Related papers: Joint PoS Tagging and Stemming for Agglutinative L…

Recent work in word spotting in handwritten documents has yielded impressive results. This progress has largely been made by supervised learning systems, which are dependent on manually annotated data, making deployment to new collections a…

In this paper we study how different ways of combining character and word-level representations affect the quality of both final word and sentence representations. We provide strong empirical evidence that modeling characters improves the…

With the dramatically increased number of parameters in language models, sparsity methods have received ever-increasing research focus to compress and accelerate the models. While most research focuses on how to accurately retain…

Methods such as chain-of-thought prompting and self-consistency have pushed the frontier of language model reasoning performance with no additional training. To further improve performance, we propose a prompt ensembling method for large…

Languages are grouped into families that share common linguistic traits. While this approach has been successful in understanding genetic relations between diverse languages, more analyses are needed to accurately quantify their…

Word embeddings -- distributed representations of words -- in deep learning are beneficial for many tasks in natural language processing (NLP). However, different embedding sets vary greatly in quality and characteristics of the captured…

Multilingual Automatic Speech Recognition (ASR) aims to recognize and transcribe speech from multiple languages within a single system. Whisper, one of the most advanced ASR models, excels in this domain by handling 99 languages…

We present labeled morphological segmentation, an alternative view of morphological processing that unifies several tasks. From an annotation standpoint, we additionally introduce a new hierarchy of morphotactic tagsets. Finally, we develop…

Large language models (LLMs) can memorize and reproduce training sequences verbatim -- a tendency that undermines both generalization and privacy. Existing mitigation methods apply interventions uniformly, degrading performance on the…

This paper describes continuing work on semantic frame slot filling for a command and control task using a weakly-supervised approach. We investigate the advantages of using retraining techniques that take the output of a hierarchical…

Recently, there have been attempts to integrate various speech processing tasks into a unified model. However, few previous works directly demonstrated that joint optimization of diverse tasks in multitask speech models has positive…

Many words are ambiguous in terms of their part of speech (POS). However, when a word appears in a text, this ambiguity is generally much reduced. Disambiguating POS involves using context to reduce the number of POS associated with words,…

Cross-lingual transfer learning is an invaluable tool for overcoming data scarcity, yet selecting a suitable transfer language remains a challenge. The precise roles of linguistic typology, training data, and model architecture in transfer…

Recently, the Large Language Model-based Phoneme-to-Grapheme (LLM-P2G) method has shown excellent performance in speech recognition tasks and has become a feasible direction to replace the traditional WFST decoding method. This framework…

Speech recognition and speech synthesis models are typically trained separately, each with its own set of learning objectives, training data, and model parameters, resulting in two distinct large networks. We propose a parameter-efficient…

This work tackles the problem of learning a set of language specific acoustic units from unlabeled speech recordings given a set of labeled recordings from other languages. Our approach may be described by the following two steps procedure:…

Introduction: Part-of-Speech (POS) Tagging, the process of classifying words into their respective parts of speech (e.g., verb or noun), is essential in various natural language processing applications. POS tagging is a crucial…

We explore training an automatic modality tagger. Modality is the attitude that a speaker might have toward an event or state. One of the main hurdles for training a linguistic tagger is gathering training data. This is particularly…

We present a framework for the induction of semantic frames from utterances in the context of an adaptive command-and-control interface. The system is trained on an individual user's utterances and the corresponding semantic frames…

Language typology databases enhance multi-lingual Natural Language Processing (NLP) by improving model adaptability to diverse linguistic structures. The widely-used lang2vec toolkit integrates several such databases, but its coverage…