The task of dialog management is commonly decomposed into two sequential subtasks: dialog state tracking and dialog policy learning. In an end-to-end dialog system, the aim of dialog state tracking is to accurately estimate the true dialog state from noisy observations produced by the speech recognition and the natural…
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.
168,742 papers · 148 categories
Trend · papers per month
16 results for “state-tracking”
GOLOMB improves dialogue state tracking for unseen services.
problem Improving dialogue state tracking for multiple services and APIs.
method GOLOMB uses a BERT-based model that queries dialogue history with slot descriptions and values.
result GOLOMB achieves a joint goal accuracy of 53.97% on the SGD dataset.
In an end-to-end dialog system, the aim of dialog state tracking is to accurately estimate a compact representation of the current dialog status from a sequence of noisy observations produced by the speech recognition and the natural language understanding modules. This paper introduces a novel method of dialog state t…
MA-DST improves multi-domain dialog state tracking.
problem Accurate multi-domain dialog state tracking in natural language interfaces.
method Multi-attention based architecture to encode conversation history and slot semantics.
result Improves joint goal accuracy by 5% in full-data setting and up to 2% in zero-shot setting.
Transformers learn chain-of-thought reasoning for longer problems, proving length generalization.
problem Challenging problems require deeper reasoning, but how do models generalize this to longer tasks?
method Theoretical analysis of transformers on synthetic state-tracking tasks, proving length generalization through attention concentration.
result Transformers can learn chain-of-thought reasoning for longer problems, proving length generalization.
Multi-domain dialogue state tracking (DST) is a critical component for conversational AI systems. The domain ontology (i.e., specification of domains, slots, and values) of a conversational AI system is generally incomplete, making the capability for DST models to generalize to new slots, values, and domains during inf…
FastSGT improves accuracy in BERT-based DST for SGD datasets.
problem Dialog State Tracking in goal-oriented dialogue systems.
method BERT-based model with two carry-over procedures and multi-head attention.
result Significantly improved accuracy compared to baseline model.
Enhances particle filters with neural augmentation for multi-sub-state tracking.
problem Particle filters struggle with complex or approximated models and low latency requirements.
method Learning Flock (LF) uses a neural network to correct particle weights based on sub-particle relationships.
result LF improves performance, robustness, and latency in radar multi-target tracking.
Word vectors are at the core of many natural language processing tasks. Recently, there has been interest in post-processing word vectors to enrich their semantic information. In this paper, we introduce a novel word vector post-processing technique based on matrix conceptors (Jaeger2014), a family of regularized ident…
We introduce TextWorld, a sandbox learning environment for the training and evaluation of RL agents on text-based games. TextWorld is a Python library that handles interactive play-through of text games, as well as backend functions like state tracking and reward assignment. It comes with a curated list of games whose …
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…
TempoPFN models for zero-shot time series forecasting using synthetic data.
problem Efficient long-horizon prediction and reproducibility in zero-shot time series forecasting.
method Linear RNNs pre-trained on synthetic data with GatedDeltaProduct architecture and state-weaving.
result Achieves top-tier competitive performance on various benchmarks.
Machine reading using differentiable reasoning models has recently shown remarkable progress. In this context, End-to-End trainable Memory Networks, MemN2N, have demonstrated promising performance on simple natural language based reasoning tasks such as factual reasoning and basic deduction. However, other tasks, namel…
Transformers mimic Bayesian reasoning in controlled settings, revealing geometric mechanisms.
problem Verifying if transformers perform Bayesian reasoning rigorously in natural data.
method Constructing Bayesian wind tunnels with known posteriors and proving memorization impossibility.
result Transformers achieve - bit accuracy in Bayesian posteriors, while MLPs fail.
ISOMORPH: A Supply Chain Digital Twin for Simulation, Dataset Generation, and Forecasting Benchmarksstat.ML
ISOMORPH creates a digital twin for supply chain logistics, advancing time-series forecasting benchmarks.
problem Lack of public benchmarks for supply chain logistics time-series forecasting.
method Developed a digital twin simulator with interpretable parameters and modular topology, generating datasets and verifying conservation laws.
result Foundation models achieve MASE values exceeding public benchmarks at low-to-moderate horizons, supporting UQ.
HalluWorld benchmarks hallucinations in language models across diverse tasks.
problem Inconsistent benchmarks of hallucination in language models.
method Explicit reference-world formulation, synthetic and semi-synthetic environments, controlled variation of world complexity.
result Models struggle with perceptual hallucination but not multi-step state tracking.