Search Results for author:
Found 36 papers, 11 papers with code
SoDA: On-device Conversational Slot Extraction
We propose a novel on-device neural sequence labeling model which uses embedding-free projections and character information to construct compact word representations to learn a sequence model using a combination of bidirectional LSTM with self-attention and CRF.
Approximating 1-Wasserstein Distance with Trees
In this paper, we aim to approximate the 1-Wasserstein distance by the tree-Wasserstein distance (TWD), where TWD is a 1-Wasserstein distance with tree-based embedding and can be computed in linear time with respect to the number of nodes on a tree.
Fixed Support Tree-Sliced Wasserstein Barycenter
By contrast, the Wasserstein distance on a tree, called the tree-Wasserstein distance, can be computed in linear time and allows for the fast comparison of a large number of distributions.
Evaluating the Tradeoff Between Abstractiveness and Factuality in Abstractive Summarization
Neural models for abstractive summarization tend to generate output that is fluent and well-formed but lacks semantic faithfulness, or factuality, with respect to the input documents.
Efficiently Summarizing Text and Graph Encodings of Multi-Document Clusters
We also show improvements in a transfer-only setup on the DUC-2004 dataset.
Efficient Retrieval Optimized Multi-task Learning
Our ROM approach presents a unified and generalizable framework that enables scaling efficiently to multiple tasks, varying levels of supervision, and optimization choices such as different learning schedules without changing the model architecture.
Transductive Learning for Abstractive News Summarization
This applies to scenarios such as a news publisher training a summarizer on dated news and summarizing incoming recent news.
GoEmotions: A Dataset of Fine-Grained Emotions
Understanding emotion expressed in language has a wide range of applications, from building empathetic chatbots to detecting harmful online behavior.
Low-Dimensional Hyperbolic Knowledge Graph Embeddings
However, existing hyperbolic embedding methods do not account for the rich logical patterns in KGs.
Ranked #5 on
Link Prediction
on YAGO3-10
ProFormer: Towards On-Device LSH Projection Based Transformers
At the heart of text based neural models lay word representations, which are powerful but occupy a lot of memory making it challenging to deploy to devices with memory constraints such as mobile phones, watches and IoT.
Environment-agnostic Multitask Learning for Natural Language Grounded Navigation
Recent research efforts enable study for natural language grounded navigation in photo-realistic environments, e. g., following natural language instructions or dialog.
Graph Agreement Models for Semi-Supervised Learning
To address this, we propose Graph Agreement Models (GAM), which introduces an auxiliary model that predicts the probability of two nodes sharing the same label as a learned function of their features.
Learning from a Teacher using Unlabeled Data
Knowledge distillation is a widely used technique for model compression.
PRADO: Projection Attention Networks for Document Classification On-Device
We evaluate our approach on multiple large document text classification tasks.
ProSeqo: Projection Sequence Networks for On-Device Text Classification
Our model ProSeqo uses dynamic recurrent projections without the need to store or look up any pre-trained embeddings.
Generalized Clustering by Learning to Optimize Expected Normalized Cuts
We introduce a novel end-to-end approach for learning to cluster in the absence of labeled examples.
Generalized Natural Language Grounded Navigation via Environment-agnostic Multitask Learning
Recent research efforts enable study for natural language grounded navigation in photo-realistic environments, e. g., following natural language instructions or dialog.
On-Device Text Representations Robust To Misspellings via Projections
Recently, there has been a strong interest in developing natural language applications that live on personal devices such as mobile phones, watches and IoT with the objective to preserve user privacy and have low memory.
Deep Reinforcement Learning For Modeling Chit-Chat Dialog With Discrete Attributes
Open domain dialog systems face the challenge of being repetitive and producing generic responses.
On-device Structured and Context Partitioned Projection Networks
We show that this results in accelerated inference and performance improvements.
A2N: Attending to Neighbors for Knowledge Graph Inference
State-of-the-art models for knowledge graph completion aim at learning a fixed embedding representation of entities in a multi-relational graph which can generalize to infer unseen entity relationships at test time.
Transferable Neural Projection Representations
Neural word representations are at the core of many state-of-the-art natural language processing models.
GAP: Generalizable Approximate Graph Partitioning Framework
Graph partitioning is the problem of dividing the nodes of a graph into balanced partitions while minimizing the edge cut across the partitions.
Ranked #1 on
graph partitioning
on custom
Graph-RISE: Graph-Regularized Image Semantic Embedding
Learning image representations to capture fine-grained semantics has been a challenging and important task enabling many applications such as image search and clustering.
Ranked #11 on
Image Classification
on iNaturalist
Self-Governing Neural Networks for On-Device Short Text Classification
Deep neural networks reach state-of-the-art performance for wide range of natural language processing, computer vision and speech applications.
ProjectionNet: Learning Efficient On-Device Deep Networks Using Neural Projections
At its core lies a novel objective that jointly trains using two different types of networks--a full trainer neural network (using existing architectures like Feed-forward NNs or LSTM RNNs) combined with a simpler "projection" network that leverages random projections to transform inputs or intermediate representations into bits.
Ranked #61 on
Image Classification
on MNIST
Neural Graph Machines: Learning Neural Networks Using Graphs
In this work, we propose a training framework with a graph-regularised objective, namely "Neural Graph Machines", that can combine the power of neural networks and label propagation.
Semantic Video Trailers
Our approach effectively captures the multimodal semantics of queries and videos using state-of-the-art deep neural networks and creates a summary that is both semantically coherent and visually attractive.
Smart Reply: Automated Response Suggestion for Email
In this paper we propose and investigate a novel end-to-end method for automatically generating short email responses, called Smart Reply.
Conversational flow in Oxford-style debates
Public debates are a common platform for presenting and juxtaposing diverging views on important issues.
Large Scale Distributed Semi-Supervised Learning Using Streaming Approximation
Traditional graph-based semi-supervised learning (SSL) approaches, even though widely applied, are not suited for massive data and large label scenarios since they scale linearly with the number of edges $|E|$ and distinct labels $m$.
Parallel Algorithms for Unsupervised Tagging
We propose a new method for unsupervised tagging that finds minimal models which are then further improved by Expectation Maximization training.
FastEx: Hash Clustering with Exponential Families
Clustering is a key component in data analysis toolbox.
