Adithya Samavedhi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Interests
Adithya Samavedhi has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Akshita Jha
Virginia Tech, Arlington, Virginia, USA
2 shared publications - Chandan K. Reddy
Virginia Tech, USA
2 shared publications - Jaideep Chandrashekar
InterDigital
2 shared publications - Vineeth Rakesh
InterDigital CA
2 shared publications
Latest Publications
- Open Access
Transformer-based Models for Long-Form Document Matching: Challenges and Empirical Analysis
Recent advances in the area of long document matching have primarily focused on using transformer-based models for long document encoding and matching. There are two primary challenges associated with these models. Firstly, the performance gain provided by transformer-based models comes at a steep cost - both in terms of the required training time and the resource (memory and energy) consumption. The second major limitation is their inability to handle more than a pre-defined input token length at a time. In this work, we empirically demonstrate the effectiveness of simple neural models (such as feed-forward networks, and CNNs) and simple embeddings (like GloVe, and Paragraph Vector) over transformer-based models on the task of document matching. We show that simple models outperform the more complex BERT-based models while taking significantly less training time, energy, and memory. The simple models are also more robust to variations in document length and text perturbations.
Open AccessTransformer-based Models for Long-Form Document Matching: Challenges and Empirical Analysis
Recent advances in the area of long document matching have primarily focused on using transformer-based models for long document encoding and matching. There are two primary challenges associated with these models. Firstly, the performance gain provided by transformer-based models comes at a steep cost - both in terms of the required training time and the resource (memory and energy) consumption. The second major limitation is their inability to handle more than a pre-defined input token length at a time. In this work, we empirically demonstrate the effectiveness of simple neural models (such as feed-forward networks, and CNNs) and simple embeddings (like GloVe, and Paragraph Vector) over transformer-based models on the task of document matching. We show that simple models outperform the more complex BERT-based models while taking significantly less training time, energy, and memory. The simple models are also more robust to variations in document length and text perturbations.
- Open Access
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 2345-2355
Transformer-based Models for Long-Form Document Matching: Challenges and Empirical Analysis
Akshita Jha, Adithya Samavedhi, Vineeth Rakesh, Jaideep Chandrashekar, Chandan Reddy. Findings of the Association for Computational Linguistics: EACL 2023. 2023.
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 2345-2355
Open AccessTransformer-based Models for Long-Form Document Matching: Challenges and Empirical Analysis
Akshita Jha, Adithya Samavedhi, Vineeth Rakesh, Jaideep Chandrashekar, Chandan Reddy. Findings of the Association for Computational Linguistics: EACL 2023. 2023.