no code implementations • Findings (EMNLP) 2021 • Akhil Kedia, Sai Chetan Chinthakindi, WonHo Ryu
Inspired by these approaches for a single task setting, this paper proposes to use the finite differences first-order algorithm to calculate this gradient from dot-product of gradients, allowing explicit control on the weightage of this component relative to standard gradients.
Ranked #1 on Text Summarization on GigaWord (using extra training data)
1 code implementation • 14 Mar 2024 • Akhil Kedia, Mohd Abbas Zaidi, Sushil Khyalia, Jungho Jung, Harshith Goka, Haejun Lee
In spite of their huge success, transformer models remain difficult to scale in depth.
no code implementations • 18 Nov 2022 • Akhil Kedia, Mohd Abbas Zaidi, Haejun Lee
Using our proposed method, we outperform the current state-of-the-art method by $2. 5$ Exact Match score on the Natural Question dataset while using only $25\%$ of parameters and $35\%$ of the latency during inference, and $4. 4$ Exact Match on WebQuestions dataset.
Ranked #1 on Question Answering on WebQuestions (using extra training data)
no code implementations • 14 Dec 2021 • Haejun Lee, Akhil Kedia, Jongwon Lee, Ashwin Paranjape, Christopher D. Manning, Kyoung-Gu Woo
Recent approaches to Open-domain Question Answering refer to an external knowledge base using a retriever model, optionally rerank passages with a separate reranker model and generate an answer using another reader model.
no code implementations • EACL 2021 • Akhil Kedia, Sai Chetan Chinthakindi
A common approach in many machine learning algorithms involves self-supervised learning on large unlabeled data before fine-tuning on downstream tasks to further improve performance.
Ranked #1 on Answer Selection on Ubuntu Dialogue (v2, Ranking)
no code implementations • 1 Jan 2021 • Seohyun Back, Akhil Kedia, Sai Chetan Chinthakindi, Haejun Lee, Jaegul Choo
We evaluate our method against existing ones in terms of the quality of generated questions as well as the fine-tuned MRC model accuracy after training on the data synthetically generated by our method.
Ranked #3 on Question Generation on SQuAD1.1 (using extra training data)
no code implementations • ICLR 2020 • Seohyun Back, Sai Chetan Chinthakindi, Akhil Kedia, Haejun Lee, Jaegul Choo
Real-world question answering systems often retrieve potentially relevant documents to a given question through a keyword search, followed by a machine reading comprehension (MRC) step to find the exact answer from them.
no code implementations • 25 Sep 2019 • Akhil Kedia, Sai Chetan Chinthakindi, Seohyun Back, Haejun Lee, Jaegul Choo
We evaluate the question generation capability of our method by comparing the BLEU score with existing methods and test our method by fine-tuning the MRC model on the downstream MRC data after training on synthetic data.