Search Results for author:
Found 23 papers, 9 papers with code
Deferred NAM: Low-latency Top-K Context Injection via Deferred Context Encoding for Non-Streaming ASR
Contextual biasing enables speech recognizers to transcribe important phrases in the speaker's context, such as contact names, even if they are rare in, or absent from, the training data.
Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention
This work introduces an efficient method to scale Transformer-based Large Language Models (LLMs) to infinitely long inputs with bounded memory and computation.
Hierarchical Recurrent Adapters for Efficient Multi-Task Adaptation of Large Speech Models
However, their per-task parameter overhead is considered still high when the number of downstream tasks to adapt for is large.
Contextual Biasing with the Knuth-Morris-Pratt Matching Algorithm
Contextual biasing refers to the problem of biasing the automatic speech recognition (ASR) systems towards rare entities that are relevant to the specific user or application scenarios.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Improving Speech Recognition for African American English With Audio Classification
By combining the classifier output with coarse geographic information, we can select a subset of utterances from a large corpus of untranscribed short-form queries for semi-supervised learning at scale.
Diverse Distributions of Self-Supervised Tasks for Meta-Learning in NLP
Meta-learning considers the problem of learning an efficient learning process that can leverage its past experience to accurately solve new tasks.
Fast Contextual Adaptation with Neural Associative Memory for On-Device Personalized Speech Recognition
Fast contextual adaptation has shown to be effective in improving Automatic Speech Recognition (ASR) of rare words and when combined with an on-device personalized training, it can yield an even better recognition result.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Learning Associative Inference Using Fast Weight Memory
Humans can quickly associate stimuli to solve problems in novel contexts.
Ranked #1 on
Question Answering
on catbAbI LM-mode
Self-Supervised Meta-Learning for Few-Shot Natural Language Classification Tasks
We meta-train a transformer model on this distribution of tasks using a recent meta-learning framework.
Sparse Meta Networks for Sequential Adaptation and its Application to Adaptive Language Modelling
We augment a deep neural network with a layer-specific fast-weight memory.
A Locally Adaptive Interpretable Regression
Therefore, LoAIR is a step towards bridging the gap between econometrics, statistics, and machine learning by improving the predictive ability of linear regression without depreciating its interpretability.
Exploring and Predicting Transferability across NLP Tasks
We also develop task embeddings that can be used to predict the most transferable source tasks for a given target task, and we validate their effectiveness in experiments controlled for source and target data size.
Metalearned Neural Memory
We augment recurrent neural networks with an external memory mechanism that builds upon recent progress in metalearning.
Building Dynamic Knowledge Graphs from Text using Machine Reading Comprehension
We harness and extend a recently proposed machine reading comprehension (MRC) model to query for entity states, since these states are generally communicated in spans of text and MRC models perform well in extracting entity-centric spans.
Ranked #3 on
Procedural Text Understanding
on ProPara
Metalearning with Hebbian Fast Weights
We unify recent neural approaches to one-shot learning with older ideas of associative memory in a model for metalearning.
Sentence Simplification with Memory-Augmented Neural Networks
Sentence simplification aims to simplify the content and structure of complex sentences, and thus make them easier to interpret for human readers, and easier to process for downstream NLP applications.
Ranked #1 on
Text Simplification
on PWKP / WikiSmall
Rapid Adaptation with Conditionally Shifted Neurons
We describe a mechanism by which artificial neural networks can learn rapid adaptation - the ability to adapt on the fly, with little data, to new tasks - that we call conditionally shifted neurons.
Meta Networks
Neural networks have been successfully applied in applications with a large amount of labeled data.
Understanding Deep Learning Performance through an Examination of Test Set Difficulty: A Psychometric Case Study
We examine the impact of a test set question's difficulty to determine if there is a relationship between difficulty and performance.
Reasoning with Memory Augmented Neural Networks for Language Comprehension
Hypothesis testing is an important cognitive process that supports human reasoning.
Neural Tree Indexers for Text Understanding
NTI constructs a full n-ary tree by processing the input text with its node function in a bottom-up fashion.
Ranked #46 on
Natural Language Inference
on SNLI
Neural Semantic Encoders
We present a memory augmented neural network for natural language understanding: Neural Semantic Encoders.
Ranked #18 on
Question Answering
on WikiQA
