Related papers: A theoretical model of dynamical grammatical gende…
Multilingual representations embed words from many languages into a single semantic space such that words with similar meanings are close to each other regardless of the language. These embeddings have been widely used in various settings,…
Morphological segmentation has traditionally been modeled with non-hierarchical models, which yield flat segmentations as output. In many cases, however, proper morphological analysis requires hierarchical structure -- especially in the…
Formal work in linguistics has both produced and used important mathematical tools. Motivated by a survey of models for context and word meaning, syntactic categories, phrase structure rules and trees, an attempt is being made in the…
The representations in large language models contain multiple types of gender information. We focus on two types of such signals in English texts: factual gender information, which is a grammatical or semantic property, and gender bias,…
Modern language modeling tasks are often underspecified: for a given token prediction, many words may satisfy the user's intent of producing natural language at inference time, however only one word will minimize the task's loss function at…
Transformers for language modeling usually rely on deterministic internal computation, with uncertainty expressed mainly at the output layer. We introduce variational neurons into Transformer feed-forward computation so that uncertainty…
We introduce a framework for quantifying semantic variation of common words in Communities of Practice and in sets of topic-related communities. We show that while some meaning shifts are shared across related communities, others are…
In the principles-and-parameters framework, the structural features of languages depend on parameters that may be toggled on or off, with a single parameter often dictating the status of multiple features. The implied covariance between…
When translating from notional gender languages (e.g., English) into grammatical gender languages (e.g., Italian), the generated translation requires explicit gender assignments for various words, including those referring to the speaker.…
Contemporary deep learning models effectively handle languages with diverse morphology despite not being directly integrated into them. Morphology and word order are closely linked, with the latter incorporated into transformer-based models…
Numerous studies have demonstrated the ability of neural language models to learn various linguistic properties without direct supervision. This work takes an initial step towards exploring the less researched topic of how neural models…
The semantics used for particular terms in an academic field organically evolve over time. Tracking this evolution through inspection of published literature has either been from the perspective of Linguistic scholars or has concentrated…
Morphisms are homomorphisms under the concatenation operation of the set of words over a finite set. Changing the elements of the finite set does not essentially change the morphism. We propose a way to select a unique representing member…
Humans can flexibly extend word usages across different grammatical classes, a phenomenon known as word class conversion. Noun-to-verb conversion, or denominal verb (e.g., to Google a cheap flight), is one of the most prevalent forms of…
Recent instruction fine-tuned models can solve multiple NLP tasks when prompted to do so, with machine translation (MT) being a prominent use case. However, current research often focuses on standard performance benchmarks, leaving…
This paper describes a computational framework for a grammar architecture in which different linguistic domains such as morphology, syntax, and semantics are treated not as separate components but compositional domains. Word and phrase…
Recent research has demonstrated that vector space models of semantics can reflect undesirable biases in human culture. Our investigation of crosslinguistic word embeddings reveals that topical gender bias interacts with, and is surpassed…
Recent years have witnessed a surge of publications aimed at tracing temporal changes in lexical semantics using distributional methods, particularly prediction-based word embedding models. However, this vein of research lacks the cohesion,…
Deep pre-trained contextualized encoders like BERT (Delvin et al., 2019) demonstrate remarkable performance on a range of downstream tasks. A recent line of research in probing investigates the linguistic knowledge implicitly learned by…
We propose a new computational approach for tracking and detecting statistically significant linguistic shifts in the meaning and usage of words. Such linguistic shifts are especially prevalent on the Internet, where the rapid exchange of…