Search Results for author:
Found 23 papers, 2 papers with code
Building Adaptive Acceptability Classifiers for Neural NLG
We propose a novel framework to train models to classify acceptability of responses generated by natural language generation (NLG) models, improving upon existing sentence transformation and model-based approaches.
Getting to Production with Few-shot Natural Language Generation Models
In this paper, we study the utilization of pre-trained language models to enable few-shotNatural Language Generation (NLG) in task-oriented dialog systems.
Lumos : Empowering Multimodal LLMs with Scene Text Recognition
We introduce Lumos, the first end-to-end multimodal question-answering system with text understanding capabilities.
A Posteriori Evaluation of a Physics-Constrained Neural Ordinary Differential Equations Approach Coupled with CFD Solver for Modeling Stiff Chemical Kinetics
Proof-of-concept studies are performed with physics-constrained neuralODE (PC-NODE) approach for homogeneous autoignition of hydrogen-air mixture over a range of composition and thermodynamic conditions.
Multiple Protein Profiler 1.0 (MPP): A webserver for predicting and visualizing physiochemical properties of proteins at the proteome level
Determining the physicochemical properties of a protein can reveal important insights in their structure, biological functions, stability, and interactions with other molecules.
AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model
We present Any-Modality Augmented Language Model (AnyMAL), a unified model that reasons over diverse input modality signals (i. e. text, image, video, audio, IMU motion sensor), and generates textual responses.
Ranked #7 on
Video Question Answering
on STAR Benchmark
A Framework for Combustion Chemistry Acceleration with DeepONets
A combustion chemistry acceleration scheme is developed based on deep operator networks (DeepONets).
Extended Feature Space-Based Automatic Melanoma Detection System
In recent years, the detection of melanoma using image processing techniques has become a dominant research field.
An Indian Roads Dataset for Supported and Suspended Traffic Lights Detection
Autonomous vehicles are growing rapidly, in well-developed nations like America, Europe, and China.
El Volumen Louder Por Favor: Code-switching in Task-oriented Semantic Parsing
Being able to parse code-switched (CS) utterances, such as Spanish+English or Hindi+English, is essential to democratize task-oriented semantic parsing systems for certain locales.
On the existence, uniqueness, and smoothing of solutions to the generalized SQG equations in critical Sobolev spaces
This paper studies the dissipative generalized surface quasi-geostrophic equations in a supercritical regime where the order of the dissipation is small relative to order of the velocity, and the velocities are less regular than the advected scalar by up to one order of derivative.
Analysis of PDEs 76D03, 35Q35, 35Q86, 35K59, 35B65, 34K37
Best Practices for Data-Efficient Modeling in NLG:How to Train Production-Ready Neural Models with Less Data
In this paper, we present approaches that have helped us deploy data-efficient neural solutions for NLG in conversational systems to production.
Conversational Semantic Parsing
In this paper, we propose a semantic representation for such task-oriented conversational systems that can represent concepts such as co-reference and context carryover, enabling comprehensive understanding of queries in a session.
Information Extraction of Clinical Trial Eligibility Criteria
Clinical trials predicate subject eligibility on a diversity of criteria ranging from patient demographics to food allergies.
Memory Graph Networks for Explainable Memory-grounded Question Answering
We introduce Episodic Memory QA, the task of answering personal user questions grounded on memory graph (MG), where episodic memories and related entity nodes are connected via relational edges.
Memory Grounded Conversational Reasoning
To implement such a system, we collect a new corpus of memory grounded conversations, which comprises human-to-human role-playing dialogs given synthetic memory graphs with simulated attributes.
A Tree-to-Sequence Model for Neural NLG in Task-Oriented Dialog
Generating fluent natural language responses from structured semantic representations is a critical step in task-oriented conversational systems.
Active Federated Learning
To exploit this we propose Active Federated Learning, where in each round clients are selected not uniformly at random, but with a probability conditioned on the current model and the data on the client to maximize efficiency.
Federated User Representation Learning
Furthermore, we show that user embeddings learned in FL and the centralized setting have a very similar structure, indicating that FURL can learn collaboratively through the shared parameters while preserving user privacy.
OpenDialKG: Explainable Conversational Reasoning with Attention-based Walks over Knowledge Graphs
We study a conversational reasoning model that strategically traverses through a large-scale common fact knowledge graph (KG) to introduce engaging and contextually diverse entities and attributes.
Explore-Exploit: A Framework for Interactive and Online Learning
This may require constant exploration of various options that the system may have for the user and obtaining signals of user preferences on those.
Semantic Parsing for Task Oriented Dialog using Hierarchical Representations
Task oriented dialog systems typically first parse user utterances to semantic frames comprised of intents and slots.
Towards end-to-end spoken language understanding
Spoken language understanding system is traditionally designed as a pipeline of a number of components.
Natural Language Understanding
Spoken Language Understanding
