相关论文: Tagset Reduction Without Information Loss

Language segmentation consists in finding the boundaries where one language ends and another language begins in a text written in more than one language. This is important for all natural language processing tasks. The problem can be solved…

Automatically inducing the syntactic part-of-speech categories for words in text is a fundamental task in Computational Linguistics. While the performance of unsupervised tagging models has been slowly improving, current state-of-the-art…

Accurate transcription of proper names and technical terms is particularly important in speech-to-text applications for business conversations. These words, which are essential to understanding the conversation, are often rare and therefore…

In this paper, we explore the capacity of a language model-based method for grammatical error detection in detail. We first show that 5 to 10% of training data are enough for a BERT-based error detection method to achieve performance…

This paper presents the use of probabilistic class-based lexica for disambiguation in target-word selection. Our method employs minimal but precise contextual information for disambiguation. That is, only information provided by the…

There is an ongoing debate in the NLP community whether modern language models contain linguistic knowledge, recovered through so-called probes. In this paper, we study whether linguistic knowledge is a necessary condition for the good…

Abbreviations are unavoidable yet critical parts of the medical text. Using abbreviations, especially in clinical patient notes, can save time and space, protect sensitive information, and help avoid repetitions. However, most abbreviations…

The pretraining-fine-tuning paradigm has been the de facto strategy for transfer learning in modern language modeling. With the understanding that task adaptation in LMs is often a function of parameters shared across tasks, we argue that a…

This work is a study of the impact of multiple aspects in a classic unsupervised word sense disambiguation algorithm. We identify relevant factors in a decision rule algorithm, including the initial labeling of examples, the formalization…

There are many settings where it is useful to predict and explain the success or failure of a dialogue. Circumplex theory from psychology models the social orientations (e.g., Warm-Agreeable, Arrogant-Calculating) of conversation…

Transformer-based language models have taken many fields in NLP by storm. BERT and its derivatives dominate most of the existing evaluation benchmarks, including those for Word Sense Disambiguation (WSD), thanks to their ability in…

Recent advances in Large Language Models (LLMs) show that extending the length of reasoning chains significantly improves performance on complex tasks. While revealing these reasoning traces helps users better follow, verify, and learn from…

Neural Machine Translation (NMT) has been widely used in recent years with significant improvements for many language pairs. Although state-of-the-art NMT systems are generating progressively better translations, idiom translation remains…

Language model pretraining generally targets a broad range of use cases and incorporates data from diverse sources. However, there are instances where we desire a model that excels in specific areas without markedly compromising performance…

Informed speaker extraction aims to extract a target speech signal from a mixture of sources given prior knowledge about the desired speaker. Recent deep learning-based methods leverage a speaker discriminative model that maps a reference…

Adding linguistic information (syntax or semantics) to neural machine translation (NMT) has mostly focused on using point estimates from pre-trained models. Directly using the capacity of massive pre-trained contextual word embedding models…

Fine-tuning large pre-trained models with task-specific data has achieved great success in NLP. However, it has been demonstrated that the majority of information within the self-attention networks is redundant and not utilized effectively…

Automatic Speech Recognition (ASR) systems generally do not produce punctuated transcripts. To make transcripts more readable and follow the expected input format for downstream language models, it is necessary to add punctuation marks. In…

This thesis presents a constraint-based morphological disambiguation approach that is applicable to languages with complex morphology--specifically agglutinative languages with productive inflectional and derivational morphological…

In this paper, we propose a new approach to construct a system of transformation rules for the Part-of-Speech (POS) tagging task. Our approach is based on an incremental knowledge acquisition method where rules are stored in an exception…