Related papers: Functorial Language Models
Word segmentation, the problem of finding word boundaries in speech, is of interest for a range of tasks. Previous papers have suggested that for sequence-to-sequence models trained on tasks such as speech translation or speech recognition,…
We construct a symmetric monoidal closed category of polynomial endofunctors (as objects) and simulation cells (as morphisms). This structure is defined using universal properties without reference to representing polynomial diagrams and is…
Modern language models define distributions over strings, but downstream tasks often require different output formats. For instance, a model that generates byte-pair strings does not directly produce word-level predictions, and a DNA model…
We present a model for compositional distributional semantics related to the framework of Coecke et al. (2010), and emulating formal semantics by representing functions as tensors and arguments as vectors. We introduce a new learning method…
A reverse dictionary takes the description of a target word as input and outputs the target word together with other words that match the description. Existing reverse dictionary methods cannot deal with highly variable input queries and…
In this paper, we present a novel deep multimodal framework to predict human emotions based on sentence-level spoken language. Our architecture has two distinctive characteristics. First, it extracts the high-level features from both text…
Orthographic similarities across languages provide a strong signal for probabilistic decipherment, especially for closely related language pairs. The existing decipherment models, however, are not well-suited for exploiting these…
Discourse relations bind smaller linguistic units into coherent texts. However, automatically identifying discourse relations is difficult, because it requires understanding the semantics of the linked arguments. A more subtle challenge is…
This paper discusses a simple and explicit toy-model example of the categorical Hopfield equations introduced in previous work of Manin and the author. These describe dynamical assignments of resources to networks, where resources are…
We define a monoidal semantics for algebraic theories. The basis for the definition is provided by the analysis of the structural rules in the term calculus of algebraic languages. Models are described both explicitly, in a form that…
Distributed representations of words have boosted the performance of many Natural Language Processing tasks. However, usually only one representation per word is obtained, not acknowledging the fact that some words have multiple meanings.…
Pre-trained language models and other generative models have revolutionized NLP and beyond. However, these models tend to reproduce undesirable biases present in their training data. Also, they may overlook patterns that are important but…
Distributional semantics provides multi-dimensional, graded, empirically induced word representations that successfully capture many aspects of meaning in natural languages, as shown in a large body of work in computational linguistics;…
Intensional computation derives concrete outputs from abstract function definitions; extensional computation defines functions through explicit input-output pairs. In formal semantics: intensional computation interprets expressions as…
We introduced a multimodal foundational model for financial transactions that integrates both structured attributes and unstructured textual descriptions into a unified representation. By adapting masked language modeling to transaction…
We develop a method to incrementally construct programming languages. Our approach is categorical: each layer of the language is described as a monad. Our method either (i) concretely builds a distributive law between two monads, i.e.…
We present a probabilistic model that uses both prosodic and lexical cues for the automatic segmentation of speech into topically coherent units. We propose two methods for combining lexical and prosodic information using hidden Markov…
Discriminative segmental models offer a way to incorporate flexible feature functions into speech recognition. However, their appeal has been limited by their computational requirements, due to the large number of possible segments to…
Distributional semantics creates vector-space representations that capture many forms of semantic similarity, but their relation to semantic entailment has been less clear. We propose a vector-space model which provides a formal foundation…
Spoken communication occurs in a "noisy channel" characterized by high levels of environmental noise, variability within and between speakers, and lexical and syntactic ambiguity. Given these properties of the received linguistic input,…