Maharshi Gor

Selected Publications

1. EMNLP 2021

   MATE: Multi-view Attention for Table Transformer Efficiency

   Julian Martin Eisenschlos, Maharshi Gor, Thomas Müller, and William Weston Cohen

   In Empirical Methods in Natural Language Processing 2021

   Abs Bib HTML

   This work presents a sparse-attention Transformer architecture for modeling documents that contain large tables. Tables are ubiquitous on the web, and are rich in information. However, more than 20% of relational tables on the web have 20 or more rows (Cafarella et al., 2008), and these large tables present a challenge for current Transformer models, which are typically limited to 512 tokens. Here we propose MATE, a novel Transformer architecture designed to model the structure of web tables. MATE uses sparse attention in a way that allows heads to efficiently attend to either rows or columns in a table. This architecture scales linearly with respect to speed and memory, and can handle documents containing more than 8000 tokens with current accelerators. MATE also has a more appropriate inductive bias for tabular data, and sets a new state-of-the-art for three table reasoning datasets. For HybridQA (Chen et al., 2020b), a dataset that involves large documents containing tables, we improve the best prior result by 19 points.

   @inproceedings{eisenschlos2021mate,
     abbr = {EMNLP},
     bibtex_show = {true},
     title = {MATE: Multi-view Attention for Table Transformer Efficiency},
     author = {Eisenschlos, Julian Martin and Gor, Maharshi and M{\"u}ller, Thomas and Cohen, William Weston},
     booktitle = {Empirical Methods in Natural Language Processing},
     publisher = {Association for Computational Linguistics,},
     year = {2021},
     location = {Punta Cana},
     html = {https://arxiv.org/pdf/2109.04312.pdf},
     selected = {true}
   }

2. EMNLP 2021

   Toward Deconfounding the Influence of Entity Demographics for Question Answering Accuracy

   Maharshi Gor, Kellie Webster, and Jordan Boyd-Graber

   In Empirical Methods in Natural Language Processing 2021

   Abs Bib HTML

   The goal of question answering (QA) is to answer any question. However, major QA datasets have skewed distributions over gender, profession, and nationality. Despite that skew, model accuracy analysis reveals little evidence that accuracy is lower for people based on gender or nationality; instead, there is more variation on professions (question topic). But QA’s lack of representation could itself hide evidence of bias, necessitating QA datasets that better represent global diversity.

   @inproceedings{Gor:Webster:Boyd-Graber-2021,
     abbr = {EMNLP},
     bibtex_show = {true},
     title = {Toward Deconfounding the Influence of Entity Demographics for Question Answering Accuracy},
     author = {Gor, Maharshi and Webster, Kellie and Boyd-Graber, Jordan},
     booktitle = {Empirical Methods in Natural Language Processing},
     publisher = {Association for Computational Linguistics,},
     month = nov,
     year = {2021},
     location = {Punta Cana},
     html = {https://arxiv.org/pdf/2104.07571.pdf},
     selected = {true}
   }

3. ICCV 2019

   GAN-Tree: An Incrementally Learned Hierarchical Generative Framework for Multi-Modal Data Distributions

   Jogendra Nath Kundu, Maharshi Gor, Dakshit Agrawal, and R. Venkatesh Babu

   In Proceedings of the IEEE/CVF International Conference on Computer Vision 2019

   Abs Bib HTML Code

   Despite the remarkable success of generative adversarial networks, their performance seems less impressive for diverse training sets, requiring learning of discontinuous mapping functions. Though multi-mode prior or multi-generator models have been proposed to alleviate this problem, such approaches may fail depending on the empirically chosen initial mode components. In contrast to such bottom-up approaches, we present GAN-Tree, which follows a hierarchical divisive strategy to address such discontinuous multi-modal data. Devoid of any assumption on the number of modes, GAN-Tree utilizes a novel mode-splitting algorithm to effectively split the parent mode to semantically cohesive children modes, facilitating unsupervised clustering. Further, it also enables incremental addition of new data modes to an already trained GAN-Tree, by updating only a single branch of the tree structure. As compared to prior approaches, the proposed framework offers a higher degree of flexibility in choosing a large variety of mutually exclusive and exhaustive tree nodes called GAN-Set. Extensive experiments on synthetic and natural image datasets including ImageNet demonstrate the superiority of GAN-Tree against the prior state-of-the-art.

   @inproceedings{Kundu:Gor:Agrawal:Babu-ICCV2019,
     abbr = {ICCV},
     bibtex_show = {true},
     author = {Kundu, Jogendra Nath and Gor, Maharshi and Agrawal, Dakshit and Babu, R. Venkatesh},
     title = {GAN-Tree: An Incrementally Learned Hierarchical Generative Framework for Multi-Modal Data Distributions},
     booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
     month = oct,
     year = {2019},
     location = {Seoul, South Korea},
     html = {https://openaccess.thecvf.com/content_ICCV_2019/papers/Kundu_GAN-Tree_An_Incrementally_Learned_Hierarchical_Generative_Framework_for_Multi-Modal_Data_ICCV_2019_paper.pdf},
     selected = {true},
     code = {https://github.com/maharshi95/GANTree}
   }