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.
Vector representations of words have heralded a transformational approach to classical problems in NLP; the most popular example is word2vec. However, a single vector does not suffice to model the polysemous nature of many (frequent) words, i.e., words with multiple meanings. In this paper, we propose a three-fold appr…
DKPCA improves WSD accuracy with scarce labeled data.
Due to recent technical and scientific advances, we have a wealth of information hidden in unstructured text data such as offline/online narratives, research articles, and clinical reports. To mine these data properly, attributable to their innate ambiguity, a Word Sense Disambiguation (WSD) algorithm can avoid numbers…
We describe our language-independent unsupervised word sense induction system. This system only uses topic features to cluster different word senses in their global context topic space. Using unlabeled data, this system trains a latent Dirichlet allocation (LDA) topic model then uses it to infer the topics distribution…
In this paper, we present our method of using fixed-size ordinally forgetting encoding (FOFE) to solve the word sense disambiguation (WSD) problem. FOFE enables us to encode variable-length sequence of words into a theoretically unique fixed-size representation that can be fed into a feed forward neural network (FFNN),…
Paper develops neural network for Mandarin polyphone disambiguation.
Enhanced word embeddings boost multiclass text classification accuracy.
In supervised machine learning for author name disambiguation, negative training data are often dominantly larger than positive training data. This paper examines how the ratios of negative to positive training data can affect the performance of machine learning algorithms to disambiguate author names in bibliographic …
Fruit fly brain network learns word embeddings using sparse binary codes.
This research explores using kernels in the softmax layer for better contextual word classification.
Paper proposes MMD-Sense-Analysis for detecting word sense shifts.
Out-of-vocabulary word translation is a major problem for the translation of low-resource languages that suffer from a lack of parallel training data. This paper evaluates the contributions of target-language context models towards the translation of OOV words, specifically in those cases where OOV translations are der…
Word embeddings are ubiquitous in NLP and information retrieval, but it is unclear what they represent when the word is polysemous. Here it is shown that multiple word senses reside in linear superposition within the word embedding and simple sparse coding can recover vectors that approximately capture the senses. The …
Approaches KL divergence for learning multi-sense word distributions.
We present an LDA approach to entity disambiguation. Each topic is associated with a Wikipedia article and topics generate either content words or entity mentions. Training such models is challenging because of the topic and vocabulary size, both in the millions. We tackle these problems using a novel distributed infer…
We introduce Probabilistic FastText, a new model for word embeddings that can capture multiple word senses, sub-word structure, and uncertainty information. In particular, we represent each word with a Gaussian mixture density, where the mean of a mixture component is given by the sum of n-grams. This representation al…
We present an approach to learning multi-sense word embeddings relying both on monolingual and bilingual information. Our model consists of an encoder, which uses monolingual and bilingual context (i.e. a parallel sentence) to choose a sense for a given word, and a decoder which predicts context words based on the chos…
EviTrack improves sequential prediction in delayed disambiguation scenarios.
Paper proposes an algorithm to recover full supervision from weakly labeled data.
Model learns to discover and disambiguate entities and relations in text streams.
A new system learns entity representations to improve local entity disambiguation.
A new method for name disambiguation in academic networks using multi-view attention and recurrent neural networks.
Improves medical note processing by training model on related concepts and global context.
A coloring scheme improves graph neural networks for node disambiguation.
There is rising interest in vector-space word embeddings and their use in NLP, especially given recent methods for their fast estimation at very large scale. Nearly all this work, however, assumes a single vector per word type ignoring polysemy and thus jeopardizing their usefulness for downstream tasks. We present an …
While humor is often thought to be beyond the reach of Natural Language Processing, we show that several aspects of single-word humor correlate with simple linear directions in Word Embeddings. In particular: (a) the word vectors capture multiple aspects discussed in humor theories from various disciplines; (b) each in…
Author name disambiguation in bibliographic databases is the problem of grouping together scientific publications written by the same person, accounting for potential homonyms and/or synonyms. Among solutions to this problem, digital libraries are increasingly offering tools for authors to manually curate their publica…
We address the problem of disambiguating large scale catalogs through the definition of an unknown artist clustering task. We explore the use of metric learning techniques to learn artist embeddings directly from audio, and using a dedicated homonym artists dataset, we compare our method with a recent approach that lea…
3-manifold groups' word problem solved in nearly linear time.
DivDis learns diverse hypotheses from underspecified data to improve robustness.
Sparse-mode DMD disambiguates local and global modes in spatiotemporal data.
We explore two techniques which use color to make sense of statistical text models. One method uses in-text annotations to illustrate a model's view of particular tokens in particular documents. Another uses a high-level, "words-as-pixels" graphic to display an entire corpus. Together, these methods offer both zoomed-i…
PML-GAN tackles noisy multi-label annotations using adversarial learning.
Following a particular news story online is an important but difficult task, as the relevant information is often scattered across different domains/sources (e.g., news articles, blogs, comments, tweets), presented in various formats and language styles, and may overlap with thousands of other stories. In this work we …
This work addresses the problem of author name homonymy in the Web of Science. Aiming for an efficient, simple and straightforward solution, we introduce a novel probabilistic similarity measure for author name disambiguation based on feature overlap. Using the researcher-ID available for a subset of the Web of Science…
Entity linking is the task of mapping potentially ambiguous terms in text to their constituent entities in a knowledge base like Wikipedia. This is useful for organizing content, extracting structured data from textual documents, and in machine learning relevance applications like semantic search, knowledge graph const…
Efficient autoregressive entity linking with correction for faster, more accurate results.
Given a small corpus pertaining to a limited set of focused topics, our goal is to train embeddings that accurately capture the sense of words in the topic in spite of the limited size of . These embeddings may be used in various tasks involving . A popular strategy in limited…
Let S be a closed surface of genus at least 2. We show that a finitely generated group G which is an extension of the fundamental group H of S is word hyperbolic if and only the orbit map of the quotient group G/H on the complex of curves is a quasi-isometric embedding.This in turn is equivalent to G/H being convex coc…
FONDUE identifies ambiguous nodes in networks for better analysis.
The paper proposes a method of financial time series forecasting taking into account the semantics of news. For the semantic analysis of financial news the sampling of negative and positive words in economic sense was formed based on Loughran McDonald Master Dictionary. The sampling included the words with high frequen…
Recent work on end-to-end automatic speech recognition (ASR) has shown that the connectionist temporal classification (CTC) loss can be used to convert acoustics to phone or character sequences. Such systems are used with a dictionary and separately-trained Language Model (LM) to produce word sequences. However, they a…
Corpus poisoning can manipulate word meanings in word embeddings, affecting natural language processing tasks.
Improves biomedical entity linking with latent type modeling.
A new transformer model corrects diacritics and typos in multiple languages.
We revisit skip-gram negative sampling (SGNS), one of the most popular neural-network based approaches to learning distributed word representation. We first point out the ambiguity issue undermining the SGNS model, in the sense that the word vectors can be entirely distorted without changing the objective value. To res…
Word meaning changes over time, depending on linguistic and extra-linguistic factors. Associating a word's correct meaning in its historical context is a central challenge in diachronic research, and is relevant to a range of NLP tasks, including information retrieval and semantic search in historical texts. Bayesian m…
Enhances topic models to better handle polysemous words.