17 citations · 44 across the 20 of their papers we have counts for
15 papers · 1 filter
Multistage Collaborative Knowledge Distillation from a Large Language Model for Semi-Supervised Sequence Generation
Jiachen Zhao, Wenlong Zhao, Andrew Drozdov +5
We study semi-supervised sequence generation tasks, where the few labeled examples are too scarce to finetune a model, and meanwhile, few-shot prompted large language models (LLMs)…
Ensemble-Instruct: Generating Instruction-Tuning Data with a Heterogeneous Mixture of LMs
Young-Suk Lee, Md Arafat Sultan, Yousef El-Kurdi +4
Using in-context learning (ICL) for data generation, techniques such as Self-Instruct (Wang et al., 2023) or the follow-up Alpaca (Taori et al., 2023) can train strong conversation…
PrimeQA: The Prime Repository for State-of-the-Art Multilingual Question Answering Research and Development
Avirup Sil, Jaydeep Sen, Bhavani Iyer +12
The field of Question Answering (QA) has made remarkable progress in recent years, thanks to the advent of large pre-trained language models, newer realistic benchmark datasets wit…
SPARTAN: Sparse Hierarchical Memory for Parameter-Efficient Transformers
Ameet Deshpande, Md Arafat Sultan, Anthony Ferritto +3
Fine-tuning pre-trained language models (PLMs) achieves impressive performance on a range of downstream tasks, and their sizes have consequently been getting bigger. Since a differ…
GAAMA 2.0: An Integrated System that Answers Boolean and Extractive Questions
Scott McCarley, Mihaela Bornea, Sara Rosenthal +4
Recent machine reading comprehension datasets include extractive and boolean questions but current approaches do not offer integrated support for answering both question types. We…
Not to Overfit or Underfit the Source Domains? An Empirical Study of Domain Generalization in Question Answering
Md Arafat Sultan, Avirup Sil, Radu Florian
Machine learning models are prone to overfitting their training (source) domains, which is commonly believed to be the reason why they falter in novel target domains. Here we exami…
Entity-Conditioned Question Generation for Robust Attention Distribution in Neural Information Retrieval
Revanth Gangi Reddy, Md Arafat Sultan, Martin Franz +2
We show that supervised neural information retrieval (IR) models are prone to learning sparse attention patterns over passage tokens, which can result in key phrases including name…
Synthetic Target Domain Supervision for Open Retrieval QA
Revanth Gangi Reddy, Bhavani Iyer, Md Arafat Sultan +5
Neural passage retrieval is a new and promising approach in open retrieval question answering. In this work, we stress-test the Dense Passage Retriever (DPR) -- a state-of-the-art…
Learning Cross-Lingual IR from an English Retriever
Yulong Li, Martin Franz, Md Arafat Sultan +3
We present DR.DECR (Dense Retrieval with Distillation-Enhanced Cross-Lingual Representation), a new cross-lingual information retrieval (CLIR) system trained using multi-stage know…
Towards Robust Neural Retrieval Models with Synthetic Pre-Training
Revanth Gangi Reddy, Vikas Yadav, Md Arafat Sultan +4
Recent work has shown that commonly available machine reading comprehension (MRC) datasets can be used to train high-performance neural information retrieval (IR) systems. However,…
End-to-End QA on COVID-19: Domain Adaptation with Synthetic Training
Revanth Gangi Reddy, Bhavani Iyer, Md Arafat Sultan +5
End-to-end question answering (QA) requires both information retrieval (IR) over a large document collection and machine reading comprehension (MRC) on the retrieved passages. Rece…
Answer Span Correction in Machine Reading Comprehension
Revanth Gangi Reddy, Md Arafat Sultan, Efsun Sarioglu Kayi +3
Answer validation in machine reading comprehension (MRC) consists of verifying an extracted answer against an input context and question pair. Previous work has looked at re-assess…
Improved Synthetic Training for Reading Comprehension
Yanda Chen, Md Arafat Sultan, Vittorio Castelli
Automatically generated synthetic training examples have been shown to improve performance in machine reading comprehension (MRC). Compared to human annotated gold standard data, s…
Multi-Stage Pre-training for Low-Resource Domain Adaptation
Rong Zhang, Revanth Gangi Reddy, Md Arafat Sultan +7
Transfer learning techniques are particularly useful in NLP tasks where a sizable amount of high-quality annotated data is difficult to obtain. Current approaches directly adapt a…
GPT-too: A language-model-first approach for AMR-to-text generation
Manuel Mager, Ramon Fernandez Astudillo, Tahira Naseem +4
Meaning Representations (AMRs) are broad-coverage sentence-level semantic graphs. Existing approaches to generating text from AMR have focused on training sequence-to-sequence or g…