Zero-shot transfer learning for document understanding is a crucial yet under-investigated scenario to help reduce the high cost involved in annotating document entities. We present a novel query-based framework, QueryForm, that extracts entity values from form-like documents in a zero-shot fashion. QueryForm contains a dual prompting mechanism that composes both the document schema and a specific entity type into a query, which is used to prompt a Transformer model to perform a single entity extraction task. Furthermore, we propose to leverage large-scale query-entity pairs generated from form-like webpages with weak HTML annotations to pre-train QueryForm. By unifying pre-training and fine-tuning into the same query-based framework, QueryForm enables models to learn from structured documents containing various entities and layouts, leading to better generalization to target document types without the need for target-specific training data. QueryForm sets new state-of-the-art average F1 score on both the XFUND (+4.6%~10.1%) and the Payment (+3.2%~9.5%) zero-shot benchmark, with a smaller model size and no additional image input.
In this work, we investigate two specific linear ADRC structures, namely output- and error-based. The former is considered a 'standard' version of ADRC, a title obtained primarily thanks to its simplicity and effectiveness, which have spurred its adoption across multiple industries. The latter is found to be especially appealing to practitioners as its feedback error-driven structure bares similarities to conventional control solutions, like PI and PID. In this paper, we describe newly found connections between the two considered ADRC structures, which allowed us to formally establish conditions for their equivalence. Furthermore, the conducted comprehensive performance comparison between output- and error-based ADRCs has facilitated the identification of specific modules within them, which can now be conveniently used as building blocks, thus aiding the control designers in customizing ADRC-based solutions and making them most suitable for their applications.
Online forms are widely used to collect data from human and have a multi-billion market. Many software products provide online services for creating semi-structured forms where questions and descriptions are organized by pre-defined structures. However, the design and creation process of forms is still tedious and requires expert knowledge. To assist form designers, in this work we present FormLM to model online forms (by enhancing pre-trained language model with form structural information) and recommend form creation ideas (including question / options recommendations and block type suggestion). For model training and evaluation, we collect the first public online form dataset with 62K online forms. Experiment results show that FormLM significantly outperforms general-purpose language models on all tasks, with an improvement by 4.71 on Question Recommendation and 10.6 on Block Type Suggestion in terms of ROUGE-1 and Macro-F1, respectively.
We present SLATE, a sequence labeling approach for extracting tasks from free-form content such as digitally handwritten (or "inked") notes on a virtual whiteboard. Our approach allows us to create a single, low-latency model to simultaneously perform sentence segmentation and classification of these sentences into task/non-task sentences. SLATE greatly outperforms a baseline two-model (sentence segmentation followed by classification model) approach, achieving a task F1 score of 84.4%, a sentence segmentation (boundary similarity) score of 88.4% and three times lower latency compared to the baseline. Furthermore, we provide insights into tackling challenges of performing NLP on the inking domain. We release both our code and dataset for this novel task.
The horseshoe prior is known to possess many desirable properties for Bayesian estimation of sparse parameter vectors, yet its density function lacks an analytic form. As such, it is challenging to find a closed-form solution for the posterior mode. Conventional horseshoe estimators use the posterior mean to estimate the parameters, but these estimates are not sparse. We propose a novel expectation-maximisation (EM) procedure for computing the MAP estimates of the parameters in the case of the standard linear model. A particular strength of our approach is that the M-step depends only on the form of the prior and it is independent of the form of the likelihood. We introduce several simple modifications of this EM procedure that allow for straightforward extension to generalised linear models. In experiments performed on simulated and real data, our approach performs comparable, or superior to, state-of-the-art sparse estimation methods in terms of statistical performance and computational cost.
Knowledge proximity refers to the strength of association between any two entities in a structural form that embodies certain aspects of a knowledge base. In this work, we operationalize knowledge proximity within the context of the US Patent Database (knowledge base) using a knowledge graph (structural form) named PatNet built using patent metadata, including citations, inventors, assignees, and domain classifications. We train various graph embedding models using PatNet to obtain the embeddings of entities and relations. The cosine similarity between the corresponding (or transformed) embeddings of entities denotes the knowledge proximity between these. We compare the embedding models in terms of their performances in predicting target entities and explaining domain expansion profiles of inventors and assignees. We then apply the embeddings of the best-preferred model to associate homogeneous (e.g., patent-patent) and heterogeneous (e.g., inventor-assignee) pairs of entities.
Online retailers and platforms typically present alternatives using ranked product lists. By adjusting the ranking, these platforms influence consumers' choices and, in turn, conversions, platform revenues, and consumer welfare. In this paper, I study the trade-offs between ranking algorithms that target these different objectives. First, I highlight and provide reduced-form evidence for a key factor shaping these trade-offs: cross-product heterogeneity in position effects. To quantify the effects of different rankings, I then develop an empirical framework based on the search and discovery model of Greminger (2022). For this framework, I show that the ranking that maximizes conversions also maximizes consumer welfare, implying no trade-off between these two objectives. Moreover, I develop and test a heuristic ranking algorithm to maximize revenues. Finally, I estimate the model and compare the effects of the rankings developed for the different objectives. The results highlight the effectiveness of the different rankings and reveal that the proposed heuristic to maximize revenues also increases consumer welfare, suggesting that the trade-off between revenue maximization and consumer welfare also is limited.
Large language models (LLMs) have been shown to perform well in answering questions and in producing long-form texts, both in few-shot closed-book settings. While the former can be validated using well-known evaluation metrics, the latter is difficult to evaluate. We resolve the difficulties to evaluate long-form output by doing both tasks at once -- to do question answering that requires long-form answers. Such questions tend to be multifaceted, i.e., they may have ambiguities and/or require information from multiple sources. To this end, we define query refinement prompts that encourage LLMs to explicitly express the multifacetedness in questions and generate long-form answers covering multiple facets of the question. Our experiments on two long-form question answering datasets, ASQA and AQuAMuSe, show that using our prompts allows us to outperform fully finetuned models in the closed book setting, as well as achieve results comparable to retrieve-then-generate open-book models.
We present a new structure-preserving model order reduction (MOR) framework for large-scale port-Hamiltonian descriptor systems (pH-DAEs). Our method exploits the structural properties of the Rosenbrock system matrix for this system class and utilizes condensed forms which often arise in applications and reveal the solution behaviour of a system. Provided that the original system has such a form, our method produces reduced-order models (ROMs) of minimal dimension, which tangentially interpolate the original model's transfer function and are guaranteed to be again in pH-DAE form. This allows the ROM to be safely coupled with other dynamical systems when modelling large system networks, which is useful, for instance, in electric circuit simulation.
We derive exact analytical expressions for the cumulants of any orders of neuronal membrane potentials driven by spike trains in a multivariate Hawkes process model with excitation and inhibition. Such expressions can be used for the prediction and sensitivity analysis of the statistical behavior of the model over time, and to estimate the probability densities of neuronal membrane potentials using Gram-Charlier expansions. Our results are shown to provide a better alternative to Monte Carlo estimates via stochastic simulations, and computer codes based on combinatorial recursions are included.
In many organisms, homologous (or repetitive) chromosomal regions can associate or/and undergo concerted epigenetic changes in the absence of DNA breakage and recombination. The direct specific pairing of DNA duplexes with similar nucleotide sequences represents an attractive mechanism for recognizing such regions. Whereas the pairing of B-DNA duplexes may involve a large energy barrier, C-DNA duplexes are expected to pair much more readily. This unique feature of C-DNA is largely due to the fact that its major groove is wide and very shallow, permitting almost perfect initial homologous contacts between two duplexes without clashing. Overall, the conjectured role of C-DNA in recombination-independent pairing should revive the efforts to understand its structure and function in the cell.
In speaker recognition, where speech segments are mapped to embeddings on the unit hypersphere, two scoring back-ends are commonly used, namely cosine scoring and PLDA. We have recently proposed PSDA, an analog to PLDA that uses Von Mises-Fisher distributions instead of Gaussians. In this paper, we present toroidal PSDA (T-PSDA). It extends PSDA with the ability to model within and between-speaker variabilities in toroidal submanifolds of the hypersphere. Like PLDA and PSDA, the model allows closed-form scoring and closed-form EM updates for training. On VoxCeleb, we find T-PSDA accuracy on par with cosine scoring, while PLDA accuracy is inferior. On NIST SRE'21 we find that T-PSDA gives large accuracy gains compared to both cosine scoring and PLDA.
Features such as punctuation, capitalization, and formatting of entities are important for readability, understanding, and natural language processing tasks. However, Automatic Speech Recognition (ASR) systems produce spoken-form text devoid of formatting, and tagging approaches to formatting address just one or two features at a time. In this paper, we unify spoken-to-written text conversion via a two-stage process: First, we use a single transformer tagging model to jointly produce token-level tags for inverse text normalization (ITN), punctuation, capitalization, and disfluencies. Then, we apply the tags to generate written-form text and use weighted finite state transducer (WFST) grammars to format tagged ITN entity spans. Despite joining four models into one, our unified tagging approach matches or outperforms task-specific models across all four tasks on benchmark test sets across several domains.
We present a smoothly broken power law functional form (referred to by us as a Broken Neural Scaling Law (BNSL)) that accurately models and extrapolates the scaling behaviors of deep neural networks (i.e. how the evaluation metric of interest varies as the amount of compute used for training, number of model parameters, training dataset size, model input size, number of training steps, or upstream performance varies) for various architectures and for each of various tasks within a large and diverse set of upstream and downstream tasks, in zero-shot, prompted, and fine-tuned settings. This set includes large-scale vision, language, audio, video, diffusion, generative modeling, multimodal learning, contrastive learning, AI alignment, robotics, out-of-distribution (OOD) generalization, continual learning, transfer learning, uncertainty estimation / calibration, out-of-distribution detection, adversarial robustness, distillation, sparsity, retrieval, quantization, pruning, molecules, computer programming/coding, math word problems, "emergent" "phase transitions / changes", arithmetic, unsupervised/self-supervised learning, and reinforcement learning (single agent and multi-agent). When compared to other functional forms for neural scaling behavior, this functional form yields extrapolations of scaling behavior that are considerably more accurate on this set. Moreover, this functional form accurately models and extrapolates scaling behavior that other functional forms are incapable of expressing such as the non-monotonic transitions present in the scaling behavior of phenomena such as double descent and the delayed, sharp inflection points present in the scaling behavior of tasks such as arithmetic. Lastly, we use this functional form to glean insights about the limit of the predictability of scaling behavior. Code is available at https://github.com/ethancaballero/broken_neural_scaling_laws
We consider the problem of simultaneous learning in stochastic games with many players in the finite-horizon setting. While the typical target solution for a stochastic game is a Nash equilibrium, this is intractable with many players. We instead focus on variants of {\it correlated equilibria}, such as those studied for extensive-form games. We begin with a hardness result for the adversarial MDP problem: even for a horizon of 3, obtaining sublinear regret against the best non-stationary policy is \textsf{NP}-hard when both rewards and transitions are adversarial. This implies that convergence to even the weakest natural solution concept -- normal-form coarse correlated equilbrium -- is not possible via black-box reduction to a no-regret algorithm even in stochastic games with constant horizon (unless $\textsf{NP}\subseteq\textsf{BPP}$). Instead, we turn to a different target: algorithms which {\it generate} an equilibrium when they are used by all players. Our main result is algorithm which generates an {\it extensive-form} correlated equilibrium, whose runtime is exponential in the horizon but polynomial in all other parameters. We give a similar algorithm which is polynomial in all parameters for "fast-mixing" stochastic games. We also show a method for efficiently reaching normal-form coarse correlated equilibria in "single-controller" stochastic games which follows the traditional no-regret approach. When shared randomness is available, the two generative algorithms can be extended to give simultaneous regret bounds and converge in the traditional sense.
Existing summarization datasets come with two main drawbacks: (1) They tend to focus on overly exposed domains, such as news articles or wiki-like texts, and (2) are primarily monolingual, with few multilingual datasets. In this work, we propose a novel dataset, called EUR-Lex-Sum, based on manually curated document summaries of legal acts from the European Union law platform (EUR-Lex). Documents and their respective summaries exist as cross-lingual paragraph-aligned data in several of the 24 official European languages, enabling access to various cross-lingual and lower-resourced summarization setups. We obtain up to 1,500 document/summary pairs per language, including a subset of 375 cross-lingually aligned legal acts with texts available in all 24 languages. In this work, the data acquisition process is detailed and key characteristics of the resource are compared to existing summarization resources. In particular, we illustrate challenging sub-problems and open questions on the dataset that could help the facilitation of future research in the direction of domain-specific cross-lingual summarization. Limited by the extreme length and language diversity of samples, we further conduct experiments with suitable extractive monolingual and cross-lingual baselines for future work. Code for the extraction as well as access to our data and baselines is available online at: https://github.com/achouhan93/eur-lex-sum.
In this paper, we propose a comprehensive benchmark to investigate models' logical reasoning capabilities in complex real-life scenarios. Current explanation datasets often employ synthetic data with simple reasoning structures. Therefore, it cannot express more complex reasoning processes, such as the rebuttal to a reasoning step and the degree of certainty of the evidence. To this end, we propose a comprehensive logical reasoning explanation form. Based on the multi-hop chain of reasoning, the explanation form includes three main components: (1) The condition of rebuttal that the reasoning node can be challenged; (2) Logical formulae that uncover the internal texture of reasoning nodes; (3) Reasoning strength indicated by degrees of certainty. The fine-grained structure conforms to the real logical reasoning scenario, better fitting the human cognitive process but, simultaneously, is more challenging for the current models. We evaluate the current best models' performance on this new explanation form. The experimental results show that generating reasoning graphs remains a challenging task for current models, even with the help of giant pre-trained language models.
Liberalized electricity markets often include resource adequacy mechanisms that require consumers to contract with generation resources well in advance of real-time operations. While administratively defined mechanisms have most commonly taken the form of a capacity obligation, efficient markets would feature a broad array of arrangements adapted to the risk profiles and appetites of market participants. This article considers how the financial hedge embedded in alternative resource adequacy contract designs can induce different responses from risk-averse investors, with consequences for the resource mix and market structure. We construct a stochastic equilibrium model describing a competitive market with incomplete risk trading and compute investment equilibria under different contracting regimes. Two policy recommendations result. First, to avoid creating inefficiency by crowding out other forms of risk sharing, system operators should allow resources contracted through other means to opt out of mandatory capacity mechanisms, with their contribution to those requirements subtracted from administratively defined demand curves. Second, if they wish to promote a single contractual form, regulators should consider replacing existing option-like capacity mechanisms with a shaped forward contract for energy. Beyond these recommendations, we discuss the tension that liberalized systems face in seeking to promote both reliability and competitive outcomes.
Although reinforcement learning has found widespread use in dense reward settings, training autonomous agents with sparse rewards remains challenging. To address this difficulty, prior work has shown promising results when using not only task-specific demonstrations but also task-agnostic albeit somewhat related demonstrations. In most cases, the available demonstrations are distilled into an implicit prior, commonly represented via a single deep net. Explicit priors in the form of a database that can be queried have also been shown to lead to encouraging results. To better benefit from available demonstrations, we develop a method to Combine Explicit and Implicit Priors (CEIP). CEIP exploits multiple implicit priors in the form of normalizing flows in parallel to form a single complex prior. Moreover, CEIP uses an effective explicit retrieval and push-forward mechanism to condition the implicit priors. In three challenging environments, we find the proposed CEIP method to improve upon sophisticated state-of-the-art techniques.
A closed-form model for the nonlinear interference in distributed Raman amplified links is presented, the formula accounts for both forward and backward pumping.