22 Result(s)
within
Ganesh Ramakrishnan
-
Chapter and Conference Paper
TACTFUL: A Framework for Targeted Active Learning for Document Analysis
Document Layout Parsing is an important step in an OCR pipeline, and several research attempts toward supervised, and semi-supervised deep learning methods are proposed for accurately identifying the complex s...
-
Chapter and Conference Paper
CLINICAL: Targeted Active Learning for Imbalanced Medical Image Classification
Training deep learning models on medical datasets that perform well for all classes is a challenging task. It is often the case that a suboptimal performance is obtained on some classes due to the natural clas...
-
Chapter and Conference Paper
DIAGNOSE: Avoiding Out-of-Distribution Data Using Submodular Information Measures
Avoiding out-of-distribution (OOD) data is critical for training supervised machine learning models in the medical imaging domain. Furthermore, obtaining labeled medical data is difficult and expensive since i...
-
Chapter and Conference Paper
CATALIST: CAmera TrAnsformations for Multi-LIngual Scene Text Recognition
We present a CATALIST model that ‘tames’ the attention (heads) of an attention-based scene text recognition model. We provide supervision to the attention masks at multiple levels, i.e., line, word, and character...
-
Chapter and Conference Paper
Watch Hours in Minutes: Summarizing Videos with User Intent
With the ever increasing growth of videos, automatic video summarization has become an important task which has attracted lot of interest in the research community. One of the challenges which makes it a hard ...
-
Article
Neural architecture for question answering using a knowledge graph and web corpus
In Web search, entity-seeking queries often trigger a special question answering (QA) system. It may use a parser to interpret the question to a structured query, execute that on a knowledge graph (KG), and re...
-
Chapter and Conference Paper
Difficulty-Controllable Multi-hop Question Generation from Knowledge Graphs
Knowledge graphs have become ubiquitous data sources and their utility has been amplified by the research on ability to answer carefully crafted questions over knowledge graphs. We investigate the problem of q...
-
Chapter and Conference Paper
Automating Reading Comprehension by Generating Question and Answer Pairs
Neural network-based methods represent the state-of-the-art in question generation from text. Existing work focuses on generating only questions from text without concerning itself with answer generation. More...
-
Chapter and Conference Paper
Building Compact Lexicons for Cross-Domain SMT by Mining Near-Optimal Pattern Sets
Statistical machine translation models are known to benefit from the availability of a domain bilingual lexicon. Bilingual lexicons are traditionally comprised of multiword expressions, either extracted from p...
-
Chapter and Conference Paper
Explicit Query Interpretation and Diversification for Context-Driven Concept Search Across Ontologies
Finding relevant concepts from a corpus of ontologies is useful in many scenarios, such as document classification, web page annotation, and automatic ontology population. Many millions of concepts are contain...
-
Chapter and Conference Paper
Rel-Div: Generating Diversified Query Interpretations from Semantic Relations
Accelerated growth of the World Wide Web has resulted in an increase in appetite for searching over Internet to fulfill the information needs. Understanding user intent plays a pivotal role in determining the ...
-
Chapter and Conference Paper
What Kinds of Relational Features Are Useful for Statistical Learning?
A workmanlike, but nevertheless very effective combination of statistical and relational learning uses a statistical learner to construct models with features identified (quite often, separately) by a relation...
-
Chapter and Conference Paper
Probing the Space of Optimal Markov Logic Networks for Sequence Labeling
Discovering relational structure between input features in sequence labeling models has shown to improve their accuracies in several problem settings. The problem of learning relational structure for sequence ...
-
Chapter and Conference Paper
BET : An Inductive Logic Programming Workbench
Existing ILP (Inductive Logic Programming) systems are implemented in different languages namely C, Progol, etc. Also, each system has its customized format for the input data. This makes it very tedious and t...
-
Chapter and Conference Paper
Pruning Search Space for Weighted First Order Horn Clause Satisfiability
Many SRL models pose logical inference as weighted satisfiability solving. Performing logical inference after completely grounding clauses with all possible constants is computationally expensive and approache...
-
Chapter and Conference Paper
Enhancing Activity Recognition in Smart Homes Using Feature Induction
Hidden Markov Models (HMMs) are widely used in activity recognition. Ideally, the current activity should be determined using the vector of all sensor readings; however, this results in an exponentially large ...
-
Chapter and Conference Paper
Parameter Screening and Optimisation for ILP Using Designed Experiments
Reports of experiments conducted with an Inductive Logic Programming system rarely describe how specific values of parameters of the system are arrived at when constructing models. Usually, no attempt is made ...
-
Chapter and Conference Paper
Incorporating Linguistic Expertise Using ILP for Named Entity Recognition in Data Hungry Indian Languages
Develo** linguistically sound and data-compliant rules for named entity annotation is usually an intensive and time consuming process for any developer or linguist. In this work, we present the use of two In...
-
Article
An investigation into feature construction to assist word sense disambiguation
Identifying the correct sense of a word in context is crucial for many tasks in natural language processing (machine translation is an example). State-of-the art methods for Word Sense Disambiguation (WSD) bui...
-
Chapter and Conference Paper
Using ILP to Construct Features for Information Extraction from Semi-structured Text
Machine-generated documents containing semi-structured text are rapidly forming the bulk of data being stored in an organisation. Given a feature-based representation of such data, methods like SVMs are able t...
