Search Results for author: Ashish Anand

Found 20 papers, 8 papers with code

ERLKG: Entity Representation Learning and Knowledge Graph based association analysis of COVID-19 through mining of unstructured biomedical corpora

1 code implementation EMNLP (sdp) 2020 Sayantan Basu, Sinchani Chakraborty, Atif Hassan, Sana Siddique, Ashish Anand

We introduce a generic, human-out-of-the-loop pipeline, ERLKG, to perform rapid association analysis of any biomedical entity with other existing entities from a corpora of the same domain.

Association Link Prediction +1

Budget Sensitive Reannotation of Noisy Relation Classification Data Using Label Hierarchy

no code implementations26 Dec 2021 Akshay Parekh, Ashish Anand, Amit Awekar

The immediate follow-up problem is: Given a specific reannotation budget, which subset of the data should we reannotate?

Relation Classification

CL-NERIL: A Cross-Lingual Model for NER in Indian Languages

1 code implementation23 Nov 2021 Akshara Prabhakar, Gouri Sankar Majumder, Ashish Anand

We employ a variant of the Teacher-Student model and optimize it jointly on the pseudo labels of the Teacher model and predictions on the generated weakly labeled data.

named-entity-recognition NER +3

IQ-VQA: Intelligent Visual Question Answering

1 code implementation8 Jul 2020 Vatsal Goel, Mohit Chandak, Ashish Anand, Prithwijit Guha

As a part of the cyclic framework, we propose a novel implication generator which can generate implied questions from any question-answer pair.

Question Answering Visual Question Answering +1

CQ-VQA: Visual Question Answering on Categorized Questions

no code implementations17 Feb 2020 Aakansha Mishra, Ashish Anand, Prithwijit Guha

The second level, referred to as answer predictor (AP), comprises of a set of distinct classifiers corresponding to each question category.

Question Answering Visual Question Answering +1

Taxonomical hierarchy of canonicalized relations from multiple Knowledge Bases

1 code implementation13 Sep 2019 Akshay Parekh, Ashish Anand, Amit Awekar

Further, to address the second question, we canonicalize, filter, and combine the identified relations from the three resources to construct a taxonomical hierarchy.

Relation Extraction

Unsupervised Representation Learning of DNA Sequences

no code implementations7 Jun 2019 Vishal Agarwal, N Jayanth Kumar Reddy, Ashish Anand

In this work, we use a sequence-to-sequence autoencoder model to learn a latent representation of a fixed dimension for long and variable length DNA sequences in an unsupervised manner.

Classification General Classification +1

Fine-grained Entity Recognition with Reduced False Negatives and Large Type Coverage

1 code implementation AKBC 2019 Abhishek Abhishek, Sanya Bathla Taneja, Garima Malik, Ashish Anand, Amit Awekar

Fine-grained Entity Recognition (FgER) is the task of detecting and classifying entity mentions to a large set of types spanning diverse domains such as biomedical, finance and sports.

Collective Learning From Diverse Datasets for Entity Typing in the Wild

no code implementations20 Oct 2018 Abhishek Abhishek, Amar Prakash Azad, Balaji Ganesan, Ashish Anand, Amit Awekar

The CLF first creates a unified hierarchical label set (UHLS) and a label mapping by aggregating label information from all available datasets.

Entity Typing

Investigating how well contextual features are captured by bi-directional recurrent neural network models

no code implementations WS 2017 Kushal Chawla, Sunil Kumar Sahu, Ashish Anand

Our experiments focus on important contextual words as features, which can easily be extended to analyze various other feature types.

Feature Engineering

Unified Neural Architecture for Drug, Disease and Clinical Entity Recognition

no code implementations11 Aug 2017 Sunil Kumar Sahu, Ashish Anand

Three important characteristics of the framework are as follows - (1) model learns contextual as well as morphological features using two different BLSTM in hierarchy, (2) model uses first order linear conditional random field (CRF) in its output layer in cascade of BLSTM to infer label or tag sequence, (3) model does not use any domain specific features or dictionary, i. e., in another words, same set of features are used in the three NER tasks, namely, disease name recognition (Disease NER), drug name recognition (Drug NER) and clinical entity recognition (Clinical NER).

Feature Engineering named-entity-recognition +2

What matters in a transferable neural network model for relation classification in the biomedical domain?

no code implementations11 Aug 2017 Sunil Kumar Sahu, Ashish Anand

We systematically investigate effectiveness of the proposed frameworks in transferring the knowledge under multiple aspects related to source and target tasks, such as, similarity or relatedness between source and target tasks, and size of training data for source task.

BIG-bench Machine Learning General Classification +2

Drug-Drug Interaction Extraction from Biomedical Text Using Long Short Term Memory Network

1 code implementation28 Jan 2017 Sunil Kumar Sahu, Ashish Anand

The two models, {\it AB-LSTM} and {\it Joint AB-LSTM} also use attentive pooling in the output of Bi-LSTM layer to assign weights to features.

Drug–drug Interaction Extraction Feature Engineering +1

Recurrent neural network models for disease name recognition using domain invariant features

no code implementations ACL 2016 Sunil Kumar Sahu, Ashish Anand

In particular, we propose various end-to-end recurrent neural network (RNN) models for the tasks of disease name recognition and their classification into four pre-defined categories.

Feature Engineering General Classification

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