Search Results for author:
Found 13 papers, 7 papers with code
Application Specific Compression of Deep Learning Models
Our method, Application Specific Compression (ASC), identifies and prunes components of the large Deep Learning model that are redundant specifically for the given target application.
Compressed models are NOT miniature versions of large models
Compressed models are assumed to be miniature versions of corresponding large neural models.
Effect of dimensionality change on the bias of word embeddings
First, there is a significant variation in the bias of word embeddings with the dimensionality change.
Noise in Relation Classification Dataset TACRED: Characterization and Reduction
Towards the first objective, we analyze predictions and performance of state-of-the-art (SOTA) models to identify the root cause of noise in the dataset.
Budget Sensitive Reannotation of Noisy Relation Classification Data Using Label Hierarchy
The immediate follow-up problem is: Given a specific reannotation budget, which subset of the data should we reannotate?
Are Word Embedding Methods Stable and Should We Care About It?
A representation learning method is considered stable if it consistently generates similar representation of the given data across multiple runs.
Taxonomical hierarchy of canonicalized relations from multiple Knowledge Bases
Further, to address the second question, we canonicalize, filter, and combine the identified relations from the three resources to construct a taxonomical hierarchy.
Decoding the Style and Bias of Song Lyrics
We focus on two aspects: style and biases of song lyrics.
Fine-grained Entity Recognition with Reduced False Negatives and Large Type Coverage
Fine-grained Entity Recognition (FgER) is the task of detecting and classifying entity mentions to a large set of types spanning diverse domains such as biomedical, finance and sports.
Collective Learning From Diverse Datasets for Entity Typing in the Wild
The CLF first creates a unified hierarchical label set (UHLS) and a label mapping by aggregating label information from all available datasets.
Deep Learning for Detecting Cyberbullying Across Multiple Social Media Platforms
We show that deep learning based models can overcome all three bottlenecks.
Fine-Grained Entity Type Classification by Jointly Learning Representations and Label Embeddings
Fine-grained entity type classification (FETC) is the task of classifying an entity mention to a broad set of types.
Faster K-Means Cluster Estimation
We propose a fast heuristic to overcome this bottleneck with only marginal increase in MSE.
