Learning latent representations from long text sequences is an important first step in many natural language processing applications. Recurrent Neural Networks (RNNs) have become a cornerstone for this challenging task. However, the quality of sentences during RNN-based decoding (reconstruction) decreases with the length of the text. We propose a sequence-to-sequence, purely convolutional and deconvolutional autoencoding framework that is free of the above issue, while also being computationally efficient. The proposed method is simple, easy to implement and can be leveraged as a building block for many applications. We show empirically that compared to RNNs, our framework is better at reconstructing and correcting long paragraphs. Quantitative evaluation on semi-supervised text classification and summarization tasks demonstrate the potential for better utilization of long unlabeled text data.
Nanjing University of Science and Technology（南京理工大学）；JD AI Research（京东人工智能研究院）
Image paragraph generation is the task of producing a coherent story (usually a paragraph) that describes the visual content of an image. The problem nevertheless is not trivial especially when there are multiple descriptive and diverse gists to be considered for paragraph generation, which often happens in real images. A valid question is how to encapsulate such gists/topics that are worthy of mention from an image, and then describe the image from one topic to another but holistically with a coherent structure. In this paper, we present a new design --- Convolutional Auto-Encoding (CAE) that…
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；The Hong Kong University of Science and Technology（香港科技大学）
Graph self-supervised learning (SSL) has been vastly employed to learn representations from unlabeled graphs. Existing methods can be roughly divided into predictive learning and contrastive learning, where the latter one attracts more research attention with better empirical performance. We argue that, however, predictive models weaponed with powerful decoder could achieve comparable or even better representation power than contrastive models. In this work, we propose a Wiener Graph Deconvolutional Network (WGDN), an augmentation-adaptive decoder empowered by graph wiener filter to perform in…
Word2vec (Mikolov et al., 2013) has proven to be successful in natural language processing by capturing the semantic relationships between different words. Built on top of single-word embeddings, paragraph vectors (Le and Mikolov, 2014) find fixed-length representations for pieces of text with arbitrary lengths, such as documents, paragraphs, and sentences. In this work, we propose a novel interpretation for neural-network-based paragraph vectors by developing an unsupervised generative model whose maximum likelihood solution corresponds to traditional paragraph vectors. This probabilistic for…
Paragraph Vectors has been recently proposed as an unsupervised method for learning distributed representations for pieces of texts. In their work, the authors showed that the method can learn an embedding of movie review texts which can be leveraged for sentiment analysis. That proof of concept, while encouraging, was rather narrow. Here we consider tasks other than sentiment analysis, provide a more thorough comparison of Paragraph Vectors to other document modelling algorithms such as Latent Dirichlet Allocation, and evaluate performance of the method as we vary the dimensionality of the le…
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
Representing texts as fixed-length vectors is central to many language processing tasks. Most traditional methods build text representations based on the simple Bag-of-Words (BoW) representation, which loses the rich semantic relations between words. Recent advances in natural language processing have shown that semantically meaningful representations of words can be efficiently acquired by distributed models, making it possible to build text representations based on a better foundation called the Bag-of-Word-Embedding (BoWE) representation. However, existing text representation methods using …
Zhengzhou University（郑州大学）；University of Maryland Baltimore County（马里兰大学巴尔的摩分校）；North China University of Water Resources and Electric Power（华北水利水电大学）
We propose a new model based on the deconvolutional networks and SAX discretization to learn the representation for multivariate time series. Deconvolutional networks fully exploit the advantage the powerful expressiveness of deep neural networks in the manner of unsupervised learning. We design a network structure specifically to capture the cross-channel correlation with deconvolution, forcing the pooling operation to perform the dimension reduction along each position in the individual channel. Discretization based on Symbolic Aggregate Approximation is applied on the feature vectors to fur…
Many machine learning algorithms require the input to be represented as a fixed-length feature vector. When it comes to texts, one of the most common fixed-length features is bag-of-words. Despite their popularity, bag-of-words features have two major weaknesses: they lose the ordering of the words and they also ignore semantics of the words. For example, "powerful," "strong" and "Paris" are equally distant. In this paper, we propose Paragraph Vector, an unsupervised algorithm that learns fixed-length feature representations from variable-length pieces of texts, such as sentences, paragraphs, …
Bidirectional Long Short-Term Memory Network (Bi-LSTM) has shown promising performance in sentiment classification task. It processes inputs as sequence of information. Due to this behavior, sentiment predictions by Bi-LSTM were influenced by words sequence and the first or last phrases of the texts tend to have stronger features than other phrases. Meanwhile, in the problem scope of Indonesian sentiment analysis, phrases that express the sentiment of a document might not appear in the first or last part of the document that can lead to incorrect sentiment classification. To this end, we propo…
Institute of Mathematics and Computer Science, University of São Paulo（圣保罗大学数学与计算机科学研究所）；São Carlos Institute of Physics, University of São Paulo（圣保罗大学圣卡洛斯物理研究所）；School of Informatics, Computing and Engineering, Indiana University（印第安纳大学信息学、计算与工程学院）
With the increasing number of texts made available on the Internet, many applications have relied on text mining tools to tackle a diversity of problems. A relevant model to represent texts is the so-called word adjacency (co-occurrence) representation, which is known to capture mainly syntactical features of texts.In this study, we introduce a novel network representation that considers the semantic similarity between paragraphs. Two main properties of paragraph networks are considered: (i) their ability to incorporate characteristics that can discriminate real from artificial, shuffled manus…
A latent-variable model is introduced for text matching, inferring sentence representations by jointly optimizing generative and discriminative objectives. To alleviate typical optimization challenges in latent-variable models for text, we employ deconvolutional networks as the sequence decoder (generator), providing learned latent codes with more semantic information and better generalization. Our model, trained in an unsupervised manner, yields stronger empirical predictive performance than a decoder based on Long Short-Term Memory (LSTM), with less parameters and considerably faster trainin…
We introduce PerSenT, a dataset of crowd-sourced annotations of the sentiment expressed by the authors towards the main entities in news articles. The dataset also includes paragraph-level sentiment annotations to provide more fine-grained supervision for the task. Our benchmarks of multiple strong baselines show that this is a difficult classification task. The results also suggest that simply fine-tuning document-level representations from BERT isn't adequate for this task. Making paragraph-level decisions and aggregating them over the entire document is also ineffective. We present empirica…
This work presents a novel objective function for the unsupervised training of neural network sentence encoders. It exploits signals from paragraph-level discourse coherence to train these models to understand text. Our objective is purely discriminative, allowing us to train models many times faster than was possible under prior methods, and it yields models which perform well in extrinsic evaluations.
Distributed representations of words and paragraphs as semantic embeddings in high dimensional data are used across a number of Natural Language Understanding tasks such as retrieval, translation, and classification. In this work, we propose "Class Vectors" - a framework for learning a vector per class in the same embedding space as the word and paragraph embeddings. Similarity between these class vectors and word vectors are used as features to classify a document to a class. In experiment on several sentiment analysis tasks such as Yelp reviews and Amazon electronic product reviews, class ve…
Montclair State University（蒙特克莱尔州立大学）；Bauman State Technical University（鲍曼国立技术大学）
We describe an algorithm for automatic classification of idiomatic and literal expressions. Our starting point is that words in a given text segment, such as a paragraph, that are highranking representatives of a common topic of discussion are less likely to be a part of an idiomatic expression. Our additional hypothesis is that contexts in which idioms occur, typically, are more affective and therefore, we incorporate a simple analysis of the intensity of the emotions expressed by the contexts. We investigate the bag of words topic representation of one to three paragraphs containing an expre…
University of Freiburg（弗莱堡大学）；University of Maryland Baltimore County（马里兰大学巴尔的摩县分校）
Many real-world video-text tasks involve different levels of granularity, such as frames and words, clip and sentences or videos and paragraphs, each with distinct semantics. In this paper, we propose a Cooperative hierarchical Transformer (COOT) to leverage this hierarchy information and model the interactions between different levels of granularity and different modalities. The method consists of three major components: an attention-aware feature aggregation layer, which leverages the local temporal context (intra-level, e.g., within a clip), a contextual transformer to learn the interaction…
Antwerp University Hospital（安特卫普大学医院）；University of Antwerp（安特卫普大学）
We have three contributions in this work: 1. We explore the utility of a stacked denoising autoencoder and a paragraph vector model to learn task-independent dense patient representations directly from clinical notes. To analyze if these representations are transferable across tasks, we evaluate them in multiple supervised setups to predict patient mortality, primary diagnostic and procedural category, and gender. We compare their performance with sparse representations obtained from a bag-of-words model. We observe that the learned generalized representations significantly outperform the spar…
Academia Sinica（中央研究院）；National Taiwan Normal University（国立台湾师范大学）
In the context of natural language processing, representation learning has emerged as a newly active research subject because of its excellent performance in many applications. Learning representations of words is a pioneering study in this school of research. However, paragraph (or sentence and document) embedding learning is more suitable/reasonable for some tasks, such as sentiment classification and document summarization. Nevertheless, as far as we are aware, there is relatively less work focusing on the development of unsupervised paragraph embedding methods. Classic paragraph embedding …
International Institute of Information Technology, Hyderabad（海得拉巴国际信息技术学院）；Microsoft India（微软印度）
This paper aims to provide an unsupervised modelling approach that allows for a more flexible representation of text embeddings. It jointly encodes the words and the paragraphs as individual matrices of arbitrary column dimension with unit Frobenius norm. The representation is also linguistically motivated with the introduction of a novel similarity metric. The proposed modelling and the novel similarity metric exploits the matrix structure of embeddings. We then go on to show that the same matrices can be reshaped into vectors of unit norm and transform our problem into an optimization proble…
Taibah University（塔伊巴大学）；Facebook AI Research（脸书人工智能研究院）；The George Washington University（乔治华盛顿大学）
Modern sentence encoders are used to generate dense vector representations that capture the underlying linguistic characteristics for a sequence of words, including phrases, sentences, or paragraphs. These kinds of representations are ideal for training a classifier for an end task such as sentiment analysis, question answering and text classification. Different models have been proposed to efficiently generate general purpose sentence representations to be used in pretraining protocols. While averaging is the most commonly used efficient sentence encoder, Discrete Cosine Transform (DCT) was r…
Recently Le & Mikolov described two log-linear models, called Paragraph Vector, that can be used to learn state-of-the-art distributed representations of documents. Inspired by this work, we present Binary Paragraph Vector models: simple neural networks that learn short binary codes for fast information retrieval. We show that binary paragraph vectors outperform autoencoder-based binary codes, despite using fewer bits. We also evaluate their precision in transfer learning settings, where binary codes are inferred for documents unrelated to the training corpus. Results from these experiments in…
Capabilities to categorize a clause based on the type of situation entity (e.g., events, states and generic statements) the clause introduces to the discourse can benefit many NLP applications. Observing that the situation entity type of a clause depends on discourse functions the clause plays in a paragraph and the interpretation of discourse functions depends heavily on paragraph-wide contexts, we propose to build context-aware clause representations for predicting situation entity types of clauses. Specifically, we propose a hierarchical recurrent neural network model to read a whole paragr…
Microsoft Research Asia（微软亚洲研究院）；Peking University（北京大学）；University of Michigan（密歇根大学）
Unsupervised text embedding methods, such as Skip-gram and Paragraph Vector, have been attracting increasing attention due to their simplicity, scalability, and effectiveness. However, comparing to sophisticated deep learning architectures such as convolutional neural networks, these methods usually yield inferior results when applied to particular machine learning tasks. One possible reason is that these text embedding methods learn the representation of text in a fully unsupervised way, without leveraging the labeled information available for the task. Although the low dimensional representa…
Several popular Transformer based language models have been found to be successful for text-driven brain encoding. However, existing literature leverages only pretrained text Transformer models and has not explored the efficacy of task-specific learned Transformer representations. In this work, we explore transfer learning from representations learned for ten popular natural language processing tasks (two syntactic and eight semantic) for predicting brain responses from two diverse datasets: Pereira (subjects reading sentences from paragraphs) and Narratives (subjects listening to the spoken s…
We present a new local entity disambiguation system. The key to our system is a novel approach for learning entity representations. In our approach we learn an entity aware extension of Embedding for Language Model (ELMo) which we call Entity-ELMo (E-ELMo). Given a paragraph containing one or more named entity mentions, each mention is first defined as a function of the entire paragraph (including other mentions), then they predict the referent entities. Utilizing E-ELMo for local entity disambiguation, we outperform all of the state-of-the-art local and global models on the popular benchmarks…
Feature extraction has gained increasing attention in the field of machine learning, as in order to detect patterns, extract information, or predict future observations from big data, the urge of informative features is crucial. The process of extracting features is highly linked to dimensionality reduction as it implies the transformation of the data from a sparse high-dimensional space, to higher level meaningful abstractions. This dissertation employs Neural Networks for distributed paragraph representations, and Latent Dirichlet Allocation to capture higher level features of paragraph vect…
Otto von Guericke University Magdeburg（马格德堡奥托·冯·格里克大学）
Authorial clustering involves the grouping of documents written by the same author or team of authors without any prior positive examples of an author's writing style or thematic preferences. For authorial clustering on shorter texts (paragraph-length texts that are typically shorter than conventional documents), the document representation is particularly important: very high-dimensional feature spaces lead to data sparsity and suffer from serious consequences like the curse of dimensionality, while feature selection may lead to information loss. We propose a high-level framework which utiliz…
Video representation learning has been successful in video-text pre-training for zero-shot transfer, where each sentence is trained to be close to the paired video clips in a common feature space. For long videos, given a paragraph of description where the sentences describe different segments of the video, by matching all sentence-clip pairs, the paragraph and the full video are aligned implicitly. However, such unit-level comparison may ignore global temporal context, which inevitably limits the generalization ability. In this paper, we propose a contrastive learning framework TempCLR to com…
Generating a long, coherent text such as a paragraph requires a high-level control of different levels of relations between sentences (e.g., tense, coreference). We call such a logical connection between sentences as a (paragraph) flow. In order to produce a coherent flow of text, we explore two forms of intersentential relations in a paragraph: one is a human-created linguistical relation that forms a structure (e.g., discourse tree) and the other is a relation from latent representation learned from the sentences themselves. Our two proposed models incorporate each form of relations into doc…
We propose an end-to-end neural model for zero-shot abstractive text summarization of paragraphs, and introduce a benchmark task, ROCSumm, based on ROCStories, a subset for which we collected human summaries. In this task, five-sentence stories (paragraphs) are summarized with one sentence, using human summaries only for evaluation. We show results for extractive and human baselines to demonstrate a large abstractive gap in performance. Our model, SummAE, consists of a denoising auto-encoder that embeds sentences and paragraphs in a common space, from which either can be decoded. Summaries for…
In this paper, we study automatic question generation, the task of creating questions from corresponding text passages where some certain spans of the text can serve as the answers. We propose an Extended Answer-aware Network (EAN) which is trained with Word-based Coverage Mechanism (WCM) and decodes with Uncertainty-aware Beam Search (UBS). The EAN represents the target answer by its surrounding sentence with an encoder, and incorporates the information of the extended answer into paragraph representation with gated paragraph-to-answer attention to tackle the problem of the inadequate represe…
Harbin Institute of Technology（哈尔滨工业大学）；Microsoft Research Asia（微软亚洲研究院）；Microsoft（微软）
Natural Questions is a new challenging machine reading comprehension benchmark with two-grained answers, which are a long answer (typically a paragraph) and a short answer (one or more entities inside the long answer). Despite the effectiveness of existing methods on this benchmark, they treat these two sub-tasks individually during training while ignoring their dependencies. To address this issue, we present a novel multi-grained machine reading comprehension framework that focuses on modeling documents at their hierarchical nature, which are different levels of granularity: documents, paragr…
In this dissertation we report results of our research on dense distributed representations of text data. We propose two novel neural models for learning such representations. The first model learns representations at the document level, while the second model learns word-level representations. For document-level representations we propose Binary Paragraph Vector: a neural network models for learning binary representations of text documents, which can be used for fast document retrieval. We provide a thorough evaluation of these models and demonstrate that they outperform the seminal method in…
In this paper we propose a new language model called AGENT, which stands for Adversarial Generation and Encoding of Nested Texts. AGENT is designed for encoding, generating and refining documents that consist of a long and coherent text, such as an entire book, provided they are hierarchically annotated (nested). i.e. divided into sentences, paragraphs and chapters. The core idea of our system is learning vector representations for each level of the text hierarchy (sentences, paragraphs, etc...), and train each such representation to perform 3 tasks: The task of reconstructing the sequence of …
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；IBM Research AI（IBM研究院人工智能部门）
Existing models on Machine Reading Comprehension (MRC) require complex model architecture for effectively modeling long texts with paragraph representation and classification, thereby making inference computationally inefficient for production use. In this work, we propose VAULT: a light-weight and parallel-efficient paragraph representation for MRC based on contextualized representation from long document input, trained using a new Gaussian distribution-based objective that pays close attention to the partially correct instances that are close to the ground-truth. We validate our VAULT archit…
EPFL（洛桑联邦理工学院）；Facebook AI Research（Facebook人工智能研究部）；LORIA（洛里亚实验室）
We propose a method to learn unsupervised sentence representations in a non-compositional manner based on Generative Latent Optimization. Our approach does not impose any assumptions on how words are to be combined into a sentence representation. We discuss a simple Bag of Words model as well as a variant that models word positions. Both are trained to reconstruct the sentence based on a latent code and our model can be used to generate text. Experiments show large improvements over the related Paragraph Vectors. Compared to uSIF, we achieve a relative improvement of 5% when trained on the sam…
Assessing risk for voluminous legal documents such as request for proposal; contracts is tedious and error prone. We have developed "risk-o-meter", a framework, based on machine learning and natural language processing to review and assess risks of any legal document. Our framework uses Paragraph Vector, an unsupervised model to generate vector representation of text. This enables the framework to learn contextual relations of legal terms and generate sensible context aware embedding. The framework then feeds the vector space into a supervised classification algorithm to predict whether a para…
The growing complexity of legal cases has lead to an increasing interest in legal information retrieval systems that can effectively satisfy user-specific information needs. However, such downstream systems typically require documents to be properly formatted and segmented, which is often done with relatively simple pre-processing steps, disregarding topical coherence of segments. Systems generally rely on representations of individual sentences or paragraphs, which may lack crucial context, or document-level representations, which are too long for meaningful search results. To address this is…
Since fake news poses a serious threat to society and individuals, numerous studies have been brought by considering text, propagation and user profiles. Due to the data collection problem, these methods based on propagation and user profiles are less applicable in the early stages. A good alternative method is to detect news based on text as soon as they are released, and a lot of text-based methods were proposed, which usually utilized words, sentences or paragraphs as basic units. But, word is a too fine-grained unit to express coherent information well, sentence or paragraph is too coarse …
This paper introduces a sentence to vector encoding framework suitable for advanced natural language processing. Our latent representation is shown to encode sentences with common semantic information with similar vector representations. The vector representation is extracted from an encoder-decoder model which is trained on sentence paraphrase pairs. We demonstrate the application of the sentence representations for two different tasks -- sentence paraphrasing and paragraph summarization, making it attractive for commonly used recurrent frameworks that process text. Experimental results help …
University of Michigan（密歇根大学）；Yale University（耶鲁大学）
Modeling the structure of coherent texts is a key NLP problem. The task of coherently organizing a given set of sentences has been commonly used to build and evaluate models that understand such structure. We propose an end-to-end unsupervised deep learning approach based on the set-to-sequence framework to address this problem. Our model strongly outperforms prior methods in the order discrimination task and a novel task of ordering abstracts from scientific articles. Furthermore, our work shows that useful text representations can be obtained by learning to order sentences. Visualizing the l…
Institute of Computer Science（计算机科学研究所）；University of Wrocław（弗罗茨瓦夫大学）
In this work, we focus on a lightweight convolutional architecture that creates fixed-size vector embeddings of sentences. Such representations are useful for building NLP systems, including conversational agents. Our work derives from a recently proposed recursive convolutional architecture for auto-encoding text paragraphs at byte level. We propose alternations that significantly reduce training time, the number of parameters, and improve auto-encoding accuracy. Finally, we evaluate the representations created by our model on tasks from SentEval benchmark suite, and show that it can serve as…
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…
Institute of Mathematics and Computer Science, University of São Paulo（圣保罗大学数学与计算机科学研究所）；São Carlos Institute of Physics, University of São Paulo（圣保罗大学圣卡洛斯物理研究所）
Statistical techniques that analyze texts, referred to as text analytics, have departed from the use of simple word count statistics towards a new paradigm. Text mining now hinges on a more sophisticated set of methods, including the representations in terms of complex networks. While well-established word-adjacency (co-occurrence) methods successfully grasp syntactical features of written texts, they are unable to represent important aspects of textual data, such as its topical structure, i.e. the sequence of subjects developing at a mesoscopic level along the text. Such aspects are often ove…
Structured Memory Mechanisms for Stable Context Representation in Large Language Models
University of Pennsylvania（宾夕法尼亚大学）；Illinois Institute of Technology（伊利诺伊理工学院）；University of Michigan（密歇根大学）；University of Saskatchewan（萨斯喀彻温大学）；Fordham University（福特汉姆大学）；Northeastern University（东北大学）
