Related papers: The Annotated Dependency Pair Framework for Almost…
Preference learning is critical for aligning large language models (LLMs) with human values, yet its success hinges on high-quality datasets comprising three core components: Preference \textbf{A}nnotations, \textbf{I}nstructions, and…
The aim of this paper is to define a dependency grammar framework which is both linguistically motivated and computationally parsable. See the demo at http://www.conexor.fi/analysers.html#testing
Training a real-time gesture recognition model heavily relies on annotated data. However, manual data annotation is costly and demands substantial human effort. In order to address this challenge, we propose a framework that can…
We consider the problem of refuting equivalence of probabilistic programs, i.e., the problem of proving that two probabilistic programs induce different output distributions. We study this problem in the context of programs with…
Functional dependencies -- traditional, approximate and conditional are of critical importance in relational databases, as they inform us about the relationships between attributes. They are useful in schema normalization, data…
We propose trace abstraction modulo probability, a proof technique for verifying high-probability accuracy guarantees of probabilistic programs. Our proofs overapproximate the set of program traces using failure automata, finite-state…
This paper proposes a novel training scheme for fast matching models in Search Ads, which is motivated by the real challenges in model training. The first challenge stems from the pursuit of high throughput, which prohibits the deployment…
Dependency parsing is a tool widely used in the field of Natural language processing and computational linguistics. However, there is hardly any work that connects dependency parsing to monotonicity, which is an essential part of logic and…
We describe the Amber tool for proving and refuting the termination of a class of probabilistic while-programs with polynomial arithmetic, in a fully automated manner. Amber combines martingale theory with properties of asymptotic bounding…
We study the problem of completely automatically verifying uninterpreted programs---programs that work over arbitrary data models that provide an interpretation for the constants, functions and relations the program uses. The verification…
Producing the required amounts of training data for machine learning and NLP tasks often involves human annotators doing very repetitive and monotonous work. In this paper, we present and evaluate our novel annotation framework DALPHI,…
The paper presents a language model that develops syntactic structure and uses it to extract meaningful information from the word history, thus enabling the use of long distance dependencies. The model assigns probability to every joint…
Correctness of program transformations in extended lambda calculi with a contextual semantics is usually based on reasoning about the operational semantics which is a rewrite semantics. A successful approach to proving correctness is the…
Mapping complex metadata structures is crucial in a number of domains such as data integration, ontology alignment or model management. To speed up that process automatic matching systems were developed to compute mapping suggestions that…
Annotated pushdown automata provide an automaton model of higher-order recursion schemes, which may in turn be used to model higher-order programs for the purposes of verification. We study Ground Annotated Stack Tree Rewrite Systems -- a…
In binary classification, Learning from Positive and Unlabeled data (LePU) is semi-supervised learning but with labeled elements from only one class. Most of the research on LePU relies on some form of independence between the selection…
We introduce a novel dependency parser, the hexatagger, that constructs dependency trees by tagging the words in a sentence with elements from a finite set of possible tags. In contrast to many approaches to dependency parsing, our approach…
Understanding fine-grained links between documents is crucial for many applications, yet progress is limited by the lack of efficient methods for data curation. To address this limitation, we introduce a domain-agnostic framework for…
An important question for a probabilistic program is whether the probability mass of all its diverging runs is zero, that is that it terminates "almost surely". Proving that can be hard, and this paper presents a new method for doing so; it…
Recent progress on parse tree encoder for sentence representation learning is notable. However, these works mainly encode tree structures recursively, which is not conducive to parallelization. On the other hand, these works rarely take…