136 citations · 466 across the 24 of their papers we have counts for
24 papers
VAANI: Capturing the language landscape for an inclusive digital India
Sujith Pulikodan, Abhayjeet Singh, Agneedh Basu +17
Voice based technologies have the potential to bridge digital accessibility gaps; however, existing datasets fail to capture the linguistic and regional diversity of Indic language…
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431
In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…
STAB: Speech Tokenizer Assessment Benchmark
Shikhar Vashishth, Harman Singh, Shikhar Bharadwaj +6
Representing speech as discrete tokens provides a framework for transforming speech into a format that closely resembles text, thus enabling the use of speech as an input to the wi…
A Morphology-Based Investigation of Positional Encodings
Poulami Ghosh, Shikhar Vashishth, Raj Dabre +1
Contemporary deep learning models effectively handle languages with diverse morphology despite not being directly integrated into them. Morphology and word order are closely linked…
LLM Augmented LLMs: Expanding Capabilities through Composition
Rachit Bansal, Bidisha Samanta, Siddharth Dalmia +6
Foundational models with billions of parameters which have been trained on large corpora of data have demonstrated non-trivial skills in a variety of domains. However, due to their…
Self-Influence Guided Data Reweighting for Language Model Pre-training
Megh Thakkar, Tolga Bolukbasi, Sriram Ganapathy +3
Language Models (LMs) pre-trained with self-supervision on large text corpora have become the default starting point for developing models for various NLP tasks. Once the pre-train…
Multimodal Modeling For Spoken Language Identification
Shikhar Bharadwaj, Min Ma, Shikhar Vashishth +10
Spoken language identification refers to the task of automatically predicting the spoken language in a given utterance. Conventionally, it is modeled as a speech-based language ide…
MASR: Multi-label Aware Speech Representation
Anjali Raj, Shikhar Bharadwaj, Sriram Ganapathy +2
In the recent years, speech representation learning is constructed primarily as a self-supervised learning (SSL) task, using the raw audio signal alone, while ignoring the side-inf…
Label Aware Speech Representation Learning For Language Identification
Shikhar Vashishth, Shikhar Bharadwaj, Sriram Ganapathy +5
Speech representation learning approaches for non-semantic tasks such as language recognition have either explored supervised embedding extraction methods using a classifier model…
Knowledge-Rich Self-Supervision for Biomedical Entity Linking
Sheng Zhang, Hao Cheng, Shikhar Vashishth +6
Entity linking faces significant challenges such as prolific variations and prevalent ambiguities, especially in high-value domains with myriad entities. Standard classification ap…
Robust Knowledge Graph Completion with Stacked Convolutions and a Student Re-Ranking Network
Justin Lovelace, Denis Newman-Griffis, Shikhar Vashishth +2
Knowledge Graph (KG) completion research usually focuses on densely connected benchmark datasets that are not representative of real KGs. We curate two KG datasets that include bio…
DialoGraph: Incorporating Interpretable Strategy-Graph Networks into Negotiation Dialogues
Rishabh Joshi, Vidhisha Balachandran, Shikhar Vashishth +2
To successfully negotiate a deal, it is not enough to communicate fluently: pragmatic planning of persuasive negotiation strategies is essential. While modern dialogue agents excel…
MedFilter: Improving Extraction of Task-relevant Utterances from Doctor-Patient Conversations through Integration of Discourse Structure and Ontological Knowledge
Sopan Khosla, Shikhar Vashishth, Jill Fain Lehman +1
Information extraction from conversational data is particularly challenging because the task-centric nature of conversation allows for effective communication of implicit informati…
Improving Broad-Coverage Medical Entity Linking with Semantic Type Prediction and Large-Scale Datasets
Shikhar Vashishth, Denis Newman-Griffis, Rishabh Joshi +2
Medical entity linking is the task of identifying and standardizing medical concepts referred to in an unstructured text. Most of the existing methods adopt a three-step approach o…
A Re-evaluation of Knowledge Graph Completion Methods
Zhiqing Sun, Shikhar Vashishth, Soumya Sanyal +2
Knowledge Graph Completion (KGC) aims at automatically predicting missing links for large-scale knowledge graphs. A vast number of state-of-the-art KGC techniques have got publishe…
Composition-based Multi-Relational Graph Convolutional Networks
Shikhar Vashishth, Soumya Sanyal, Vikram Nitin +1
Graph Convolutional Networks (GCNs) have recently been shown to be quite successful in modeling graph-structured data. However, the primary focus has been on handling simple undire…
Neural Graph Embedding Methods for Natural Language Processing
Shikhar Vashishth
Knowledge graphs are structured representations of facts in a graph, where nodes represent entities and edges represent relationships between them. Recent research has resulted in…
InteractE: Improving Convolution-based Knowledge Graph Embeddings by Increasing Feature Interactions
Shikhar Vashishth, Soumya Sanyal, Vikram Nitin +2
Most existing knowledge graphs suffer from incompleteness, which can be alleviated by inferring missing links based on known facts. One popular way to accomplish this is to generat…
Attention Interpretability Across NLP Tasks
Shikhar Vashishth, Shyam Upadhyay, Gaurav Singh Tomar +1
The attention layer in a neural network model provides insights into the model's reasoning behind its prediction, which are usually criticized for being opaque. Recently, seemingly…
Confidence-based Graph Convolutional Networks for Semi-Supervised Learning
Shikhar Vashishth, Prateek Yadav, Manik Bhandari +1
Predicting properties of nodes in a graph is an important problem with applications in a variety of domains. Graph-based Semi-Supervised Learning (SSL) methods aim to address this…
Dating Documents using Graph Convolution Networks
Shikhar Vashishth, Shib Sankar Dasgupta, Swayambhu Nath Ray +1
Document date is essential for many important tasks, such as document retrieval, summarization, event detection, etc. While existing approaches for these tasks assume accurate know…
CESI: Canonicalizing Open Knowledge Bases using Embeddings and Side Information
Shikhar Vashishth, Prince Jain, Partha Talukdar
Open Information Extraction (OpenIE) methods extract (noun phrase, relation phrase, noun phrase) triples from text, resulting in the construction of large Open Knowledge Bases (Ope…
RESIDE: Improving Distantly-Supervised Neural Relation Extraction using Side Information
Shikhar Vashishth, Rishabh Joshi, Sai Suman Prayaga +2
Distantly-supervised Relation Extraction (RE) methods train an extractor by automatically aligning relation instances in a Knowledge Base (KB) with unstructured text. In addition t…
Incorporating Syntactic and Semantic Information in Word Embeddings using Graph Convolutional Networks
Shikhar Vashishth, Manik Bhandari, Prateek Yadav +3
Word embeddings have been widely adopted across several NLP applications. Most existing word embedding methods utilize sequential context of a word to learn its embedding. While th…