no code implementations • 22 Apr 2024 • Dujian Ding, Ankur Mallick, Chi Wang, Robert Sim, Subhabrata Mukherjee, Victor Ruhle, Laks V. S. Lakshmanan, Ahmed Hassan Awadallah
Large language models (LLMs) excel in most NLP tasks but also require expensive cloud servers for deployment due to their size, while smaller models that can be deployed on lower cost (e. g., edge) devices, tend to lag behind in terms of response quality.
no code implementations • 25 Feb 2024 • Md Tawkat Islam Khondaker, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan
We then train a suite of detoxification models with our cross-platform corpus.
no code implementations • 25 Oct 2023 • Ganesh Jawahar, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan, Dujian Ding
We show that HS-NAS performs very similar to SOTA NAS across benchmarks, reduces search hours by 50% roughly, and in some cases, improves latency, GFLOPs, and model size.
1 code implementation • 17 Jun 2023 • Yuxi Feng, Xiaoyuan Yi, Laks V. S. Lakshmanan, Xing Xie
Self-training (ST) has come to fruition in language understanding tasks by producing pseudo labels, which reduces the labeling bottleneck of language model fine-tuning.
no code implementations • 8 Jun 2023 • Ganesh Jawahar, Haichuan Yang, Yunyang Xiong, Zechun Liu, Dilin Wang, Fei Sun, Meng Li, Aasish Pappu, Barlas Oguz, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan, Raghuraman Krishnamoorthi, Vikas Chandra
In addition, the proposed method achieves the SOTA performance in NAS for building fast machine translation models, yielding better latency-BLEU tradeoff compared to HAT, state-of-the-art NAS for MT.
1 code implementation • 16 Dec 2022 • Yuxi Feng, Xiaoyuan Yi, Xiting Wang, Laks V. S. Lakshmanan, Xing Xie
Augmented by only self-generated pseudo text, generation models over-emphasize exploitation of the previously learned space, suffering from a constrained generalization boundary.
no code implementations • 11 Nov 2022 • Md Tawkat Islam Khondaker, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan
The prevalence of abusive language on different online platforms has been a major concern that raises the need for automated cross-platform abusive language detection.
1 code implementation • 22 Oct 2022 • Md Tawkat Islam Khondaker, El Moatez Billah Nagoudi, AbdelRahim Elmadany, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan
Contrastive learning (CL) brought significant progress to various NLP tasks.
1 code implementation • 14 Oct 2022 • Ganesh Jawahar, Subhabrata Mukherjee, Xiaodong Liu, Young Jin Kim, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan, Ahmed Hassan Awadallah, Sebastien Bubeck, Jianfeng Gao
Furthermore, existing MoE works do not consider computational constraints (e. g., FLOPs, latency) to guide their design.
no code implementations • 6 Oct 2022 • Ganesh Jawahar, Subhabrata Mukherjee, Debadeepta Dey, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan, Caio Cesar Teodoro Mendes, Gustavo Henrique de Rosa, Shital Shah
In this work, we study the more challenging open-domain setting consisting of low frequency user prompt patterns (or broad prompts, e. g., prompt about 93rd academy awards) and demonstrate the effectiveness of character-based language models.
1 code implementation • ACL 2022 • Ganesh Jawahar, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan
We propose a neural network based detector that detects manipulated news articles by reasoning about the facts mentioned in the article.
no code implementations • NAACL (CALCS) 2021 • Ganesh Jawahar, El Moatez Billah Nagoudi, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan
We describe models focused at the understudied problem of translating between monolingual and code-mixed language pairs.
no code implementations • 6 Dec 2020 • Prithu Banerjee, Wei Chen, Laks V. S. Lakshmanan
Competitive IM focuses on the propagation of competing items in the network.
1 code implementation • COLING 2020 • Ganesh Jawahar, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan
Detectors that can distinguish text generated by TGM from human written text play a vital role in mitigating such misuse of TGMs.
2 code implementations • 15 May 2017 • Wei Lu, Xiaokui Xiao, Amit Goyal, Keke Huang, Laks V. S. Lakshmanan
In a recent SIGMOD paper titled "Debunking the Myths of Influence Maximization: An In-Depth Benchmarking Study", Arora et al. [1] undertake a performance benchmarking study of several well-known algorithms for influence maximization.
Social and Information Networks