相关论文: Normalization of Different Swedish Dialects Spoken…

Large-scale pretrained language models are the major driving force behind recent improvements in performance on the Winograd Schema Challenge, a widely employed test of common sense reasoning ability. We show, however, with a new diagnostic…

We present SDS-200, a corpus of Swiss German dialectal speech with Standard German text translations, annotated with dialect, age, and gender information of the speakers. The dataset allows for training speech translation, dialect…

Fine-tuning pre-trained cross-lingual language models can transfer task-specific supervision from one language to the others. In this work, we propose to improve cross-lingual fine-tuning with consistency regularization. Specifically, we…

Building open-domain conversational systems (or chatbots) that produce convincing responses is a recognized challenge. Recent state-of-the-art (SoTA) transformer-based models for the generation of natural language dialogue have demonstrated…

We address the problem of speech enhancement generalisation to unseen environments by performing two manipulations. First, we embed an additional recording from the environment alone, and use this embedding to alter activations in the main…

The best performing transformer-based language models use subword tokenization techniques, such as Byte-Pair-Encoding (BPE). However, these approaches often overlook linguistic principles, such as morphological segmentation, which we…

Large language models have the potential to generate explanations for their own predictions in a variety of styles based on user instructions. Recent research has examined whether these self-explanations faithfully reflect the models'…

The absence of standardized spelling conventions and the organic evolution of human language present an inherent linguistic challenge within historical documents, a longstanding concern for scholars in the humanities. Addressing this issue,…

In this research, we advanced a spoken language recognition system, moving beyond traditional feature vector-based models. Our improvements focused on effectively capturing language characteristics over extended periods using a specialized…

Social media networks and chatting platforms often use an informal version of natural text. Adversarial spelling attacks also tend to alter the input text by modifying the characters in the text. Normalizing these texts is an essential step…

The tasks of idiom understanding and dialect understanding are both well-established benchmarks in natural language processing. In this paper, we propose combining them, and using regional idioms as a test of dialect understanding. Towards…

We investigate a set of techniques for RNN Transducers (RNN-Ts) that were instrumental in lowering the word error rate on three different tasks (Switchboard 300 hours, conversational Spanish 780 hours and conversational Italian 900 hours).…

While recent automatic speech recognition systems achieve remarkable performance when large amounts of adequate, high quality annotated speech data is used for training, the same systems often only achieve an unsatisfactory result for tasks…

This work investigates the performance of Voice Adaptation models for Swiss German dialects, i.e., translating Standard German text to Swiss German dialect speech. For this, we preprocess a large dataset of Swiss podcasts, which we…

For sensible progress in natural language processing, it is important that we are aware of the limitations of the evaluation metrics we use. In this work, we evaluate how robust metrics are to non-standardized dialects, i.e. spelling…

We propose an unsupervised method for detecting loanwords i.e., words borrowed from one language into another. While prior work has primarily relied on language-external information to identify loanwords, such approaches can introduce…

We present two methods for unsupervised segmentation of words into morpheme-like units. The model utilized is especially suited for languages with a rich morphology, such as Finnish. The first method is based on the Minimum Description…

Corpora and web texts can become a rich language learning resource if we have a means of assessing whether they are linguistically appropriate for learners at a given proficiency level. In this paper, we aim at addressing this issue by…

We generalize the word analogy task across languages, to provide a new intrinsic evaluation method for cross-lingual semantic spaces. We experiment with six languages within different language families, including English, German, Spanish,…

Research in natural language processing commonly assumes that approaches that work well for English and and other widely-used languages are "language agnostic". In high-resource languages, especially those that are analytic, a common…