Related papers: Internal Effectful Forcing in System T
We propose learning flexible but interpretable functions that aggregate a variable-length set of permutation-invariant feature vectors to predict a label. We use a deep lattice network model so we can architect the model structure to…
Automata-logic connections are pillars of the theory of regular languages. Such connections are harder to obtain for transducers, but important results have been obtained recently for word-to-word transformations, showing that the three…
We apply decision tree induction to the problem of discourse clue word sense disambiguation with a genetic algorithm. The automatic partitioning of the training set which is intrinsic to decision tree induction gives rise to linguistically…
Dialogue systems capable of social influence such as persuasion, negotiation, and therapy, are essential for extending the use of technology to numerous realistic scenarios. However, existing research primarily focuses on either…
This chapter contains an exposition of the sheaf-theoretic framework for contextuality emphasising resource-theoretic aspects, as well as some original results on this topic. In particular, we consider functions that transform empirical…
The modal logic of forcing arises when one considers a model of set theory in the context of all its forcing extensions, interpreting necessity as "in all forcing extensions" and possibility as "in some forcing extension". In this modal…
This paper synthesizes a series of formal proofs to construct a unified theory on the logical limits of the Symbol Grounding Problem. We distinguish between internal meaning (sense), which formal systems can possess via axioms, and external…
We study L\"owenheim-Skolem and Omitting Types theorems in Transition Algebra, a logical system obtained by enhancing many sorted first-order logic with features from dynamic logic. The sentences we consider include compositions, unions,…
The end-to-end TTS, which can predict speech directly from a given sequence of graphemes or phonemes, has shown improved performance over the conventional TTS. However, its predicting capability is still limited by the acoustic/phonetic…
In the era of intelligent computing, computational progress in text processing is an essential consideration. Many systems have been developed to process text over different languages. Though, there is considerable development, they still…
Neural language models exhibit impressive performance on a variety of tasks, but their internal reasoning may be difficult to understand. Prior art aims to uncover meaningful properties within model representations via probes, but it is…
Task-oriented dialogue systems are designed to achieve specific goals while conversing with humans. In practice, they may have to handle simultaneously several domains and tasks. The dialogue manager must therefore be able to take into…
Scala's type system unifies ML modules, object-oriented, and functional programming. The Dependent Object Types (DOT) family of calculi has been proposed as a new foundation for Scala and similar languages. Unfortunately, it is not clear…
We prove various iteration theorems for forcing classes related to subproper and subcomplete forcing, introduced by Jensen. In the first part, we use revised countable support iterations, and show that 1) the class of subproper,…
Discourse information, as postulated by popular discourse theories, such as RST and PDTB, has been shown to improve an increasing number of downstream NLP tasks, showing positive effects and synergies of discourse with important real-world…
Exploiting rich linguistic information in raw text is crucial for expressive text-to-speech (TTS). As large scale pre-trained text representation develops, bidirectional encoder representations from Transformers (BERT) has been proven to…
This paper is concerned with the expressivity and denotational semantics of a functional higher-order reversible programming language based on Theseus. In this language, pattern-matching is used to ensure the reversibility of functions. We…
Recent advances in Neural Machine Translation (NMT) show that adding syntactic information to NMT systems can improve the quality of their translations. Most existing work utilizes some specific types of linguistically-inspired tree…
Classical set theory constructs the continuum via the power set P(N), thereby postulating an uncountable totality. However, constructive and computability-based approaches reveal that no formal system with countable syntax can generate all…
When trained on language data, do transformers learn some arbitrary computation that utilizes the full capacity of the architecture or do they learn a simpler, tree-like computation, hypothesized to underlie compositional meaning systems…