• Publications
  • Influence
Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering
TLDR
A new kind of question answering dataset, OpenBookQA, modeled after open book exams for assessing human understanding of a subject, and oracle experiments designed to circumvent the knowledge retrieval bottleneck demonstrate the value of both the open book and additional facts. Expand
Knowledgeable Reader: Enhancing Cloze-Style Reading Comprehension with External Commonsense Knowledge
TLDR
A neural reading comprehension model that integrates external commonsense knowledge, encoded as a key-value memory, in a cloze-style setting that improves results over a very strong baseline on a hard Common Nouns dataset, making it a strong competitor of much more complex models. Expand
The dark side of news community forums: opinion manipulation trolls
TLDR
The idea that a user who is called a troll by several people is likely to be one further demonstrates the utility of this idea for detecting accused and paid opinion manipulation trolls and their comments as well as for predicting the credibility of comments in news community forums. Expand
Finding Opinion Manipulation Trolls in News Community Forums
TLDR
This work assumes that a user who is called a troll by several people is likely to be one, and shows that a classifier can be trained to distinguish a likely troll from a non-troll with very high accuracy, 82‐95%, thanks to the rich feature set. Expand
Hunting for Troll Comments in News Community Forums
TLDR
In this work, two classifiers are built that can distinguish a post by such a paid troll from one by a non-troll with 81-82% accuracy; the same classifier achieves 81- 82% accuracy on so called mentioned troll vs. non-Troll posts. Expand
SUper Team at SemEval-2016 Task 3: Building a Feature-Rich System for Community Question Answering
We present the system we built for participating in SemEval-2016 Task 3 on Community Question Answering. We achieved the best results on subtask C, and strong results on subtasks A and B, byExpand
Discourse Relation Sense Classification Using Cross-argument Semantic Similarity Based on Word Embeddings
TLDR
After the official submission of the CoNLL 2016 Shared Task’s supplementary task on Discourse Relation Sense Classification, the model for Non-Explicit relations was enriched by including similarities of explicit connectives with the relation arguments, and part of speech similarities based on modal verbs. Expand
Discourse-Aware Semantic Self-Attention for Narrative Reading Comprehension
TLDR
This work uses linguistic annotations as a basis for a Discourse-Aware Semantic Self-Attention encoder that is employed for reading comprehension on narrative texts and shows that dedicating self-attention heads to intra-sentential relations and relations connecting neighboring sentences is beneficial for finding answers to questions in longer contexts. Expand
Story Cloze Ending Selection Baselines and Data Examination
TLDR
These experiments show that a model using representation features based on average word embedding vectors over the given story words and the candidate ending sentences words, joint with similarity features between the story and candidate ending representations performed better than the neural models. Expand
SemanticZ at SemEval-2016 Task 3: Ranking Relevant Answers in Community Question Answering Using Semantic Similarity Based on Fine-tuned Word Embeddings
We describe our system for finding good answers in a community forum, as defined in SemEval-2016, ask 3 on Community Question Answering. Our approach relies on several semantic similarity featuresExpand
...
1
2
...