Most state-of-the-art techniques for Language Models (LMs) today rely on transformer-based architectures and their ubiquitous attention mechanism. However, the exponential growth in computational requirements with longer input sequences confines Transformers to handling short passages. Recent efforts have aimed to address this limitation by introducing selective attention mechanisms, notably local and global attention. While sparse attention mechanisms, akin to full attention in being Turing-complete, have been theoretically established, their practical impact on pre-training remains unexplored. This study focuses on empirically assessing the influence of global attention on BERT pre-training. The primary steps involve creating an extensive corpus of structure-aware text through arXiv data, alongside a text-only counterpart. We carry out pre-training on these two datasets, investigate shifts in attention patterns, and assess their implications for downstream tasks. Our analysis underscores the significance of incorporating document structure into LM models, demonstrating their capacity to excel in more abstract tasks, such as document understanding.
Mila（米拉研究所）；Université de Montréal（蒙特利尔大学）；Google Research（谷歌研究院）
There are two major classes of natural language grammar -- the dependency grammar that models one-to-one correspondences between words and the constituency grammar that models the assembly of one or several corresponded words. While previous unsupervised parsing methods mostly focus on only inducing one class of grammars, we introduce a novel model, StructFormer, that can simultaneously induce dependency and constituency structure. To achieve this, we propose a new parsing framework that can jointly generate a constituency tree and dependency graph. Then we integrate the induced dependency rel…
LiMe: a Latin Corpus of Late Medieval Criminal Sentences
Università degli Studi di Milano, Department of Italian and Supranational Public Law（米兰大学意大利与超国家公共法系）；Università degli Studi di Milano, Department of Historical Studies（米兰大学历史学系）；Università degli Studi di Milano, Department of Computer Science（米兰大学计算机科学系）
Document-level relation extraction aims to extract relations among entities within a document. Compared with its sentence-level counterpart, Document-level relation extraction requires inference over multiple sentences to extract complex relational triples. Previous research normally complete reasoning through information propagation on the mention-level or entity-level document-graphs, regardless of the correlations between the relationships. In this paper, we propose a novel Document-level Relation Extraction model based on a Masked Image Reconstruction network (DRE-MIR), which models infere…
University of British Columbia（不列颠哥伦比亚大学）；Allen Institute for AI（艾伦人工智能研究所）；University of Washington（华盛顿大学）
We introduce PRIMERA, a pre-trained model for multi-document representation with a focus on summarization that reduces the need for dataset-specific architectures and large amounts of fine-tuning labeled data. PRIMERA uses our newly proposed pre-training objective designed to teach the model to connect and aggregate information across documents. It also uses efficient encoder-decoder transformers to simplify the processing of concatenated input documents. With extensive experiments on 6 multi-document summarization datasets from 3 different domains on zero-shot, few-shot and full-supervised se…
Much of natural language processing is focused on leveraging large capacity language models, typically trained over single messages with a task of predicting one or more tokens. However, modeling human language at higher-levels of context (i.e., sequences of messages) is under-explored. In stance detection and other social media tasks where the goal is to predict an attribute of a message, we have contextual data that is loosely semantically connected by authorship. Here, we introduce Message-Level Transformer (MeLT) -- a hierarchical message-encoder pre-trained over Twitter and applied to the…
We show that a simple unsupervised masking objective can approach near supervised performance on abstractive multi-document news summarization. Our method trains a state-of-the-art neural summarization model to predict the masked out source document with highest lexical centrality relative to the multi-document group. In experiments on the Multi-News dataset, our masked training objective yields a system that outperforms past unsupervised methods and, in human evaluation, surpasses the best supervised method without requiring access to any ground-truth summaries. Further, we evaluate how diffe…
We introduce CM3, a family of causally masked generative models trained over a large corpus of structured multi-modal documents that can contain both text and image tokens. Our new causally masked approach generates tokens left to right while also masking out a small number of long token spans that are generated at the end of the string, instead of their original positions. The casual masking object provides a type of hybrid of the more common causal and masked language models, by enabling full generative modeling while also providing bidirectional context when generating the masked spans. We …
Bar-Ilan University（巴伊兰大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；University of Washington（华盛顿大学）
We introduce a new pretraining approach geared for multi-document language modeling, incorporating two key ideas into the masked language modeling self-supervised objective. First, instead of considering documents in isolation, we pretrain over sets of multiple related documents, encouraging the model to learn cross-document relationships. Second, we improve over recent long-range transformers by introducing dynamic global attention that has access to the entire input to predict masked tokens. We release CDLM (Cross-Document Language Model), a new general language model for multi-document sett…
Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection
Graduate School of Artificial Intelligence, POSTECH, Republic of Korea（人工智能研究生院，POSTECH，韩国）；Department of Computer Science and Engineering, POSTECH, Republic of Korea（计算机科学与工程系，POSTECH，韩国）
Alibaba Group（阿里巴巴集团）；The University of New South Wales（新南威尔士大学）；A*STAR Centre for Frontier AI Research（新加坡科技研究局前沿人工智能研究中心）；Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
Keyphrase extraction (KPE) automatically extracts phrases in a document that provide a concise summary of the core content, which benefits downstream information retrieval and NLP tasks. Previous state-of-the-art (SOTA) methods select candidate keyphrases based on the similarity between learned representations of the candidates and the document. They suffer performance degradation on long documents due to discrepancy between sequence lengths which causes mismatch between representations of keyphrase candidates and the document. In this work, we propose a novel unsupervised embedding-based KPE …
South China University of Technology（华南理工大学）；HKUST（香港科技大学）；University of Illinois, Urbana Champaign（伊利诺伊大学厄巴纳-香槟分校）；Stanford University（斯坦福大学）
Solving text classification in a weakly supervised manner is important for real-world applications where human annotations are scarce. In this paper, we propose to query a masked language model with cloze style prompts to obtain supervision signals. We design a prompt which combines the document itself and "this article is talking about [MASK]." A masked language model can generate words for the [MASK] token. The generated words which summarize the content of a document can be utilized as supervision signals. We propose a latent variable model to learn a word distribution learner which associa…
The Hebrew University of Jerusalem（耶路撒冷希伯来大学）；IBM Research（IBM研究院）
We present models which complete missing text given transliterations of ancient Mesopotamian documents, originally written on cuneiform clay tablets (2500 BCE - 100 CE). Due to the tablets' deterioration, scholars often rely on contextual cues to manually fill in missing parts in the text in a subjective and time-consuming process. We identify that this challenge can be formulated as a masked language modelling task, used mostly as a pretraining objective for contextualized language models. Following, we develop several architectures focusing on the Akkadian language, the lingua franca of the …
University of Washington（华盛顿大学）；Google Research（谷歌研究院）
In this paper, we introduce DOCmT5, a multilingual sequence-to-sequence language model pretrained with large scale parallel documents. While previous approaches have focused on leveraging sentence-level parallel data, we try to build a general-purpose pretrained model that can understand and generate long documents. We propose a simple and effective pretraining objective - Document reordering Machine Translation (DrMT), in which the input documents that are shuffled and masked need to be translated. DrMT brings consistent improvements over strong baselines on a variety of document-level genera…
StatNLP Research Group, Singapore University of Technology and Design（新加坡科技设计大学StatNLP研究组）；Microsoft Research Asia, Beijing, China（微软亚洲研究院，北京）
Abstractive document summarization is usually modeled as a sequence-to-sequence (Seq2Seq) learning problem. Unfortunately, training large Seq2Seq based summarization models on limited supervised summarization data is challenging. This paper presents three pre-training objectives which allow us to pre-train a Seq2Seq based abstractive summarization model on unlabeled text. The main idea is that, given an input text artificially constructed from a document, a model is pre-trained to reinstate the original document. These objectives include sentence reordering, next sentence generation, and maske…
Sun Yat-sen University（中山大学）；Microsoft Research Asia（微软亚洲研究院）
Self-supervised pre-training techniques have achieved remarkable progress in Document AI. Most multimodal pre-trained models use a masked language modeling objective to learn bidirectional representations on the text modality, but they differ in pre-training objectives for the image modality. This discrepancy adds difficulty to multimodal representation learning. In this paper, we propose \textbf{LayoutLMv3} to pre-train multimodal Transformers for Document AI with unified text and image masking. Additionally, LayoutLMv3 is pre-trained with a word-patch alignment objective to learn cross-modal…
University of California, San Diego（加州大学圣迭戈分校）；University of Maryland（马里兰大学）
We present a self-supervised pre-training approach for learning rich visual language representations for both handwritten and printed historical document transcription. After supervised fine-tuning of our pre-trained encoder representations for low-resource document transcription on two languages, (1) a heterogeneous set of handwritten Islamicate manuscript images and (2) early modern English printed documents, we show a meaningful improvement in recognition accuracy over the same supervised model trained from scratch with as few as 30 line image transcriptions for training. Our masked languag…
Language use differs between domains and even within a domain, language use changes over time. For pre-trained language models like BERT, domain adaptation through continued pre-training has been shown to improve performance on in-domain downstream tasks. In this article, we investigate whether temporal adaptation can bring additional benefits. For this purpose, we introduce a corpus of social media comments sampled over three years. It contains unlabelled data for adaptation and evaluation on an upstream masked language modelling task as well as labelled data for fine-tuning and evaluation on…
Harbin Institute of Technology（哈尔滨工业大学）；Microsoft Research Asia（微软亚洲研究院）；Microsoft Azure AI（微软 Azure AI）；Soochow University（苏州大学）
Pre-training of text and layout has proved effective in a variety of visually-rich document understanding tasks due to its effective model architecture and the advantage of large-scale unlabeled scanned/digital-born documents. We propose LayoutLMv2 architecture with new pre-training tasks to model the interaction among text, layout, and image in a single multi-modal framework. Specifically, with a two-stream multi-modal Transformer encoder, LayoutLMv2 uses not only the existing masked visual-language modeling task but also the new text-image alignment and text-image matching tasks, which make …
Moscow Institute of Physics and Technology（莫斯科物理技术学院）
Transformer variants dominate the state-of-the-art in different natural language processing tasks such as translation, reading comprehension and summarization. Our paper is more directed to use general memory slots added to the inputs and studying the results of adding these slots. This paper is a go on study of general memory slots rule that were added to the input of the proposed model in previous work. We have two main tasks;1) pretraining task using masked language modeling and b) fine tuning task using HotpotQA . This study aims to verify the ability of the proposed model to handle chunks…
Many natural language processing and information retrieval problems can be formalized as the task of semantic matching. Existing work in this area has been largely focused on matching between short texts (e.g., question answering), or between a short and a long text (e.g., ad-hoc retrieval). Semantic matching between long-form documents, which has many important applications like news recommendation, related article recommendation and document clustering, is relatively less explored and needs more research effort. In recent years, self-attention based models like Transformers and BERT have ach…
The Chinese University of Hong Kong（香港中文大学）；Tencent AI Lab（腾讯AI Lab）
In recent years, reference-based and supervised summarization evaluation metrics have been widely explored. However, collecting human-annotated references and ratings are costly and time-consuming. To avoid these limitations, we propose a training-free and reference-free summarization evaluation metric. Our metric consists of a centrality-weighted relevance score and a self-referenced redundancy score. The relevance score is computed between the pseudo reference built from the source document and the given summary, where the pseudo reference content is weighted by the sentence centrality to pr…
Unsupervised pre-training on millions of digital-born or scanned documents has shown promising advances in visual document understanding~(VDU). While various vision-language pre-training objectives are studied in existing solutions, the document textline, as an intrinsic granularity in VDU, has seldom been explored so far. A document textline usually contains words that are spatially and semantically correlated, which can be easily obtained from OCR engines. In this paper, we propose Wukong-Reader, trained with new pre-training objectives to leverage the structural knowledge nested in document…
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 documents. In this work, we propose LinkBERT, an LM pretraining method that leverages links between documents, e.g., hyperlinks. Given a text corpus, we view it as a graph of documents and create LM inputs by placing linked documents in the same context. We then pretrain the LM with two joint self-supervised objectives: masked language modeling and our new proposal, …
University of Tehran（德黑兰大学）；Institute for Research in Fundamental Sciences (IPM)（基础科学研究研究所（IPM））
Abstractive text summarization is one of the areas influenced by the emergence of pre-trained language models. Current pre-training works in abstractive summarization give more points to the summaries with more words in common with the main text and pay less attention to the semantic similarity between generated sentences and the original document. We propose ARMAN, a Transformer-based encoder-decoder model pre-trained with three novel objectives to address this issue. In ARMAN, salient sentences from a document are selected according to a modified semantic score to be masked and form a pseudo…
Due to the complex layouts of documents, it is challenging to extract information for documents. Most previous studies develop multimodal pre-trained models in a self-supervised way. In this paper, we focus on the embedding learning of word blocks containing text and layout information, and propose UTel, a language model with Unified TExt and Layout pre-training. Specifically, we propose two pre-training tasks: Surrounding Word Prediction (SWP) for the layout learning, and Contrastive learning of Word Embeddings (CWE) for identifying different word blocks. Moreover, we replace the commonly use…
We present a simple approach for text infilling, the task of predicting missing spans of text at any position in a document. While infilling could enable rich functionality especially for writing assistance tools, more attention has been devoted to language modeling---a special case of infilling where text is predicted at the end of a document. In this paper, we aim to extend the capabilities of language models (LMs) to the more general task of infilling. To this end, we train (or fine-tune) off-the-shelf LMs on sequences containing the concatenation of artificially-masked text and the text wh…
While Transformer language models (LMs) are state-of-the-art for information extraction, long text introduces computational challenges requiring suboptimal preprocessing steps or alternative model architectures. Sparse attention LMs can represent longer sequences, overcoming performance hurdles. However, it remains unclear how to explain predictions from these models, as not all tokens attend to each other in the self-attention layers, and long sequences pose computational challenges for explainability algorithms when runtime depends on document length. These challenges are severe in the medic…
Tohoku University（东北大学）；Riken Center for Advanced Intelligence Project（理化学研究所先进智能项目中心）；Stony Brook University（石溪大学）
Existing approaches for automated essay scoring and document representation learning typically rely on discourse parsers to incorporate discourse structure into text representation. However, the performance of parsers is not always adequate, especially when they are used on noisy texts, such as student essays. In this paper, we propose an unsupervised pre-training approach to capture discourse structure of essays in terms of coherence and cohesion that does not require any discourse parser or annotation. We introduce several types of token, sentence and paragraph-level corruption techniques fo…
Filipino Benchmarks for Measuring Sexist and Homophobic Bias in Multilingual Language Models from Southeast Asia
School of Computer Science, University of Birmingham（英国伯明翰大学计算机科学学院）；Department of Information Systems and Computer Science, Ateneo de Manila University（马尼拉亚托大学信息系统与计算机科学系）
We introduce MARGE, a pre-trained sequence-to-sequence model learned with an unsupervised multi-lingual multi-document paraphrasing objective. MARGE provides an alternative to the dominant masked language modeling paradigm, where we self-supervise the reconstruction of target text by retrieving a set of related texts (in many languages) and conditioning on them to maximize the likelihood of generating the original. We show it is possible to jointly learn to do retrieval and reconstruction, given only a random initialization. The objective noisily captures aspects of paraphrase, translation, mu…
Language exhibits structure at different scales, ranging from subwords to words, sentences, paragraphs, and documents. To what extent do deep models capture information at these scales, and can we force them to better capture structure across this hierarchy? We approach this question by focusing on individual neurons, analyzing the behavior of their activations at different timescales. We show that signal processing provides a natural framework for separating structure across scales, enabling us to 1) disentangle scale-specific information in existing embeddings and 2) train models to learn mo…
Baidu Inc.（百度公司）；Beijing University of Posts and Telecommunications（北京邮电大学）；Taikang Insurance Group（泰康保险集团）
Structured text understanding on Visually Rich Documents (VRDs) is a crucial part of Document Intelligence. Due to the complexity of content and layout in VRDs, structured text understanding has been a challenging task. Most existing studies decoupled this problem into two sub-tasks: entity labeling and entity linking, which require an entire understanding of the context of documents at both token and segment levels. However, little work has been concerned with the solutions that efficiently extract the structured data from different levels. This paper proposes a unified framework named StrucT…
Imperial College London（伦敦帝国学院）；Google Research（谷歌研究院）
Recent work pre-training Transformers with self-supervised objectives on large text corpora has shown great success when fine-tuned on downstream NLP tasks including text summarization. However, pre-training objectives tailored for abstractive text summarization have not been explored. Furthermore there is a lack of systematic evaluation across diverse domains. In this work, we propose pre-training large Transformer-based encoder-decoder models on massive text corpora with a new self-supervised objective. In PEGASUS, important sentences are removed/masked from an input document and are generat…
Language model pre-training has been shown to capture a surprising amount of world knowledge, crucial for NLP tasks such as question answering. However, this knowledge is stored implicitly in the parameters of a neural network, requiring ever-larger networks to cover more facts. To capture knowledge in a more modular and interpretable way, we augment language model pre-training with a latent knowledge retriever, which allows the model to retrieve and attend over documents from a large corpus such as Wikipedia, used during pre-training, fine-tuning and inference. For the first time, we show how…
