Related papers: Learning Page Order in Shuffled WOO Releases
Recent studies have shown that language models pretrained and/or fine-tuned on randomly permuted sentences exhibit competitive performance on GLUE, putting into question the importance of word order information. Somewhat…
We propose a self-supervised learning method for long text documents based on contrastive learning. A key to our method is Shuffle and Divide (SaD), a simple text augmentation algorithm that sets up a pretext task required for contrastive…
We tested over 20 Transformer models for ranking long documents (including recent LongP models trained with FlashAttention and RankGPT models "powered" by OpenAI and Anthropic cloud APIs). We compared them with the simple FirstP baseline,…
Recent advancements in data-to-text generation largely take on the form of neural end-to-end systems. Efforts have been dedicated to improving text generation systems by changing the order of training samples in a process known as…
Long document re-ranking has been a challenging problem for neural re-rankers based on deep language models like BERT. Early work breaks the documents into short passage-like chunks. These chunks are independently mapped to scalar scores or…
Packing and shuffling tokens is a common practice in training auto-regressive language models (LMs) to prevent overfitting and improve efficiency. Typically documents are concatenated to chunks of maximum sequence length (MSL) and then…
Domain adaptation of embedding models, updating a generic embedding to the language of a specific domain, is a proven technique for domains that have insufficient data to train an effective model from scratch. Chemistry publications is one…
We study a twist on the classic secretary problem, which we term the secretary ranking problem: elements from an ordered set arrive in random order and instead of picking the maximum element, the algorithm is asked to assign a rank, or…
The ability to understand and answer questions over documents can be useful in many business and practical applications. However, documents often contain lengthy and diverse multimodal contents such as texts, figures, and tables, which are…
The problem of organizing information for multidocument summarization so that the generated summary is coherent has received relatively little attention. While sentence ordering for single document summarization can be determined from the…
Recent works show that ordering of the training data affects the model performance for Neural Machine Translation. Several approaches involving dynamic data ordering and data sharding based on curriculum learning have been analysed for the…
We present a novel Bayesian topic model for learning discourse-level document structure. Our model leverages insights from discourse theory to constrain latent topic assignments in a way that reflects the underlying organization of document…
Transformer-based pre-trained models, such as BERT, have achieved remarkable results on machine reading comprehension. However, due to the constraint of encoding length (e.g., 512 WordPiece tokens), a long document is usually split into…
We consider the large-scale query-document retrieval problem: given a query (e.g., a question), return the set of relevant documents (e.g., paragraphs containing the answer) from a large document corpus. This problem is often solved in two…
Building on insights from the grokking literature, we study character-level Transformers trained to compute modular addition from text, and focus on robustness under input-format variation rather than only in-distribution accuracy. We…
Data duplication during pretraining can degrade generalization and lead to memorization, motivating aggressive deduplication pipelines. However, at web scale, it is unclear what constitutes a ``duplicate'': beyond surface-form matches,…
The rapid advancement of Large Language Models (LLMs) has improved text understanding and generation but poses challenges in computational resources. This study proposes a curriculum learning-inspired, data-centric training strategy that…
Learning quality document embeddings is a fundamental problem in natural language processing (NLP), information retrieval (IR), recommendation systems, and search engines. Despite recent advances in the development of transformer-based…
Since their release, Transformers have revolutionized many fields from Natural Language Understanding to Computer Vision. Document Understanding (DU) was not left behind with first Transformer based models for DU dating from late 2019.…
In long structured document retrieval, existing methods typically fine-tune pre-trained language models (PLMs) using contrastive learning on datasets lacking explicit structural information. This practice suffers from two critical issues:…