Related papers: J-UniMorph: Japanese Morphological Annotation thro…
Distributed word representations, or word vectors, have recently been applied to many tasks in natural language processing, leading to state-of-the-art performance. A key ingredient to the successful application of these representations is…
We propose a bottom-up framework for automatic speech recognition (ASR) in syllable-based languages by unifying language-universal articulatory attribute modeling with syllable-level prediction. The system first recognizes sequences or…
This memoir explores two fundamental aspects of Natural Language Processing (NLP): the creation of linguistic resources and the evaluation of NLP system performance. Over the past decade, my work has focused on developing a morpheme-based…
A morphism h is unambiguous with respect to a word w if there is no other morphism g that maps w to the same image as h. In the present paper we study the question of whether, for any given word, there exists an unambiguous 1-uniform…
We present the QuranMorph corpus, a morphologically annotated corpus for the Quran (77,429 tokens). Each token in the QuranMorph was manually lemmatized and tagged with its part-of-speech by three expert linguists. The lemmatization process…
Uniform Meaning Representation (UMR) is a novel graph-based semantic representation which captures the core meaning of a text, with flexibility incorporated into the annotation schema such that the breadth of the world's languages can be…
Rapid advances of technology and development of research in precision medicine domain have led to the production of different types of biomedical data. Standard medical vocabularies were shown to be limited in dealing with such…
We present DisMo, a multi-level annotator for spoken language corpora that integrates part-of-speech tagging with basic disfluency detection and annotation, and multi-word unit recognition. DisMo is a hybrid system that uses a combination…
Recent years have brought great advances into solving morphological tasks, mostly due to powerful neural models applied to various tasks as (re)inflection and analysis. Yet, such morphological tasks cannot be considered solved, especially…
Morphological inflection generation is the task of generating the inflected form of a given lemma corresponding to a particular linguistic transformation. We model the problem of inflection generation as a character sequence to sequence…
This paper presents Universal Vision-Language Dense Retrieval (UniVL-DR), which builds a unified model for multi-modal retrieval. UniVL-DR encodes queries and multi-modality resources in an embedding space for searching candidates from…
Neural models for the various flavours of morphological inflection tasks have proven to be extremely accurate given ample labeled data -- data that may be slow and costly to obtain. In this work we aim to overcome this annotation bottleneck…
The CoNLL--SIGMORPHON 2018 shared task on supervised learning of morphological generation featured data sets from 103 typologically diverse languages. Apart from extending the number of languages involved in earlier supervised tasks of…
Approximately half of the world's population is multilingual, making multilingual ASR (MASR) essential. Deploying multiple monolingual models is challenging when the ground-truth language is unknown in advance. This motivates research…
We describe a resource-based method of morphological annotation of written Korean text. Korean is an agglutinative language. The output of our system is a graph of morphemes annotated with accurate linguistic information. The language…
In this paper we present a lexicon-based approach to the problem of morphological processing. Full-form words, lemmas and grammatical tags are interconnected in a DAWG. Thus, the process of analysis/synthesis is reduced to a search in the…
Building language-universal speech recognition systems entails producing phonological units of spoken sound that can be shared across languages. While speech annotations at the language-specific phoneme or surface levels are readily…
The advancement of artificial intelligence (AI) for organ segmentation and tumor detection is propelled by the growing availability of computed tomography (CT) datasets with detailed, per-voxel annotations. However, these AI models often…
Multimodal learning has seen great success mining data features from multiple modalities with remarkable model performance improvement. Meanwhile, federated learning (FL) addresses the data sharing problem, enabling privacy-preserved…
Sound symbolism is a linguistic concept that refers to non-arbitrary associations between phonetic forms and their meanings. We suggest that this can be a compelling probe into how Multimodal Large Language Models (MLLMs) interpret auditory…