Related papers: Orthographic Syllable as basic unit for SMT betwee…

This paper proposes a technique for adding a new source or target language to an existing multilingual NMT model without re-training it on the initial set of languages. It consists in replacing the shared vocabulary with a small…

Words are fundamental linguistic units that connect thoughts and things through meaning. However, words do not appear independently in a text sequence. The existence of syntactic rules induces correlations among neighboring words. Using an…

Usually bilingual word vectors are trained "online". Mikolov et al. showed they can also be found "offline", whereby two pre-trained embeddings are aligned with a linear transformation, using dictionaries compiled from expert knowledge. In…

We propose a straightforward vocabulary adaptation scheme to extend the language capacity of multilingual machine translation models, paving the way towards efficient continual learning for multilingual machine translation. Our approach is…

Separation is a classical problem asking whether, given two sets belonging to some class, it is possible to separate them by a set from a smaller class. We discuss the separation problem for regular languages. We give a Ptime algorithm to…

This paper explores the idea of using phonemes as a textual representation within a conventional multilingual simultaneous speech-to-speech translation pipeline, as opposed to the traditional reliance on text-based language representations.…

In a hybrid automatic speech recognition (ASR) system, a pronunciation lexicon (PL) and a language model (LM) are essential to correctly retrieve spoken word sequences. Being a morphologically complex language, the vocabulary of Malayalam…

Spoken Language Understanding (SLU) is a task that aims to extract semantic information from spoken utterances. Previous research has made progress in end-to-end SLU by using paired speech-text data, such as pre-trained Automatic Speech…

How to achieve neural machine translation with limited parallel data? Existing techniques often rely on large-scale monolingual corpora, which is impractical for some low-resource languages. In this paper, we turn to connect several…

This paper describes a first step towards the definition of an abstract machine for linguistic formalisms that are based on typed feature structures, such as HPSG. The core design of the abstract machine is given in detail, including the…

Soft Prompt Tuning (SPT) is a parameter-efficient method for adapting pre-trained language models (PLMs) to specific tasks by inserting learnable embeddings, or soft prompts, at the input layer of the PLM, without modifying its parameters.…

These are lecture notes on the algebraic approach to regular languages. The classical algebraic approach is for finite words; it uses semigroups instead of automata. However, the algebraic approach can be extended to structures beyond…

A fundamental theme in automata theory is regular languages of words and trees, and their many equivalent definitions. Salvati has proposed a generalization to regular languages of simply typed $\lambda$-terms, defined using denotational…

This paper describes an abstract machine for linguistic formalisms that are based on typed feature structures, such as HPSG. The core design of the abstract machine is given in detail, including the compilation process from a high-level…

Despite impressive empirical successes of neural machine translation (NMT) on standard benchmarks, limited parallel data impedes the application of NMT models to many language pairs. Data augmentation methods such as back-translation make…

Existing representations for human motion, such as MotionGPT, often operate as black-box latent vectors with limited interpretability and build on joint positions which can cause ambiguity. Inspired by the hierarchical structure of natural…

State-of-the-art multilingual machine translation relies on a universal encoder-decoder, which requires retraining the entire system to add new languages. In this paper, we propose an alternative approach that is based on language-specific…

Multilingual pretrained language models (mPLMs) have shown their effectiveness in multilingual word alignment induction. However, these methods usually start from mBERT or XLM-R. In this paper, we investigate whether multilingual sentence…

Tokenization constitutes a fundamental stage in Large Language Model (LLM) processing; however, subword-based tokenization methods optimized on English-dominant corpora may produce token fragmentation misaligned with the linguistic…

Previous cross-lingual transfer methods are restricted to orthographic representation learning via textual scripts. This limitation hampers cross-lingual transfer and is biased towards languages sharing similar well-known scripts. To…