AutoAugment Is What You Need: Enhancing Rule-based Augmentation Methods in Low-resource Regimes
The paper discusses the challenges in text data augmentation due to the discrete nature of sentences. It…
SoftEDA: Rethinking Rule-Based Data Augmentation with Soft Labels
This paper introduces SoftEDA, a novel technique that applies soft labels to augmented data. Traditional Easy Data…
AttnLRP: Attention-Aware Layer-wise Relevance Propagation for Transformers
The paper discusses AttnLRP, a method that extends Layer-wise Relevance Propagation to handle attention layers in transformer…
Pretrained Generative Language Models as General Learning Frameworks for Sequence-Based Tasks
This research proposes using small pretrained foundational generative language models as a general learning framework for sequence-based…
Deep Learning-based Computational Job Market Analysis: A Survey on Skill Extraction and Classification from Job Postings
This academic article presents a comprehensive survey on the use of deep learning methodologies for skill extraction…
Efficient Models for the Detection of Hate, Abuse and Profanity
The article presents a study from IBM Research AI on creating efficient models for detecting hate, abuse,…
Merging Facts, Crafting Fallacies: Evaluating the Contradictory Nature of Aggregated Factual Claims in Long-Form Generations
The paper discusses how large language models (LLMs) generate texts that often mix factual and non-factual claims,…
Multilingual E5 Text Embeddings: A Technical Report
The technical report discusses the multilingual E5 text embedding models released by Microsoft. The models are trained…
Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulation
This article discusses a novel method for aligning large language models (LLMs) with human values, using a…
Unified Speech-Text Pretraining for Spoken Dialog Modeling
The academic article discusses the Unified Spoken Dialog Model (USDM), a framework that enables large language models…