A new method for document network embedding interprets and generalizes well.
problem Lack of interpretability and generalization to new documents in existing methods.
method Introduces Topic-Word Attention (TWA) and Inductive Document Network Embedding (IDNE) to generate document representations.
result Achieves state-of-the-art performance on various networks and produces meaningful representations.
This paper improves topic modeling by embedding words and topics together.
problem Topic models struggle with short documents and approximate inference.
method Model each document as a mixture of word embeddings and each topic as a mixture of topic embeddings.
result The method optimizes topic embeddings to minimize semantic differences between words and topics.
New document embedding method finds more relevant tech docs.
problem Computing document similarities for technical content.
method Hybrid approach using graph techniques to extract keyphrases and score sentences.
result Proposed methods outperform baselines up to 27% in NDCG.
Word embedding maps words into a low-dimensional continuous embedding space by exploiting the local word collocation patterns in a small context window. On the other hand, topic modeling maps documents onto a low-dimensional topic space, by utilizing the global word collocation patterns in the same document. These two …
Hybrid approach combines topic and graph embeddings for legal document clustering.
problem Challenges in classifying legal texts due to domain-specific language and limited labeled data.
method Combines unsupervised topic and graph embeddings with a supervised model.
result Improves clustering quality over text-only or graph-only embeddings.
D-ETM models document topics over time using embeddings and variational inference.
problem Capturing evolving topic patterns in sequential documents.
method Combines D-LDA and word embeddings, using random walk priors and variational inference.
result D-ETM outperforms D-LDA on document completion tasks, learning more diverse and coherent topics.
SemSentSum uses embeddings to link facts across documents efficiently.
problem Linking facts across documents is challenging due to language variability.
method Develops SemSentSum, a fully data-driven model using universal and domain-specific sentence embeddings to build a semantic relation graph.
result SemSentSum achieves competitive results on multi-document summarization tasks.
While the celebrated Word2Vec technique yields semantically rich representations for individual words, there has been relatively less success in extending to generate unsupervised sentences or documents embeddings. Recent work has demonstrated that a distance measure between documents called \emph{Word Mover's Distance…
LITE models improve query-document relevance with learnable late interactions.
problem Improving query-document relevance with lower latency and storage.
method Proposes learnable late-interaction models (LITE) that use factorized query and document embeddings followed by a learnable scorer.
result Empirically, LITE outperforms previous late-interaction models in re-ranking tasks.
Proposes spherical text embedding for better directional similarity.
problem Directional similarity is more effective but unsupervised text embeddings are typically learned in Euclidean space.
method Develops a spherical generative model and an efficient optimization algorithm for unsupervised word and paragraph embeddings.
result Achieves state-of-the-art performances on various text embedding tasks.
Improves retrieval accuracy for hierarchical documents, especially for distant matches.
problem Limited expressive power of dual encoder models in hierarchical retrieval.
method Proves feasibility of DEs for HR, introduces pretrain-finetune recipe to improve long-distance retrieval.
result Pretrain-finetune boosts recall on long-distance pairs from 19% to 76%.
Neural topic models improve topic discovery in large corpora.
problem Topic discovery in large text corpora.
method Neural auto-encoder based document embedding with PLSA assumptions.
result Neural topic models outperform LDA in capturing relevant topics and perplexity.
Improved object detection for scientific document images.
problem Current object detectors fail to accurately localize regions in scientific document images.
method Revised R-CNN model with region embedding for fine-grained proposals.
result 17% mAP improvement over standard object detection models.
Improves document summarization by combining word embeddings and n-grams.
problem Exact word matching fails to measure semantic similarity between sentences.
method Uses deep embedding features and tf-idf features to improve sentence similarity measure; builds an improved sentence similarity graph; employs a submodular objective function; develops a Transformer-based compression model.
result Outperforms tf-idf based approach and achieves state-of-the-art performance on DUC04 dataset.
ETM discovers interpretable topics in large vocabularies.
problem Existing topic models fail with large, heavy-tailed vocabularies.
method Generative model combining topic models and word embeddings with variational inference.
result ETM discovers interpretable topics even with large vocabularies.
Transformer models improve query-document retrieval efficiency and accuracy.
problem Efficiently retrieve relevant documents from large corpora for query matching.
method Designed paragraph-level pre-training tasks to optimize embedding-based Transformer models.
result Transformer models significantly outperform BM-25 and non-Transformer embedding models.
Current state-of-the-art nonparametric Bayesian text clustering methods model documents through multinomial distribution on bags of words. Although these methods can effectively utilize the word burstiness representation of documents and achieve decent performance, they do not explore the sequential information of text…
Word embeddings are representations of individual words of a text document in a vector space and they are often use- ful for performing natural language pro- cessing tasks. Current state of the art al- gorithms for learning word embeddings learn vector representations from large corpora of text documents in an unsu- pe…
We introduce Gaussian Process Topic Models (GPTMs), a new family of topic models which can leverage a kernel among documents while extracting correlated topics. GPTMs can be considered a systematic generalization of the Correlated Topic Models (CTMs) using ideas from Gaussian Process (GP) based embedding. Since GPTMs w…
We propose a new model for unsupervised document embedding. Leading existing approaches either require complex inference or use recurrent neural networks (RNN) that are difficult to parallelize. We take a different route and develop a convolutional neural network (CNN) embedding model. Our CNN architecture is fully par…
Top2Vec finds topic vectors from documents and words without needing stop words or custom settings.
problem Topic modeling weaknesses, including needing known topics, stop words, and custom settings.
method Joint document and word semantic embedding to find topic vectors automatically.
result Top2Vec finds more informative and representative topics than probabilistic models.
Paper benchmarks Bengali language classification tasks using MConv-LSTM network.
problem Lack of computational resources for NLP tasks in under-resourced languages like Bengali.
method Built three datasets, BengFastText word embeddings, and MConv-LSTM network for hate speech detection, document classification, and sentiment analysis.
result BengFastText yields up to 92.30%, 82.25%, and 90.45% F1-scores in document classification, sentiment analysis, and hate speech detection respectively.
Contrastive learning helps linear models understand document topics.
problem Document classification with limited labeled data.
method Contrastive learning applied to document topic modeling.
result Linear models can recover topic posterior information from contrastive learning representations.
Conventional text classification models make a bag-of-words assumption reducing text into word occurrence counts per document. Recent algorithms such as word2vec are capable of learning semantic meaning and similarity between words in an entirely unsupervised manner using a contextual window and doing so much faster th…
FiNCAT tool automatically identifies financial numerals in documents.
problem Differentiating between in-claim and out-of-claim numerals in financial documents.
method Extracts context embeddings of numerals using BERT, then uses Logistic Regression to classify.
result Achieved a Macro F1 score of 0.8223 on validation set.
CCAligned creates a massive web document dataset for cross-lingual research.
problem Identifying comparable documents across different languages.
method Using URL signals to label web documents and mining Common Crawl corpus.
result Release of a dataset with over 392 million URL pairs from 8144 language pairs.
Paper develops a new unsupervised scoring function for cross-lingual document alignment.
problem Aligning documents across different languages for NLP tasks.
method Uses cross-lingual sentence embeddings to compute semantic distances and guides document alignment.
result The proposed scoring function outperforms current methods by 7-22% on various language pairs.
Improved TF-IDF for word relevance in health-care social media documents.
problem Determining word relevance in informal documents.
method Semantic Sensitive TF-IDF (STF-IDF) method.
result Decreased TF-IDF mean error rate by 50% to 13.7%.
Text embedding representing natural language documents in a semantic vector space can be used for document retrieval using nearest neighbor lookup. In order to study the feasibility of neural models specialized for retrieval in a semantically meaningful way, we suggest the use of the Stanford Question Answering Dataset…
Topic models are frequently used in machine learning owing to their high interpretability and modular structure. However, extending a topic model to include a supervisory signal, to incorporate pre-trained word embedding vectors and to include a nonlinear output function is not an easy task because one has to resort to…
Transform learning improves K-means clustering for document analysis.
problem Improving K-means clustering for document analysis.
method Embedding K-means clustering loss into transform learning framework and solving jointly using ADMM.
result Improves over state-of-the-art in document clustering.
The power of machine learning systems not only promises great technical progress, but risks societal harm. As a recent example, researchers have shown that popular word embedding algorithms exhibit stereotypical biases, such as gender bias. The widespread use of these algorithms in machine learning systems, from automa…
Protocol minimizes disclosure in classification tasks.
problem Ensuring minimal disclosure in classification protocols.
method Developed a protocol for multi-party classification that minimizes non-responsive document disclosure.
result Guarantees minimal disclosure of non-responsive documents.
Capturing the compositional process which maps the meaning of words to that of documents is a central challenge for researchers in Natural Language Processing and Information Retrieval. We introduce a model that is able to represent the meaning of documents by embedding them in a low dimensional vector space, while pre…
A new neural topic model using optimal transport improves document representation and topic coherence.
problem Challenges in achieving good document representation and coherent/diverse topics in existing NTMs.
method Proposes a neural topic model via optimal transport, learning topic distribution by minimising OT distance to document word distributions.
result Significantly outperforms state-of-the-art NTMs on discovering coherent and diverse topics.
Given vector representations for individual words, it is necessary to compute vector representations of sentences for many applications in a compositional manner, often using artificial neural networks. Relatively little work has explored the internal structure and properties of such sentence vectors. In this paper, we…
New examples show immersions not homologous to embeddings.
problem Tackles the question of immersions vs. embeddings in manifolds.
method Provides examples showing immersions not homologous to embeddings.
result Double points represent non-trivial homology classes.
Does adding a theorem to a paper affect its chance of acceptance? Does labeling a post with the author's gender affect the post popularity? This paper develops a method to estimate such causal effects from observational text data, adjusting for confounding features of the text such as the subject or writing quality. We…
Enhances topic models to better handle polysemous words.
problem Lack of polysemy handling in Gaussian latent Dirichlet allocation.
method Introduces a hierarchical structure to capture polysemy in Gaussian latent Dirichlet allocation.
result Significantly improves polysemy detection and provides more parsimonious topic representations.
SOLAR improves search efficiency and accuracy with sparse, orthogonal embeddings.
problem Bottleneck of indexing large dense vectors and NNS for query efficiency and accuracy.
method Proposes SOLAR embeddings: sparse, orthogonal, learned, and random vectors across multiple GPUs.
result Successfully trains 500K dimensional SOLAR embeddings for 1.6M books and multi-label classification.
Urban2Vec combines street view imagery and POIs for better urban neighborhood embeddings.
problem Lack of comprehensive representation of urban neighborhoods using heterogeneous data.
method Unsupervised multi-modal framework using CNN for visual features and bag-of-words for POI data.
result Urban2Vec achieves better performance than baseline models and comparable to fully-supervised methods.
SFBoW provides sentence embeddings with predefined dimensions.
problem Sentence embeddings problem at document-level.
method Refinement of Fuzzy Bag-of-Words, predefined dimension.
result Competitive performances in Semantic Textual Similarity benchmarks.
BERT-based word embeddings improve active learning for text datasets.
problem Efficiently labelling large text datasets for machine learning.
method Evaluation of text representation mechanisms (BERT vs. bag of words) in active learning.
result BERT-based word embeddings significantly improve active learning performance.
This paper presents a Semantic Attribute Modulation (SAM) for language modeling and style variation. The semantic attribute modulation includes various document attributes, such as titles, authors, and document categories. We consider two types of attributes, (title attributes and category attributes), and a flexible a…
HTMLPhish detects phishing web pages using deep learning on HTML content.
problem Growing phishing attacks on the web require new detection methods.
method HTMLPhish uses Convolutional Neural Networks (CNNs) to classify HTML documents as phishing or benign.
result HTMLPhish achieves over 93% accuracy in detecting phishing web pages.
Text segmentation plays an important role in various Natural Language Processing (NLP) tasks like summarization, context understanding, document indexing and document noise removal. Previous methods for this task require manual feature engineering, huge memory requirements and large execution times. To the best of our …
AEALT uses autoencoders to reduce text embedding dimensions for improved efficiency.
problem High dimensionality of text embeddings hinders downstream tasks.
method Factor-augmented supervised learning with autoencoders.
result AEALT outperforms conventional deep-learning approaches.
A novel method extracts topological features from word embeddings for text classification.
problem High dimensional and noisy text representations in natural language processing.
method Persistent homology for topological data analysis on word embeddings.
result Topological features outperform conventional text mining features on long textual documents.