18 citations · 32 across the 4 of their papers we have counts for
5 papers
Dynamic ordering in sequence generation in Transformers: experiments on low-resource Tagging scenarios
Giacomo Bais, Tejaswini Deoskar
This paper introduces TagInsert, a Transformer-based model that challenges the common left-to-right (L2R) generation paradigm in Transformers, for sequence labelling tasks where de…
MERGE: Minimal Expression-Replacement GEneralization Test for Natural Language Inference
Mădălina Zgreabăn, Tejaswini Deoskar, Lasha Abzianidze
As many benchmarks have become saturated, it is increasingly important to create new datasets that evaluate the generalization capacity of current state-of-the-art models in reason…
Generating image captions with external encyclopedic knowledge
Sofia Nikiforova, Tejaswini Deoskar, Denis Paperno +1
Accurately reporting what objects are depicted in an image is largely a solved problem in automatic caption generation. The next big challenge on the way to truly humanlike caption…
A comparison of latent semantic analysis and correspondence analysis of document-term matrices
Qianqian Qi, David J. Hessen, Tejaswini Deoskar +1
Latent semantic analysis (LSA) and correspondence analysis (CA) are two techniques that use a singular value decomposition (SVD) for dimensionality reduction. LSA has been extensiv…
Constructive Type-Logical Supertagging with Self-Attention Networks
Konstantinos Kogkalidis, Michael Moortgat, Tejaswini Deoskar
We propose a novel application of self-attention networks towards grammar induction. We present an attention-based supertagger for a refined type-logical grammar, trained on constr…