Search Results for author:
Found 20 papers, 7 papers with code
Active Learning for BERT: An Empirical Study
Here, we present a large-scale empirical study on active learning techniques for BERT-based classification, addressing a diverse set of AL strategies and datasets.
Conversational Prompt Engineering
We propose Conversational Prompt Engineering (CPE), a user-friendly tool that helps users create personalized prompts for their specific tasks.
Stay Tuned: An Empirical Study of the Impact of Hyperparameters on LLM Tuning in Real-World Applications
Here, we provide recommended HP configurations for practical use-cases that represent a better starting point for practitioners, when considering two SOTA LLMs and two commonly used tuning methods.
Unitxt: Flexible, Shareable and Reusable Data Preparation and Evaluation for Generative AI
In the dynamic landscape of generative NLP, traditional text processing pipelines limit research flexibility and reproducibility, as they are tailored to specific dataset, task, and model combinations.
Knowledge is a Region in Weight Space for Fine-tuned Language Models
Notably, we show that language models that have been finetuned on the same dataset form a tight cluster in the weight space, while models finetuned on different datasets from the same underlying task form a looser cluster.
ColD Fusion: Collaborative Descent for Distributed Multitask Finetuning
We propose a new paradigm to continually evolve pretrained models, denoted ColD Fusion.
Where to start? Analyzing the potential value of intermediate models
Such a model, finetuned on some source dataset, may provide a better starting point for a new finetuning process on a desired target dataset.
Label Sleuth: From Unlabeled Text to a Classifier in a Few Hours
Text classification can be useful in many real-world scenarios, saving a lot of time for end users.
Benchmark Data and Evaluation Framework for Intent Discovery Around COVID-19 Vaccine Hesitancy
We use this framework to report baseline intent discovery results over VIRADialogs, that highlight the difficulty of this task.
VIRATrustData: A Trust-Annotated Corpus of Human-Chatbot Conversations About COVID-19 Vaccines
Public trust in medical information is crucial for successful application of public health policies such as vaccine uptake.
Multi-Domain Targeted Sentiment Analysis
Our results and analysis show that our approach is a promising step towards a practical domain-robust TSA system.
Fusing finetuned models for better pretraining
We also show that fusing is often better than intertraining.
Overview of the 2021 Key Point Analysis Shared Task
We describe the 2021 Key Point Analysis (KPA-2021) shared task on key point analysis that we organized as a part of the 8th Workshop on Argument Mining (ArgMining 2021) at EMNLP 2021.
Project Debater APIs: Decomposing the AI Grand Challenge
Engaging in a live debate requires a diverse set of skills, and Project Debater has been developed accordingly as a collection of components, each designed to perform a specific subtask.
YASO: A Targeted Sentiment Analysis Evaluation Dataset for Open-Domain Reviews
Current TSA evaluation in a cross-domain setup is restricted to the small set of review domains available in existing datasets.
Ranked #1 on
Aspect Extraction
on YASO - YELP
Financial Event Extraction Using Wikipedia-Based Weak Supervision
Extraction of financial and economic events from text has previously been done mostly using rule-based methods, with more recent works employing machine learning techniques.
Fast End-to-End Wikification
Wikification of large corpora is beneficial for various NLP applications.
From Surrogacy to Adoption; From Bitcoin to Cryptocurrency: Debate Topic Expansion
When debating a controversial topic, it is often desirable to expand the boundaries of discussion.
Learning to combine Grammatical Error Corrections
We also present a spellchecker created for this task which outperforms standard spellcheckers tested on the task of spellchecking.
Ranked #10 on
Grammatical Error Correction
on BEA-2019 (test)
