research
∙
04/11/2023
Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference
We propose Conditional Adapter (CoDA), a parameter-efficient transfer le...
share
research
∙
03/17/2023
CoLT5: Faster Long-Range Transformers with Conditional Computation
Many natural language processing tasks benefit from long inputs, but pro...
research
∙
11/02/2022
Multi-Vector Retrieval as Sparse Alignment
Multi-vector retrieval models improve over single-vector dual encoders o...
research
∙
10/07/2022
Breaking BERT: Evaluating and Optimizing Sparsified Attention
Transformers allow attention between all pairs of tokens, but there is r...
research
∙
11/29/2020
Improved Semantic Role Labeling using Parameterized Neighborhood Memory Adaptation
Deep neural models achieve some of the best results for semantic role la...
research
∙
11/09/2020
CLAR: A Cross-Lingual Argument Regularizer for Semantic Role Labeling
Semantic role labeling (SRL) identifies predicate-argument structure(s) ...
research
∙
09/17/2020
Small but Mighty: New Benchmarks for Split and Rephrase
Split and Rephrase is a text simplification task of rewriting a complex ...
research
∙
08/25/2018
Efficiently Processing Workflow Provenance Queries on SPARK
In this paper, we investigate how we can leverage Spark platform for eff...
research
∙
08/14/2018
Improved Language Modeling by Decoding the Past
Highly regularized LSTMs that model the auto-regressive conditional fact...
research
∙
08/13/2018
REGMAPR - Text Matching Made Easy
We propose a simple model for textual matching problems. Starting from a...
research
∙
08/13/2018
REGMAPR - A Recipe for Textual Matching
We propose a simple model for textual matching problems. Starting from a...
research
∙
08/10/2018
Unsupervised Learning of Sentence Representations Using Sequence Consistency
Computing universal distributed representations of sentences is a fundam...
research
∙
05/18/2018
Suffix Bidirectional Long Short-Term Memory
Recurrent neural networks have become ubiquitous in computing representa...
research
∙
02/20/2018
On the scaling of polynomial features for representation matching
In many neural models, new features as polynomial functions of existing ...
research
∙
02/20/2018