Related papers: Word-specific tonal realizations in Mandarin

The compositionality degree of multiword expressions indicates to what extent the meaning of a phrase can be derived from the meaning of its constituents and their grammatical relations. Prediction of (non)-compositionality is a task that…

Although contextualized automatic speech recognition (ASR) systems are commonly used to improve the recognition of uncommon words, their effectiveness is hindered by the inherent limitations of speech-text data availability. To address this…

We address the problem of tuning word embeddings for specific use cases and domains. We propose a new method that automatically combines multiple domain-specific embeddings, selected from a wide range of pre-trained domain-specific…

Continuous-output neural machine translation (CoNMT) replaces the discrete next-word prediction problem with an embedding prediction. The semantic structure of the target embedding space (i.e., closeness of related words) is intuitively…

Effective representation of a text is critical for various natural language processing tasks. For the particular task of Chinese sentiment analysis, it is important to understand and choose an effective representation of a text from…

Psychological research consistently finds that human ratings of words across diverse semantic scales can be reduced to a low-dimensional form with relatively little information loss. We find that the semantic associations encoded in the…

Dense vector representations for sentences made significant progress in recent years as can be seen on sentence similarity tasks. Real-world phrase retrieval applications, on the other hand, still encounter challenges for effective use of…

In essence, embedding algorithms work by optimizing the distance between a word and its usual context in order to generate an embedding space that encodes the distributional representation of words. In addition to single words or word…

Audio captioning quality metrics which are typically borrowed from the machine translation and image captioning areas measure the degree of overlap between predicted tokens and gold reference tokens. In this work, we consider a metric…

While the success of pre-trained language models has largely eliminated the need for high-quality static word vectors in many NLP applications, such vectors continue to play an important role in tasks where words need to be modelled in the…

Learning vectors that capture the meaning of concepts remains a fundamental challenge. Somewhat surprisingly, perhaps, pre-trained language models have thus far only enabled modest improvements to the quality of such concept embeddings.…

Contextualized word embeddings in language models have given much advance to NLP. Intuitively, sentential information is integrated into the representation of words, which can help model polysemy. However, context sensitivity also leads to…

Voice cloning is often evaluated in terms of overall quality, but less is known about accent preservation and its perceptual consequences. We compare standard and heavily accented Mandarin speech and their voice clones using a combined…

Text embeddings have become central to computational social science and psychology, enabling scalable measurement of meaning and mixed-method inference. Yet most representation learning is optimized and evaluated for prediction and…

Modern language models are typically trained over subword sequences, but ultimately define probabilities over character-strings. Ideally, the choice of the tokeniser -- which maps character-strings to subwords -- should not affect the…

The meaning of a word often varies depending on its usage in different domains. The standard word embedding models struggle to represent this variation, as they learn a single global representation for a word. We propose a method to learn…

We present FastPitch, a fully-parallel text-to-speech model based on FastSpeech, conditioned on fundamental frequency contours. The model predicts pitch contours during inference. By altering these predictions, the generated speech can be…

A common approach for sequence tagging tasks based on contextual word representations is to train a machine learning classifier directly on these embedding vectors. This approach has two shortcomings. First, such methods consider single…

Pre-trained transformer language models have shown remarkable performance on a variety of NLP tasks. However, recent research has suggested that phrase-level representations in these models reflect heavy influences of lexical content, but…

A large amount of feedback was collected over the years. Many feedback analysis models have been developed focusing on the English language. Recognizing the concept of feedback is challenging and crucial in languages which do not have…