Search Results for author: Sujith Ravi

Found 35 papers, 10 papers with code

SoDA: On-device Conversational Slot Extraction

no code implementations SIGDIAL (ACL) 2021 Sujith Ravi, Zornitsa Kozareva

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.

Fixed Support Tree-Sliced Wasserstein Barycenter

no code implementations8 Sep 2021 Yuki Takezawa, Ryoma Sato, Zornitsa Kozareva, Sujith Ravi, Makoto Yamada

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.

Natural Language Processing

Efficient Retrieval Optimized Multi-task Learning

no code implementations20 Apr 2021 Hengxin Fun, Sunil Gandhi, Sujith Ravi

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.

Multi-Task Learning Open-Domain Question Answering

Transductive Learning for Abstractive News Summarization

no code implementations17 Apr 2021 Arthur Bražinskas, Mengwen Liu, Ramesh Nallapati, Sujith Ravi, Markus Dreyer

This applies to scenarios such as a news publisher training a summarizer on dated news and summarizing incoming recent news.

Abstractive Text Summarization News Summarization

GoEmotions: A Dataset of Fine-Grained Emotions

7 code implementations ACL 2020 Dorottya Demszky, Dana Movshovitz-Attias, Jeongwoo Ko, Alan Cowen, Gaurav Nemade, Sujith Ravi

Understanding emotion expressed in language has a wide range of applications, from building empathetic chatbots to detecting harmful online behavior.

Emotion Classification Transfer Learning

ProFormer: Towards On-Device LSH Projection Based Transformers

no code implementations EACL 2021 Chinnadhurai Sankar, Sujith Ravi, Zornitsa Kozareva

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.

General Classification Text Classification

Environment-agnostic Multitask Learning for Natural Language Grounded Navigation

1 code implementation ECCV 2020 Xin Eric Wang, Vihan Jain, Eugene Ie, William Yang Wang, Zornitsa Kozareva, Sujith Ravi

Recent research efforts enable study for natural language grounded navigation in photo-realistic environments, e. g., following natural language instructions or dialog.

Vision-Language Navigation

Graph Agreement Models for Semi-Supervised Learning

1 code implementation NeurIPS 2019 Otilia Stretcu, Krishnamurthy Viswanathan, Dana Movshovitz-Attias, Emmanouil Platanios, Sujith Ravi, Andrew Tomkins

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.

Classification General Classification +2

Generalized Clustering by Learning to Optimize Expected Normalized Cuts

no code implementations16 Oct 2019 Azade Nazi, Will Hang, Anna Goldie, Sujith Ravi, Azalia Mirhoseini

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

no code implementations25 Sep 2019 Xin Wang, Vihan Jain, Eugene Ie, William Wang, Zornitsa Kozareva, Sujith Ravi

Recent research efforts enable study for natural language grounded navigation in photo-realistic environments, e. g., following natural language instructions or dialog.

Vision-Language Navigation

On-Device Text Representations Robust To Misspellings via Projections

no code implementations EACL 2021 Chinnadhurai Sankar, Sujith Ravi, Zornitsa Kozareva

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.

Text Classification Word Embeddings

A2N: Attending to Neighbors for Knowledge Graph Inference

no code implementations ACL 2019 Trapit Bansal, Da-Cheng Juan, Sujith Ravi, Andrew McCallum

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.

Knowledge Graph Completion Link Prediction

Transferable Neural Projection Representations

2 code implementations NAACL 2019 Chinnadhurai Sankar, Sujith Ravi, Zornitsa Kozareva

Neural word representations are at the core of many state-of-the-art natural language processing models.

Natural Language Processing

GAP: Generalizable Approximate Graph Partitioning Framework

1 code implementation2 Mar 2019 Azade Nazi, Will Hang, Anna Goldie, Sujith Ravi, Azalia Mirhoseini

Graph partitioning is the problem of dividing the nodes of a graph into balanced partitions while minimizing the edge cut across the partitions.

graph partitioning

Graph-RISE: Graph-Regularized Image Semantic Embedding

1 code implementation14 Feb 2019 Da-Cheng Juan, Chun-Ta Lu, Zhen Li, Futang Peng, Aleksei Timofeev, Yi-Ting Chen, Yaxi Gao, Tom Duerig, Andrew Tomkins, Sujith Ravi

Learning image representations to capture fine-grained semantics has been a challenging and important task enabling many applications such as image search and clustering.

General Classification Graph Learning +2

ProjectionNet: Learning Efficient On-Device Deep Networks Using Neural Projections

no code implementations2 Aug 2017 Sujith Ravi

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.

Image Classification Text Classification

Neural Graph Machines: Learning Neural Networks Using Graphs

no code implementations14 Mar 2017 Thang D. Bui, Sujith Ravi, Vivek Ramavajjala

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.

Document Classification General Classification +2

Semantic Video Trailers

no code implementations7 Sep 2016 Harrie Oosterhuis, Sujith Ravi, Michael Bendersky

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.

Video Summarization

Smart Reply: Automated Response Suggestion for Email

no code implementations15 Jun 2016 Anjuli Kannan, Karol Kurach, Sujith Ravi, Tobias Kaufmann, Andrew Tomkins, Balint Miklos, Greg Corrado, Laszlo Lukacs, Marina Ganea, Peter Young, Vivek Ramavajjala

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

no code implementations NAACL 2016 Justine Zhang, Ravi Kumar, Sujith Ravi, Cristian Danescu-Niculescu-Mizil

Public debates are a common platform for presenting and juxtaposing diverging views on important issues.

Large Scale Distributed Semi-Supervised Learning Using Streaming Approximation

no code implementations6 Dec 2015 Sujith Ravi, Qiming Diao

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 $m$.

graph construction

Parallel Algorithms for Unsupervised Tagging

no code implementations TACL 2014 Sujith Ravi, Sergei Vassilivitskii, Vibhor Rastogi

We propose a new method for unsupervised tagging that finds minimal models which are then further improved by Expectation Maximization training.

Part-Of-Speech Tagging

Cannot find the paper you are looking for? You can Submit a new open access paper.