Related papers: Reproducing and Comparing Distillation Techniques …

Pre-trained language models have demonstrated superior performance in various natural language processing tasks. However, these models usually contain hundreds of millions of parameters, which limits their practicality because of latency…

Recently, various intermediate layer distillation (ILD) objectives have been shown to improve compression of BERT models via Knowledge Distillation (KD). However, a comprehensive evaluation of the objectives in both task-specific and…

Neural Machine Translation (NMT) models achieve state-of-the-art performance on many translation benchmarks. As an active research field in NMT, knowledge distillation is widely applied to enhance the model's performance by transferring…

Cross-language pre-trained models such as multilingual BERT (mBERT) have achieved significant performance in various cross-lingual downstream NLP tasks. This paper proposes a multi-level contrastive learning (ML-CTL) framework to further…

Language model pre-training, such as BERT, has significantly improved the performances of many natural language processing tasks. However, pre-trained language models are usually computationally expensive, so it is difficult to efficiently…

Ranker and retriever are two important components in dense passage retrieval. The retriever typically adopts a dual-encoder model, where queries and documents are separately input into two pre-trained models, and the vectors generated by…

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…

End-to-end intent classification using speech has numerous advantages compared to the conventional pipeline approach using automatic speech recognition (ASR), followed by natural language processing modules. It attempts to predict intent…

Response retrieval is a subset of neural ranking in which a model selects a suitable response from a set of candidates given a conversation history. Retrieval-based chat-bots are typically employed in information seeking conversational…

The exponential growth of big data has intensified the need for efficient and interpretable machine learning models that can handle diverse data characteristics while maintaining computational efficiency. Knowledge distillation has…

Large Reasoning Models(LRMs) such as OpenAI o1 and DeepSeek-R1 have shown remarkable reasoning capabilities by scaling test-time compute and generating long Chain-of-Thought(CoT). Distillation--post-training on LRMs-generated data--is a…

Large language models have recently enabled a generative paradigm for query expansion, but their high inference cost makes direct deployment difficult in practical retrieval systems. To address this issue, a retrieval-feedback-driven…

Language model (LM) pretraining can learn various knowledge from text corpora, helping downstream tasks. However, existing methods such as BERT model a single document, and do not capture dependencies or knowledge that span across…

Contextual embeddings generated by LLMs exhibit strong positional inductive biases, which can limit their ability to fully capture long-range, order-sensitive dependencies in highly structured source code. Consequently, how to further…

Zero-shot cross-lingual named entity recognition (NER) aims at transferring knowledge from annotated and rich-resource data in source languages to unlabeled and lean-resource data in target languages. Existing mainstream methods based on…

Pretrained multilingual text encoders based on neural Transformer architectures, such as multilingual BERT (mBERT) and XLM, have achieved strong performance on a myriad of language understanding tasks. Consequently, they have been adopted…

State-of-the-art cross-encoders can be fine-tuned to be highly effective in passage re-ranking. The typical fine-tuning process of cross-encoders as re-rankers requires large amounts of manually labelled data, a contrastive learning…

Computing next-token likelihood ratios between two language models (LMs) is a standard task in training paradigms such as knowledge distillation. Since this requires both models to share the same probability space, it becomes challenging…

Incremental learning targets at achieving good performance on new categories without forgetting old ones. Knowledge distillation has been shown critical in preserving the performance on old classes. Conventional methods, however,…

Multilingual BERT (mBERT), XLM-RoBERTa (XLMR) and other unsupervised multilingual encoders can effectively learn cross-lingual representation. Explicit alignment objectives based on bitexts like Europarl or MultiUN have been shown to…