-
Neural keyphrase generation via reinforcement learning with adaptive rewards
A dataset for neural keyphrase generation. -
Select, extract and generate: Neural keyphrase generation with layer-wise cov...
A dataset for neural keyphrase generation with layer-wise coverage attention. -
KPEVAL: Towards Fine-Grained Semantic-Based Keyphrase Evaluation
A comprehensive evaluation framework for keyphrase systems, including reference agreement, faithfulness, diversity, and utility. -
DisCo-CLIP: A Distributed Contrastive Loss for Memory Efficient CLIP Training
We propose DisCo-CLIP, a distributed memory-efficient CLIP training approach, to reduce the memory consump- tion of contrastive loss when training contrastive learning models. -
Customer Service Calls Dataset
A dataset consisting of ten years of customer service calls to a fleet truck company. -
Ubuntu Dialogue Corpus
The Ubuntu Dialogue Corpus is the largest freely available multi-turn based dialogue corpus which consists of almost one million two-way conversations extracted from the Ubuntu... -
Visual Genome
The Visual Genome dataset is a large-scale visual question answering dataset, containing 1.5 million images, each with 15-30 annotated entities, attributes, and relationships. -
Interpreting Learned Feedback Patterns in Large Language Models
The dataset used in the paper is not explicitly described, but it is mentioned that the authors used a condensed representation of LLM activations obtained from sparse... -
WikiTableQuestions
Semantic parsing maps a user-issued natural language (NL) utterance to a machine-executable meaning representation (MR), such as λ−calculus (Zettlemoyer and Collins, 2005), SQL... -
ToolWriter: Generating query-specific tools for tabular question answering
Tabular question answering (TQA) presents a challenging setting for neural systems by requiring joint reasoning of natural language with large amounts of semi-structured data. -
Penn Treebank (PTB) dataset
The Penn Treebank (PTB) dataset is used for word ordering task. The dataset is used to evaluate the performance of different models for word ordering. -
A CHEAPER AND BETTER DIFFUSION LANGUAGE MODEL WITH SOFT-MASKED NOISE
Diffusion models that are based on iterative denoising have been recently proposed and leveraged in various generation tasks like image generation. -
PAUSE: Positive and Annealed Unlabeled Sentence Embedding
PAUSE is a generic and end-to-end sentence embedding approach that exploits the labels and explores the unlabeled sentence pairs simultaneously.
