• Publications
  • Influence
Learning to Rationalize for Nonmonotonic Reasoning with Distant Supervision
TLDR
This paper investigates multiple ways to automatically generate rationales using pre-trained language models, neural knowledge models, and distant supervision from related tasks, and trains generative models capable of composing explanatory rationales for unseen instances.
Modeling Protagonist Emotions for Emotion-Aware Storytelling
TLDR
This paper designs methods that generate stories that adhere to given story titles and desired emotion arcs for the protagonist, and includes Emotion Supervision and two Emotion-Reinforced (EmoRL) models.
ParsiNLU: A Suite of Language Understanding Challenges for Persian
TLDR
This work introduces ParsiNLU, the first benchmark in Persian language that includes a range of language understanding tasks—reading comprehension, textual entailment, and so on, and presents the first results on state-of-the-art monolingual and multilingual pre-trained language models on this benchmark and compares them with human performance.
Cue Me In: Content-Inducing Approaches to Interactive Story Generation
TLDR
This work focuses on the task of interactive story generation, where the user provides the model mid-level sentence abstractions in the form of cue phrases during the generation process, and presents two content-inducing approaches to effectively incorporate this additional information.
"Let Your Characters Tell Their Story": A Dataset for Character-Centric Narrative Understanding
TLDR
LiSCU is presented – a new dataset of literary pieces and their summaries paired with descriptions of characters that appear in them and two new tasks on LiSCU : Character Identification and Character Description Generation are introduced.
Optimal energy management of hybrid CCHP and PV in a residential building
Energy crisis along with environmental concerns are some principal motivations for replacing centralized power systems with Distributed Energy Resources (DERs). In this respect, Combined Cooling,
Development of a thermal and electrical energy management in residential building micro-grid
Global warming and pressing concern about CO2 emission along with increasing fuel and oil cost have brought about great challenges for energy companies and homeowners. In this regard, a potential
Reformulating Sentence Ordering as Conditional Text Generation
TLDR
Reorder-Bart (RE-BART), a sentence ordering framework which leverages a pre-trained transformer-based model to identify a coherent order for a given set of shuffled sentences, is presented.
Uncovering Implicit Gender Bias in Narratives through Commonsense Inference
TLDR
This work infer and analyze the protagonist’s motivations, attributes, mental states, and implications on others, and uses a commonsense reasoning engine to uncover implicit biases associated with the protagonist in model-generated stories.
...
...