A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Linguistic calibration improves long-form text confidence.
New method predicts nonfactuality in LLM responses using semantic isotropy.
Paper introduces a conformer-based system for streaming language identification in long-form speech.
Adaptive Nucleus Truncation Improves Long-Form Reasoning
Streamable model improves speech recognition performance.
Express improves causal attention guarantees for language models.
Model criticism tool evaluates text coherence and structure in generated long-form text.
IPO Finance Agent extends Finance Agent v2 for SpaceX S-1 filings, improving accuracy and cost-efficiency.
Understanding and extracting of information from large documents, such as business opportunities, academic articles, medical documents and technical reports, poses challenges not present in short documents. Such large documents may be multi-themed, complex, noisy and cover diverse topics. We describe a framework that c…
A new method for document network embedding interprets and generalizes well.
A new model CDTM improves text classification by concentrating document topics.
Improved self-supervised learning for document images.
Understanding large, structured documents like scholarly articles, requests for proposals or business reports is a complex and difficult task. It involves discovering a document's overall purpose and subject(s), understanding the function and meaning of its sections and subsections, and extracting low level entities an…
We propose in this paper a new, hybrid document embedding approach in order to address the problem of document similarities with respect to the technical content. To do so, we employ a state-of-the-art graph techniques to first extract the keyphrases (composite keywords) of documents and, then, use them to score the se…
Paper develops a new unsupervised scoring function for cross-lingual document alignment.
When estimating the relevancy between a query and a document, ranking models largely neglect the mutual information among documents. A common wisdom is that if two documents are similar in terms of the same query, they are more likely to have similar relevance score. To mitigate this problem, in this paper, we propose …
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 …
Most research in reading comprehension has focused on answering questions based on individual documents or even single paragraphs. We introduce a neural model which integrates and reasons relying on information spread within documents and across multiple documents. We frame it as an inference problem on a graph. Mentio…
A scalable topic model for large document collections using MapReduce.
We develop a nested hierarchical Dirichlet process (nHDP) for hierarchical topic modeling. The nHDP is a generalization of the nested Chinese restaurant process (nCRP) that allows each word to follow its own path to a topic node according to a document-specific distribution on a shared tree. This alleviates the rigid, …
Traditional Relational Topic Models provide a way to discover the hidden topics from a document network. Many theoretical and practical tasks, such as dimensional reduction, document clustering, link prediction, benefit from this revealed knowledge. However, existing relational topic models are based on an assumption t…
Cross-lingual document alignment aims to identify pairs of documents in two distinct languages that are of comparable content or translations of each other. In this paper, we exploit the signals embedded in URLs to label web documents at scale with an average precision of 94.5% across different language pairs. We mine …
A new model analyzes document structure and customer shopping patterns.
Study improves document processing in banking with multimodal analytics.
Translating renderings (e. g. PDFs, scans) into hierarchical document structures is extensively demanded in the daily routines of many real-world applications. However, a holistic, principled approach to inferring the complete hierarchical structure of documents is missing. As a remedy, we developed "DocParser": an end…
Document clustering and topic modeling are two closely related tasks which can mutually benefit each other. Topic modeling can project documents into a topic space which facilitates effective document clustering. Cluster labels discovered by document clustering can be incorporated into topic models to extract local top…
Improved TF-IDF for word relevance in health-care social media documents.
This paper improves topic modeling by embedding words and topics together.
Develops scalable autoencoder for document networks.
Extreme multi-label text classification (XMTC) aims at tagging a document with most relevant labels from an extremely large-scale label set. It is a challenging problem especially for the tail labels because there are only few training documents to build classifier. This paper is motivated to better explore the semanti…
Contrastive learning helps linear models understand document topics.
Top2Vec finds topic vectors from documents and words without needing stop words or custom settings.
Proposes new listwise learning-to-rank models to address rating ties and document relevance.
Improves retrieval accuracy for hierarchical documents, especially for distant matches.
This paper speeds up WMD computation for multiple queries efficiently.
A neural network method for topic modeling from few documents.
DGDS uses documents to center conversations, promising broader AI understanding.
As a fundamental problem of natural language processing, it is important to measure the distance between different documents. Among the existing methods, the Word Mover's Distance (WMD) has shown remarkable success in document semantic matching for its clear physical insight as a parameter-free model. However, WMD is e…
LITE models improve query-document relevance with learnable late interactions.
The conventional solution to the recommendation problem greedily ranks individual document candidates by prediction scores. However, this method fails to optimize the slate as a whole, and hence, often struggles to capture biases caused by the page layout and document interdepedencies. The slate recommendation problem …
Latent topic models have been successfully applied as an unsupervised topic discovery technique in large document collections. With the proliferation of hypertext document collection such as the Internet, there has also been great interest in extending these approaches to hypertext [6, 9]. These approaches typically mo…
The ability to measure similarity between documents enables intelligent summarization and analysis of large corpora. Past distances between documents suffer from either an inability to incorporate semantic similarities between words or from scalability issues. As an alternative, we introduce hierarchical optimal transp…
A new neural topic model using optimal transport improves document representation and topic coherence.
Hybrid approach combines topic and graph embeddings for legal document clustering.
We introduce a novel latent grouping model for predicting the relevance of a new document to a user. The model assumes a latent group structure for both users and documents. We compared the model against a state-of-the-art method, the User Rating Profile model, where only users have a latent group structure. We estimat…
Automatically extracts hyperparameter schemas from AI library documentation.
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…
BERT model improves cross-lingual document retrieval.