Search Results for author:
Found 13 papers, 4 papers with code
IrEne-viz: Visualizing Energy Consumption of Transformer Models
IrEne is an energy prediction system that accurately predicts the interpretable inference energy consumption of a wide range of Transformer-based NLP models.
SOCIALITE-LLAMA: An Instruction-Tuned Model for Social Scientific Tasks
Social science NLP tasks, such as emotion or humor detection, are required to capture the semantics along with the implicit pragmatics from text, often with limited amounts of training data.
One Size Does Not Fit All: Customizing Open-Domain Procedures
Our approach is to test several simple multi-LLM-agent architectures for customization, as well as an end-to-end LLM, using a new evaluation set, called CustomPlans, of over 200 WikiHow procedures each with a customization need.
Evaluating Paraphrastic Robustness in Textual Entailment Models
We present PaRTE, a collection of 1, 126 pairs of Recognizing Textual Entailment (RTE) examples to evaluate whether models are robust to paraphrasing.
Systematic Evaluation of GPT-3 for Zero-Shot Personality Estimation
Very large language models (LLMs) perform extremely well on a spectrum of NLP tasks in a zero-shot setting.
TellMeWhy: A Dataset for Answering Why-Questions in Narratives
They are especially worse on questions whose answers are external to the narrative, thus providing a challenge for future QA and narrative understanding research.
IrEne: Interpretable Energy Prediction for Transformers
We present IrEne, an interpretable and extensible energy prediction system that accurately predicts the inference energy consumption of a wide range of Transformer-based NLP models.
Temporal Reasoning in Natural Language Inference
We introduce five new natural language inference (NLI) datasets focused on temporal reasoning.
Johns Hopkins University Submission for WMT News Translation Task
We describe the work of Johns Hopkins University for the shared task of news translation organized by the Fourth Conference on Machine Translation (2019).
De-Mixing Sentiment from Code-Mixed Text
The Collective Encoder captures the overall sentiment of the sentence, while the Specific Encoder utilizes an attention mechanism in order to focus on individual sentiment-bearing sub-words.
SWDE : A Sub-Word And Document Embedding Based Engine for Clickbait Detection
We generate sub-word level embeddings of the title using Convolutional Neural Networks and use them to train a bidirectional LSTM architecture.
Identifying Clickbait: A Multi-Strategy Approach Using Neural Networks
The application of neural networks for this task has only been explored partially.
