that occur in a collection of documents, which is useful for text auto-categorization and opinion mining. Expand
  • 22
  • PDF
What-if I ask you to explain: Explaining the effects of perturbations in procedural text
TLDR
We address the task of explaining the effects of perturbations in procedural text, an important test of process comprehension, by modeling the explanation task as a multitask learning problem. Expand
  • 2
  • PDF