Related papers: Orthographic Syllable as basic unit for SMT betwee…
Abugida refers to a phonogram writing system where each syllable is represented using a single consonant or typographic ligature, along with a default vowel or optional diacritic(s) to denote other vowels. However, texting in these…
Previous work has considered token overlap, or even similarity of token distributions, as predictors for multilinguality and cross-lingual knowledge transfer in language models. However, these very literal metrics assign large distances to…
Large Language Models (LLMs) show remarkable performance on a wide variety of tasks. Most LLMs split text into multi-character tokens and process them as atomic units without direct access to individual characters. This raises the question:…
Cross-lingual semantic textual similarity systems estimate the degree of the meaning similarity between two sentences, each in a different language. State-of-the-art algorithms usually employ machine translation and combine vast amount of…
Adapter modules, additional trainable parameters that enable efficient fine-tuning of pretrained transformers, have recently been used for language specialization of multilingual transformers, improving downstream zero-shot cross-lingual…
Sign language translation (SLT) is typically trained with text in a single spoken language, which limits scalability and cross-language generalization. Earlier approaches have replaced gloss supervision with text-based sentence embeddings,…
Speech signals, typically sampled at rates in the tens of thousands per second, contain redundancies, evoking inefficiencies in sequence modeling. High-dimensional speech features such as spectrograms are often used as the input for the…
Despite the well-developed cut-edge representation learning for language, most language representation models usually focus on specific levels of linguistic units. This work introduces universal language representation learning, i.e.,…
Phones, the segmental units of the International Phonetic Alphabet (IPA), are used for lexical distinctions in most human languages; Tones, the suprasegmental units of the IPA, are used in perhaps 70%. Many previous studies have explored…
Human bilinguals often use similar brain regions to process multiple languages, depending on when they learned their second language and their proficiency. In large language models (LLMs), how are multiple languages learned and encoded? In…
Writing systems of Indic languages have orthographic syllables, also known as complex graphemes, as unique horizontal units. A prominent feature of these languages is these complex grapheme units that comprise consonants/consonant…
In this paper we examine the use of semantically-aligned speech representations for end-to-end spoken language understanding (SLU). We employ the recently-introduced SAMU-XLSR model, which is designed to generate a single embedding that…
Understanding the underlying relationship between tongue and oropharyngeal muscle deformation seen in tagged-MRI and intelligible speech plays an important role in advancing speech motor control theories and treatment of speech…
Nowadays, training end-to-end neural models for spoken language translation (SLT) still has to confront with extreme data scarcity conditions. The existing SLT parallel corpora are indeed orders of magnitude smaller than those available for…
This paper investigates the use of symmetric monoidal closed (SMC) structure for representing syntax with variable binding, in particular for languages with linear aspects. In our setting, one first specifies an SMC theory T, which may…
The use of subword embedding has proved to be a major innovation in Neural Machine Translation (NMT). It helps NMT to learn better context vectors for Low Resource Languages (LRLs) so as to predict the target words by better modelling the…
In this paper I argue that Optimality Theory provides for an explanatory model of syllabic parsing in English and French. The argument is based on psycholinguistic facts that have been mysterious up to now. This argument is further…
Conventional neural machine translation (NMT) models typically use subwords and words as the basic units for model input and comprehension. However, complete words and phrases composed of several tokens are often the fundamental units for…
Relating formal grammars is a hard problem that balances between language equivalence (which is known to be undecidable) and grammar identity (which is trivial). In this paper, we investigate several milestones between those two extremes…
This paper proposes a unimodal aggregation (UMA) based nonautoregressive model for both English and Mandarin speech recognition. The original UMA explicitly segments and aggregates acoustic frames (with unimodal weights that first…