• Publications
  • Influence
A dataset for Movie Description
TLDR
Comparing ADs to scripts, it is found that ADs are far more visual and describe precisely what is shown rather than what should happen according to the scripts created prior to movie production. Expand
Movie Description
TLDR
A novel dataset which contains transcribed ADs, which are temporally aligned to full length movies are proposed, which find that ADs are more visual and describe precisely what is shown rather than what should happen according to the scripts created prior to movie production. Expand
Tracking State Changes in Procedural Text: a Challenge Dataset and Models for Process Paragraph Comprehension
TLDR
A new dataset and models for comprehending paragraphs about processes, an important genre of text describing a dynamic world, are presented and two new neural models that exploit alternative mechanisms for state prediction are introduced, in particular using LSTM input encoding and span prediction. Expand
WebChild 2.0 : Fine-Grained Commonsense Knowledge Distillation
TLDR
This paper presents a system based on a series of algorithms to distill fine-grained disambiguated commonsense knowledge from massive amounts of text. Expand
WebChild: harvesting and organizing commonsense knowledge from the web
TLDR
A method for automatically constructing a large commonsense knowledge base, called WebChild, from Web contents, based on semi-supervised Label Propagation over graphs of noisy candidate assertions that automatically derive seeds from WordNet and by pattern matching from Web text collections. Expand
Reasoning about Actions and State Changes by Injecting Commonsense Knowledge
TLDR
This paper shows how the predicted effects of actions in the context of a paragraph can be improved in two ways: by incorporating global, commonsense constraints (e.g., a non-existent entity cannot be destroyed), and by biasing reading with preferences from large-scale corpora. Expand
Learning Language-Visual Embedding for Movie Understanding with Natural-Language
TLDR
This work studies three different joint language-visual neural network model architectures and evaluates their models on large scale LSMDC16 movie dataset for two tasks: 1) Standard Ranking for video annotation and retrieval 2) The authors' proposed movie multiple-choice test. Expand
Domain-Targeted, High Precision Knowledge Extraction
TLDR
This work has created a domain-targeted, high precision knowledge extraction pipeline, leveraging Open IE, crowdsourcing, and a novel canonical schema learning algorithm (called CASI), that produces high precisionknowledge targeted to a particular domain - in this case, elementary science. Expand
Comparison of an Automated System with Conventional Identification and Antimicrobial Susceptibility Testing
TLDR
BD Phoenix can be used as a tool to facilitate early identification and susceptibility pattern of aerobic bacteria in routine microbiology laboratories and to determine if the errors reported in AST were within the range certified by FDA. Expand
What Happened? Leveraging VerbNet to Predict the Effects of Actions in Procedural Text
TLDR
This work leverages VerbNet to build a rulebase of the preconditions and effects of actions, and uses it along with commonsense knowledge of persistence to answer questions about change in paragraphs describing processes. Expand
...
1
2
3
4
5
...