Research
On-device research index

arXiv research

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.

169,181 papers · 148 categories

Trend · papers per month

25.0%50.0%75.0%100.0% · Sep 199219922001200920182026
48 results for UN General Debate Corpus

The UN General Debate Corpus analyzes speeches from UN member states to reveal their political positions.

problem Lack of data on state preferences in international politics.
method Text analysis of over 7,700 speeches from 1970-2016.
result Demonstrates how the UN General Debate Corpus can reveal country positions on various policy dimensions.

Paper uses neural word embeddings to analyze UN speeches for policy preferences and voting behavior.

problem Analyzing policy preferences and paradigm shifts in international politics.
method Applied neural word embeddings (Word2vec) to UN General Debate speeches.
result Found statistical relation between speech semantic content and voting behavior, contrary to hypothesis.

PEAR dynamically reconfigures agent roles to prevent persistent biases in multi-agent debates.

problem Persistent positional biases and sensitivity to role assignments in fixed topologies.
method Dynamic reconfiguration of agent roles and sparse topologies based on evolving agent states.
result Significantly improves average accuracy over debate baselines across multiple reasoning benchmarks.

Public debates are a common platform for presenting and juxtaposing diverging views on important issues. In this work we propose a methodology for tracking how ideas flow between participants throughout a debate. We use this approach in a case study of Oxford-style debates---a competitive format where the winner is det…

2016-04-11abs ↗pdf ↗

Paper tackles zero-shot translation by encouraging consistent agreement in models.

problem Challenges of generalizing multilingual translation without parallel data.
method Reformulated as probabilistic inference, introduced consistent agreement-based training.
result Agreement-based learning improves zero-shot translation by 2-3 BLEU points.

Two neural samplers improve high-quality sample generation from un-normalized densities.

problem Generating high-quality samples from un-normalized probability densities.
method Developed two neural samplers using deep neural networks to transform a reference distribution to a target distribution. Training schemes minimize Stein discrepancy variations.
result The proposed samplers generate samples instantaneously and perform better than traditional methods.

Nous considérons un espace topologique qui est localement isomorphe au quotient de R^k par l'action d'un groupe discret et nous l'appelons quasi-variété de dimension k. Les quasi-variétés généralisent les variétés et les V-variétés et représentent le cadre naturel pour la réduction symplectique par rapport à l'action i…

1999-04-30abs ↗pdf ↗

A novel fact-checking method using debate dynamics on knowledge graphs.

problem Fact-checking on knowledge graphs with user comprehension and interactive reasoning.
method Reinforcement learning agents debate on paths in the graph to classify facts as true or false.
result Interactive reasoning and user understanding of AI decisions on knowledge graphs.

Dans les années 1940-1970, Alexandrov et l'"École de Leningrad" ont développé une théorie très riche des surfaces singulières. Il s'agit de surfaces topologiques, munie d'une métrique intrinsèque pour laquelle on peut définir une notion de courbure, qui est une mesure de Radon. Cette classe de surfaces a de bonnes prop…

2009-06-18abs ↗pdf ↗

AI systems learn complex goals via debate with human judges.

problem Complex human goals and preferences for AI systems.
method Training agents via self-play on a debate game, where humans judge which agent gives more true, useful information.
result Boosted classifier accuracy from 48.2% to 85.2% given 4 pixels, and from 59.4% to 88.9% given 6 pixels.

Researchers solve word2vec's Corpus Replication Task to understand relational word similarities.

problem Understanding how word2vec captures relational similarities in word embeddings.
method Propose a Corpus Replication Task to generate input text for word2vec that outputs specific target relations.
result Demonstrates that word2vec can capture relational similarities in word embeddings.

Recursive KalmanNet generalizes well in noisy, out-of-distribution scenarios.

problem Generalization in noisy, out-of-distribution scenarios.
method Recurrent neural network guided by a Kalman filter.
result Recursive KalmanNet performs well in scenarios with different temporal dynamics from training data.

First-best climate policy is a uniform carbon tax which gradually rises over time. Civil servants have complicated climate policy to expand bureaucracies, politicians to create rents. Environmentalists have exaggerated climate change to gain influence, other activists have joined the climate bandwagon. Opponents to cli…

2016-08-19abs ↗pdf ↗

The un-reduction procedure introduced previously in the context of Mechanics is extended to covariant Field Theory. The new covariant un-reduction procedure is applied to the problem of shape matching of images which depend on more than one independent variable (for instance, time and an additional labelling parameter)…

2015-09-23abs ↗pdf ↗

Résumé. Nous définissons un groupoïde de Fréchet-Lie Map(S^1,X) d'ana-foncteurs du cercle vers un groupoïde de Lie X. Ceci fournit une présentation du Hom-champ Hom(S^1,\cX), où \cX est le champ différentiable associé à X. Nous appliquons cette construction au groupoïde de Lie sous-jacent au `gerbe fibré' d'une variété…

2016-02-25abs ↗pdf ↗

In this paper we consider an alternative approach to "un-reduction". This is the process where one associates to a Lagrangian system on a manifold a dynamical system on a principal bundle over that manifold, in such a way that solutions project. We show that, when written in terms of second-order ordinary differential …

2016-06-24abs ↗pdf ↗

UN-AVOIDS visualizes and detects anomalies without needing labeled data.

problem The need for a unified framework to visualize and detect anomalies.
method UN-AVOIDS is an unsupervised, nonparametric approach that transforms data into a new space (NCDF) for both visualization and detection.
result UN-AVOIDS assigns invariant anomalous scores and achieves high AUC in detecting anomalies.

RUSLAN is a large Russian speech corpus for text-to-speech.

problem Lack of high-quality annotated Russian speech data for text-to-speech.
method Developed a large annotated Russian speech corpus and trained a neural network for text-to-speech synthesis.
result Synthesized speech quality evaluated with MOS scores: 4.05 for naturalness, 3.78 for intelligibility.

ClovaCall introduces a new Korean call speech corpus for contact centers.

problem Lack of large-scale call-based speech corpora for Korean dialog scenarios.
method Development of a new large-scale Korean call-based speech corpus (ClovaCall) in a restaurant reservation domain.
result Validation of the dataset with ASR models shows its effectiveness.

Nous donnons une méthode naturelle, que nous appelons {\it "la méthode des façons"} pour stratifier la variété asymptotique associée à une application polynomiale dominante F:CnCnF: \mathbb{C}^n \to \mathbb{C}^n. La stratification obtenue est différentiable et satisfait la propriété de frontière.

2014-07-20abs ↗pdf ↗

Paper proposes using word embeddings to detect trolls in social media debates.

problem Preventing online harassment through rapid detection of offensive posts.
method Word embedding models for identifying fast-changing topics and negative content.
result GloVe model helps in discovering new keywords for trolling detection.

Simplified LSTM models improve sentiment analysis on Twitter debate data.

problem Performing sentiment analysis on long sequence data from Twitter debates.
method Developed six parameter-reduced LSTM models (slim LSTM) for faster training and reduced computational cost.
result Slim LSTM models outperform standard LSTM model in sentiment analysis of GOP Debate Twitter dataset.

How technology affects growth or employment has long been debated. With a hiatus, the debate revived once again in the form of how Information and Communications Technology, as a form of new technology, exerts on productivity and employment. Information and Communications Technology perceived as General Purpose Technol…

2017-04-05abs ↗pdf ↗

Corpus poisoning can manipulate word meanings in word embeddings, affecting natural language processing tasks.

problem Controlling word meanings via corpus modifications.
method Developed an explicit expression over corpus features to control word embeddings.
result Demonstrated the ability to manipulate word meanings in word embeddings, affecting various downstream tasks.

Unified framework improves cross-corpus EEG emotion recognition by aligning prototypes and refining decision boundaries.

problem Cross-corpus EEG emotion recognition suffers from performance degradation due to physiological variability and device inconsistencies.
method Prototype-driven Adversarial Alignment (PAA) framework with three configurations: local, contrastive, and boundary-aware.
result State-of-the-art performance improvements across four cross-corpus evaluation protocols.

The purpose of this paper is to show that any extension of a minimal Lie foliation on a compact manifold is a transversaly Riemannian g\h- foliation with trivial normal bundle. This result permits to classify the extensions of a minimal Lie foliation on a compact manifold from the Lie subgroups of its Lie group.

2006-02-08abs ↗pdf ↗

Improved embeddings by topic-sensitive attention on large corpora.

problem Capturing sense of words in limited corpora using pretrained embeddings.
method Topic-sensitive attention on large topic-rich corpora to correct sense drift in pretrained embeddings.
result Limited corpus augmentation is more effective than adapting pretrained embeddings.

We present an invariant of a three-dimensional manifold with a framed knot in it based on the Reidemeister torsion of an acyclic complex of Euclidean geometric origin. To show its nontriviality, we calculate the invariant for some framed (un)knots in lens spaces. Our invariant is related to a finite-dimensional fermion…

2006-05-06abs ↗pdf ↗

Untrained neural networks can recover natural images from few measurements.

problem Recovering natural images from a small number of measurements.
method Gradient descent on un-trained convolutional neural networks.
result Untrained neural networks can approximate reconstruct signals/images from a near minimal number of random measurements.

The theory of Vassiliev invariants deals with many modules of diagrams on which the algebra Lambda defined by Pierre Vogel acts. By specifying a quadratic simple Lie superalgebra, one obtains a character on Lambda. We show the coherence of these characters by building a map of graded algebras beetwen Lambda and a quoti…

2001-07-19abs ↗pdf ↗

We consider the volumes of classical supermanifolds such as the supersphere, complex projective superspace, and Stiefel and Grassmann supermanifolds, with respect to the natural metrics or symplectic structures. We show that the formulas for the volumes, upon certain universal normalization, can be obtained by an analy…

2015-03-23abs ↗pdf ↗

Neural User Simulator outperforms traditional ABUS in training dialogue systems.

problem Limited diversity and lack of natural language in ABUS.
method NUS learns user behavior from a corpus and generates natural language.
result NUS trained policies outperform ABUS in real user evaluations.