Papers by Krishna Srinivasan
QUILL: Query Intent with Large Language Models using Retrieval Augmentation and Multi-stage Distillation (2022.emnlp-industry)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown impressive results on a variety of text understanding tasks. |
| Approach: | They propose a two-stage distillation approach that allows retrieval augmentation to be carried over without the increased compute associated with it. |
| Outcome: | The proposed approach can carry over the gains of retrieval augmentation without suffering the increased compute typically associated with it. |
Generating Topic-Oriented Summaries Using Neural Attention (N18-1)
Copied to clipboard
| Challenge: | Existing summarization algorithms generate a single summary and are not capable of generating multiple summaries tuned to the interests of the readers. |
| Approach: | They propose an attention based RNN framework to generate multiple summaries tuned to different topics of interest. |
| Outcome: | The proposed framework outperforms baselines and shows that attention bias can be successfully used to generate topic-tuned summaries. |
Transforming Sequence Tagging Into A Seq2Seq Task (2022.emnlp-main)
Copied to clipboard
| Challenge: | Pretrained, large, generative language models have had great success in a wide range of sequence tagging and structured prediction tasks. |
| Approach: | They propose to use a new format for casting input text sentences and their output labels into the input and target of a Seq2Seq model and introduce it to test their hypothesis. |
| Outcome: | The proposed format shows to be both simpler and more effective and devoid of hallucination. |
Corpus-based Content Construction (C18-1)
Copied to clipboard
| Challenge: | Existing work in this direction focuses on generating content for standard platforms like Wikipedia, where the content style is fairly consistent, but there could be multiple representations of the same information across the repository. |
| Approach: | They propose an automatic approach to generate an initial version of the author’s intended text based on an input content snippet. |
| Outcome: | The proposed approach improves performance against baselines on several metrics. |
Vocabulary Tailored Summary Generation (C18-1)
Copied to clipboard
| Challenge: | Existing frameworks for summary generation do not account for linguistic preferences of the specific audience who will consume the summary. |
| Approach: | They propose a neural framework to generate summary constrained to a vocabulary-defined linguistic preferences of a target audience. |
| Outcome: | The proposed approach generates understandable summaries with simpler words and readable summary with shorter words against a state-of-the-art word embedding based lexical substitution algorithm. |
A Suite of Generative Tasks for Multi-Level Multimodal Webpage Understanding (2023.emnlp-main)
Copied to clipboard
Andrea Burns, Krishna Srinivasan, Joshua Ainslie, Geoff Brown, Bryan Plummer, Kate Saenko, Jianmo Ni, Mandy Guo
| Challenge: | Existing datasets for webpages contain only fragments of webpages . generative tasks like page description generation and section summarization are often left unstudied . |
| Approach: | They introduce a Wikipedia Webpage suite that contains 2M pages with all associated image, text, and structure data. |
| Outcome: | The proposed approach performs better than full attention with lower computational complexity. |
MURAL: Multimodal, Multitask Representations Across Languages (2021.findings-emnlp)
Copied to clipboard
Aashi Jain, Mandy Guo, Krishna Srinivasan, Ting Chen, Sneha Kudugunta, Chao Jia, Yinfei Yang, Jason Baldridge
| Challenge: | Image-caption pairs and translation pairs provide the means to learn deep representations of and connections between languages. |
| Approach: | They propose a dual encoder that integrates image-text matching and translation pairs to solve two tasks by learning from billions of pairs. |
| Outcome: | The proposed encoder outperforms ALIGN's cross-modal retrieval performance on well-resourced languages and significantly improves on under-resource languages. |