Papers by Hrituraj Singh
STL-CQA: Structure-based Transformers with Localization and Encoding for Chart Question Answering (2020.emnlp-main)
Copied to clipboard
| Challenge: | Chart Question Answering (CQA) is a task of answering natural language questions about visualisations in the chart image. |
| Approach: | They propose a method for Chart Question Answering which improves the question/answering through sequential elements localization, question encoding and then, a structural transformer-based learning approach. |
| Outcome: | The proposed method outperforms state-of-the-art methods on various chart Q/A datasets while outperforming even human baseline. |
Incorporating Stylistic Lexical Preferences in Generative Language Models (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in language modeling have resulted in powerful generation models, but their style is implicitly dependent on the training data and cannot emulate a specific target style. |
| Approach: | They propose an approach to induce certain target-author attributes by incorporating continuous multi-dimensional lexical preferences of an author into generative language models. |
| Outcome: | The proposed model generates text that aligns with a given target author’s lexical style and is competitive with baselines. |
DRAG: Director-Generator Language Modelling Framework for Non-Parallel Author Stylized Rewriting (2021.eacl-main)
Copied to clipboard
| Challenge: | Recent work in this area has focused on author stylized rewriting but is limited by the lack of explicit control of target attributes and being data-driven. |
| Approach: | They propose a Director-Generator framework to rewrite input text in the target author’s style, specifically focusing on certain target attributes. |
| Outcome: | The proposed framework has better meaning retention and results in more fluent generations on a small corpus of text authored by three distinct authors. |
MIMOQA: Multimodal Input Multimodal Output Question Answering (2021.naacl-main)
Copied to clipboard
| Challenge: | Multimodal research has picked up significantly in the space of question answering with the task being extended to visual question answering, charts question answering as well as multimodal input question answering. |
| Approach: | They propose a multimodal question-answering task that produces a unimodal textual output as the answer through human experiments. |
| Outcome: | The proposed framework outperforms existing frameworks on both automatic and human metrics. |