arXiv research

New neural KB representation speeds up reasoning with large symbolic knowledge bases.

A new query embedding method improves KB performance on complex queries.

Given a knowledge base or KB containing (noisy) facts about common nouns or generics, such as "all trees produce oxygen" or "some animals live in forests", we consider the problem of inferring additional such facts at a precision similar to that of the starting KB. Such KBs capture general knowledge about the world, an…

Most of previous work in knowledge base (KB) completion has focused on the problem of relation extraction. In this work, we focus on the task of inferring missing entity type instances in a KB, a fundamental task for KB competition yet receives little attention. Due to the novelty of this task, we construct a large-sca…

We present efficient differentiable implementations of second-order multi-hop reasoning using a large symbolic knowledge base (KB). We introduce a new operation which can be used to compositionally construct second-order multi-hop templates in a neural model, and evaluate a number of alternative implementations, with d…

Solves TOD systems' query annotation problem without explicit annotations.

Knowledge base (KB) completion adds new facts to a KB by making inferences from existing facts, for example by inferring with high likelihood nationality(X,Y) from bornIn(X,Y). Most previous methods infer simple one-hop relational synonyms like this, or use as evidence a multi-hop relational path treated as an atomic f…

In this paper, we consider advancing web-scale knowledge extraction and alignment by integrating OpenIE extractions in the form of (subject, predicate, object) triples with Knowledge Bases (KB). Traditional techniques from universal schema and from schema mapping fall in two extremes: either they perform instance-level…

Proposes a new PBO method with theoretical guarantees.

Knowledge bases (KBs) are the backbone of many ubiquitous applications and are thus required to exhibit high precision. However, for KBs that store subjective attributes of entities, e.g., whether a movie is "kid friendly", simply estimating precision is complicated by the inherent ambiguity in measuring subjective phe…

The Knowledge Base (KB) used for real-world applications, such as booking a movie or restaurant reservation, keeps changing over time. End-to-end neural networks trained for these task-oriented dialogs are expected to be immune to any changes in the KB. However, existing approaches breakdown when asked to handle such c…

Paper tackles non-stationary kernelized bandits with near-optimal algorithm.

This paper tackles open problem of tight bounds for KBs with Bernoulli rewards.

We study the regret minimization problem in the novel setting of generalized kernelized bandits (GKBs), where we optimize an unknown function $f^*$ belonging to a reproducing kernel Hilbert space (RKHS) having access to samples generated by an exponential family (EF) reward model whose mean is a non-linear function $μ(…

Knowledge graph based simple question answering (KBSQA) is a major area of research within question answering. Although only dealing with simple questions, i.e., questions that can be answered through a single knowledge base (KB) fact, this task is neither simple nor close to being solved. Targeting on the two main ste…

We show that $\mathbb{S}ol^3\times\mathbb{E}^1$-manifolds are Seifert fibred, with general fibre the torus, and base one of the seven flat 2-orbifolds $T, Kb, \mathbb{A}, \mathbb{M}b, S(2,2,2,2), P(2,2)$ or $\mathbb{D}(2,2)$, and outline a classification of such 4-manifolds.

Dealing with previously unseen slots is a challenging problem in a real-world multi-domain dialogue state tracking task. Other approaches rely on predefined mappings to generate candidate slot keys, as well as their associated values. This, however, may fail when the key, the value, or both, are not seen during trainin…

Generative compression technique reduces neural network size and improves performance on microcontrollers.

mGENRE improves multilingual entity linking with autoregressive sequence prediction.

Training-free source selection for LLM families with shared vocabularies

TinyBayes detects crop diseases from images on edge devices with high accuracy and minimal resources.

A Kuranishi space is a topological space with a Kuranishi structure, defined by Fukaya and Ono. Kuranishi structures occur naturally on moduli spaces of J-holomorphic curves in symplectic geometry. This paper is a brief introduction to the author's book arXiv:0707.3572. Let Y be an orbifold and R a Q-algebra. We define…

Proposes a new method for conversational agents using deep learning.

Resource allocation improved using machine learning from terminal positions.

This paper develops the FastRNN and FastGRNN algorithms to address the twin RNN limitations of inaccurate training and inefficient prediction. Previous approaches have improved accuracy at the expense of prediction costs making them infeasible for resource-constrained and real-time applications. Unitary RNNs have incre…

Combines ML and KB modeling for large chaotic systems.

This paper shows that scientific discovery can be efficiently learned via compositional function trees, reducing the sample complexity.

Inference models are a key component in scaling variational inference to deep latent variable models, most notably as encoder networks in variational auto-encoders (VAEs). By replacing conventional optimization-based inference with a learned model, inference is amortized over data examples and therefore more computatio…

Approximate probabilistic inference algorithms are central to many fields. Examples include sequential Monte Carlo inference in robotics, variational inference in machine learning, and Markov chain Monte Carlo inference in statistics. A key problem faced by practitioners is measuring the accuracy of an approximate infe…

This work frames active inference through control as inference, offering robust control algorithms.

Simformer uses transformer models to perform flexible Bayesian inference.

PE-SVI reduces SVI inference complexity by finding a suitable start point.

Improved Bayesian inference for neuronal ensemble inference reduces computational cost.

Adding metadata abruptly changes network inference outcomes.

SNVI combines likelihood estimation with variational inference for efficient Bayesian inference.

Paper introduces a diagnostic for approximate inference methods.

Probabilistic inference procedures are usually coded painstakingly from scratch, for each target model and each inference algorithm. We reduce this effort by generating inference procedures from models automatically. We make this code generation modular by decomposing inference algorithms into reusable program-to-progr…

Recent efforts on combining deep models with probabilistic graphical models are promising in providing flexible models that are also easy to interpret. We propose a variational message-passing algorithm for variational inference in such models. We make three contributions. First, we propose structured inference network…

A new method for safer statistical inference after predictions.

Bayesian interpolants explain neural network inferences concisely.

Variational inference provides a powerful tool for approximate probabilistic in- ference on complex, structured models. Typical variational inference methods, however, require to use inference networks with computationally tractable proba- bility density functions. This largely limits the design and implementation of v…

New comparison shows differences in how value is incorporated in AIF and CAI.

Paper shows how to infer hidden states in neural networks analytically.

Variational Inference shows promise for Bayesian GARCH model estimation.

Post-ADC inference corrects bias in statistical inference after active data collection.

A new particle algorithm improves mean-field variational inference.

Meta-learn Bayesian inference for task-specific BNNs using amortised inference.

Bayesian method infers contextual bandit policies robustly.