Related papers: A Swiss German Dictionary: Variation in Speech and…
Prefix parsing asks whether an input prefix can be extended to a complete string generated by a given grammar. In the weighted setting, it also provides prefix probabilities, which are central to context-free language modeling,…
We present a probabilistic language model for time-stamped text data which tracks the semantic evolution of individual words over time. The model represents words and contexts by latent trajectories in an embedding space. At each moment in…
Inflection graphs are highly complex networks representing relationships between inflectional forms of words in human languages. For so-called synthetic languages, such as Latin or Polish, they have particularly interesting structure due to…
The capabilities of Large Language Models (LLMs) in low-resource languages lag far behind those in English, making their universal accessibility a significant challenge. To alleviate this, we present $\textit{Franken-Adapter}$, a modular…
Sign Language Recognition (SLR) systems primarily focus on manual gestures, but non-manual features such as mouth movements, specifically mouthing, provide valuable linguistic information. This work directly classifies mouthing instances to…
Attributes of words and relations between two words are central to numerous tasks in Artificial Intelligence such as knowledge representation, similarity measurement, and analogy detection. Often when two words share one or more attributes…
One common approach for question answering over speech data is to first transcribe speech using automatic speech recognition (ASR) and then employ text-based retrieval-augmented generation (RAG) on the transcriptions. While this cascaded…
Speech-LLM models have demonstrated great performance in multi-modal and multi-task speech understanding. A typical speech-LLM paradigm is integrating speech modality with a large language model (LLM). While the Whisper encoder was…
We introduce Transformer Grammars (TGs), a novel class of Transformer language models that combine (i) the expressive power, scalability, and strong performance of Transformers and (ii) recursive syntactic compositions, which here are…
Pre-trained transformer language models (TLMs) have recently refashioned natural language processing (NLP): Most state-of-the-art NLP models now operate on top of TLMs to benefit from contextualization and knowledge induction. To explain…
LS is a particular type of computational processes simulating living tissue. They use an unlimited branching process arising from the simultaneous substitutions of some words instead of letters in some initial word. This combines the…
"Leichte Sprache", the German counterpart to Simple English, is a regulated language aiming to facilitate complex written language that would otherwise stay inaccessible to different groups of people. We present a new sentence-aligned…
An \omega-grammar is a formal grammar used to generate \omega-words (i.e. infinite length words), while an \omega-automaton is an automaton used to recognize \omega-words. This paper gives clean and uniform definitions for \omega-grammars…
(Part of the abstract) In this thesis, we investigate the use of unsupervised spoken term discovery in tackling this problem. Unsupervised spoken term discovery aims to discover topic-related terminologies in a speech without knowing the…
Why do some languages like Czech permit free word order, while others like English do not? We address this question by pretraining transformer language models on a spectrum of synthetic word-order variants of natural languages. We observe…
This study pioneers the use of synthetically generated data for training generative models in document-level text simplification of German texts. We demonstrate the effectiveness of our approach with real-world online texts. Addressing the…
A foundational assumption in linguistics holds that the relationship between a word's sound and its meaning is arbitrary. Accumulating evidence from sound symbolism challenges this view, yet no study has systematically mapped the…
A handwritten word recognition system comes with issues such as lack of large and diverse datasets. It is necessary to resolve such issues since millions of official documents can be digitized by training deep learning models using a large…
Phonological reconstruction is one of the central problems in historical linguistics where a proto-word of an ancestral language is determined from the observed cognate words of daughter languages. Computational approaches to historical…
A fundamental characteristic of natural language is the high rate at which speakers produce novel expressions. Because of this novelty, a heavy-tail of rare events accounts for a significant amount of the total probability mass of…