Related papers: Distilling Dense Representations for Ranking using…
Deep models are susceptible to learning spurious correlations, even during the post-processing. We take a closer look at the knowledge distillation -- a popular post-processing technique for model compression -- and find that distilling…
Neural approaches to ranking based on pre-trained language models are highly effective in ad-hoc search. However, the computational expense of these models can limit their application. As such, a process known as knowledge distillation is…
Deep learning for Information Retrieval (IR) requires a large amount of high-quality query-document relevance labels, but such labels are inherently sparse. Label smoothing redistributes some observed probability mass over unobserved…
Recent work has shown that more effective dense retrieval models can be obtained by distilling ranking knowledge from an existing base re-ranking model. In this paper, we propose a generic curriculum learning based optimization framework…
Owing to their powerful semantic reasoning capabilities, Large Language Models (LLMs) have been effectively utilized as recommenders, achieving impressive performance. However, the high inference latency of LLMs significantly restricts…
Knowledge distillation can be a cost-effective technique to distill knowledge in Large Language Models, if the teacher output logits can be pre-computed and cached. However, successfully applying this to pre-training remains largely…
Deep and large pre-trained language models are the state-of-the-art for various natural language processing tasks. However, the huge size of these models could be a deterrent to use them in practice. Some recent and concurrent works use…
The use of large transformer-based models such as BERT, GPT, and T5 has led to significant advancements in natural language processing. However, these models are computationally expensive, necessitating model compression techniques that…
Knowledge Distillation (KD), which transfers the knowledge of a well-trained large model (teacher) to a small model (student), has become an important area of research for practical deployment of recommender systems. Recently, Relaxed…
Traditionally, distillation has been used to train a student model to emulate the input/output functionality of a teacher. A more useful goal than emulation, yet under-explored, is for the student to learn feature representations that…
Knowledge distillation is an effective technique that transfers knowledge from a large teacher model to a shallow student. However, just like massive classification, large scale knowledge distillation also imposes heavy computational costs…
This study proposes a method for knowledge distillation (KD) of fine-tuned Large Language Models (LLMs) into smaller, more efficient, and accurate neural networks. We specifically target the challenge of deploying these models on…
In natural language processing (NLP) tasks, slow inference speed and huge footprints in GPU usage remain the bottleneck of applying pre-trained deep models in production. As a popular method for model compression, knowledge distillation…
This study presents a novel approach for knowledge distillation (KD) from a BERT teacher model to an automatic speech recognition (ASR) model using intermediate layers. To distil the teacher's knowledge, we use an attention decoder that…
The advent of transformer-based models such as BERT has led to the rise of neural ranking models. These models have improved the effectiveness of retrieval systems well beyond that of lexical term matching models such as BM25. While…
Representation knowledge distillation aims at transferring rich information from one model to another. Common approaches for representation distillation mainly focus on the direct minimization of distance metrics between the models'…
Existing knowledge distillation methods mostly focus on distillation of teacher's prediction and intermediate activation. However, the structured representation, which arguably is one of the most critical ingredients of deep models, is…
Representation-based retrieval models, so-called bi-encoders, estimate the relevance of a document to a query by calculating the similarity of their respective embeddings. Current state-of-the-art bi-encoders are trained using an expensive…
Prior work on English monolingual retrieval has shown that a cross-encoder trained using a large number of relevance judgments for query-document pairs can be used as a teacher to train more efficient, but similarly effective, dual-encoder…
Retrieval models based on dense representations in semantic space have become an indispensable branch for first-stage retrieval. These retrievers benefit from surging advances in representation learning towards compressive global…