Search Results for author:
Found 20 papers, 8 papers with code
Hi-DST: A Hierarchical Approach for Scalable and Extensible Dialogue State Tracking
The model parameters of Hi-DST are independent of the number of domains/slots.
Transformer based Multitask Learning for Image Captioning and Object Detection
We propose TICOD, Transformer-based Image Captioning and Object detection model for jointly training both tasks by combining the losses obtained from image captioning and object detection networks.
Trie-NLG: Trie Context Augmentation to Improve Personalized Query Auto-Completion for Short and Unseen Prefixes
However, such NLG models suffer from two drawbacks: (1) some of the previous session queries could be noisy and irrelevant to the user intent for the current prefix, and (2) NLG models cannot directly incorporate historical query popularity.
CharSpan: Utilizing Lexical Similarity to Enable Zero-Shot Machine Translation for Extremely Low-resource Languages
We address the task of machine translation (MT) from extremely low-resource language (ELRL) to English by leveraging cross-lingual transfer from 'closely-related' high-resource language (HRL).
ComplAI: Theory of A Unified Framework for Multi-factor Assessment of Black-Box Supervised Machine Learning Models
In this paper, we present ComplAI, a unique framework to enable, observe, analyze and quantify explainability, robustness, performance, fairness, and model behavior in drift scenarios, and to provide a single Trust Factor that evaluates different supervised Machine Learning models not just from their ability to make correct predictions but from overall responsibility perspective.
On Text Style Transfer via Style Masked Language Models
Text Style Transfer (TST) is performable through approaches such as latent space disentanglement, cycle-consistency losses, prototype editing etc.
DialoGen: Generalized Long-Range Context Representation for Dialogue Systems
In this work, we propose DialoGen, a novel encoder-decoder based framework for dialogue generation with a generalized context representation that can look beyond the last-$k$ utterances.
HyperHawkes: Hypernetwork based Neural Temporal Point Process
We also develop a hypernetwork based continually learning temporal point process for continuous modeling of time-to-event sequences with minimal forgetting.
Towards Robust and Semantically Organised Latent Representations for Unsupervised Text Style Transfer
We empirically show that this (a) produces a better organised latent space that clusters stylistically similar sentences together, (b) performs best on a diverse set of text style transfer tasks than similar denoising-inspired baselines, and (c) is capable of fine-grained control of Style Transfer strength.
Towards Fair Evaluation of Dialogue State Tracking by Flexible Incorporation of Turn-level Performances
Generally in DST, the dialogue state or belief state for a given turn contains all the intents shown by the user till that turn.
Meta-X$_{NLG}$: A Meta-Learning Approach Based on Language Clustering for Zero-Shot Cross-Lingual Transfer and Generation
In this paper, we propose a novel meta-learning framework (called Meta-X$_{NLG}$) to learn shareable structures from typologically diverse languages based on meta-learning and language clustering.
Graph Neural Network Enhanced Language Models for Efficient Multilingual Text Classification
To overcome these challenges, we propose a multilingual disaster related text classification system which is capable to work under \{mono, cross and multi\} lingual scenarios and under limited supervision.
Supervised Graph Contrastive Pretraining for Text Classification
In this paper, we propose a novel way to effectively utilize labeled data from related tasks with a graph based supervised contrastive learning approach.
ZmBART: An Unsupervised Cross-lingual Transfer Framework for Language Generation
In this framework, we further pre-train mBART sequence-to-sequence denoising auto-encoder model with an auxiliary task using monolingual data of three languages.
Unsupervised Domain Adaptation with Global and Local Graph Neural Networks in Limited Labeled Data Scenario: Application to Disaster Management
To handle this challenge, we utilize limited labeled data along with abundantly available unlabeled data, generated during a source disaster to propose a novel two-part graph neural network.
Walk in Wild: An Ensemble Approach for Hostility Detection in Hindi Posts
This leads to the necessity of identifying hostile content on social media platforms.
Coarse and Fine-Grained Hostility Detection in Hindi Posts using Fine Tuned Multilingual Embeddings
The proposed model outperformed the existing baseline models and emerged as the state-of-the-art model for detecting hostility in the Hindi posts.
IR2Vec: LLVM IR based Scalable Program Embeddings
As our infrastructure is based on the Intermediate Representation (IR) of the source code, obtained embeddings are both language and machine independent.
Aggression Detection in Social Media using Deep Neural Networks
On the other hand, most of the content in social media is non-aggressive in nature.
NSEmo at EmoInt-2017: An Ensemble to Predict Emotion Intensity in Tweets
The final method uses lexicons, word embeddings, word n-grams, character n-grams for training the model.
