中文
相关论文

相关论文: Tagset Reduction Without Information Loss

200 篇论文

The time domain waveform of a speech signal carries all of the auditory information. From the phonological point of view, it little can be said on the basis of the waveform itself. However, past research in mathematics, acoustics, and…

声音 · 计算机科学 2013-05-07 Urmila Shrawankar , V M Thakare

We consider the problem of disambiguating the lemma and part of speech of ambiguous words in morphologically rich languages. We propose a method for disambiguating ambiguous words in context, using a large un-annotated corpus of text, and a…

计算与语言 · 计算机科学 2020-07-14 José María Hoya Quecedo , Maximilian W. Koppatz , Giacomo Furlan , Roman Yangarber

Previous studies have shown that linguistic features of a word such as possession, genitive or other grammatical cases can be employed in word representations of a named entity recognition (NER) tagger to improve the performance for…

计算与语言 · 计算机科学 2019-11-12 Onur Güngör , Suzan Üsküdarlı , Tunga Güngör

Hate speech is a global phenomenon, but most hate speech datasets so far focus on English-language content. This hinders the development of more effective hate speech detection models in hundreds of languages spoken by billions across the…

计算与语言 · 计算机科学 2022-10-21 Paul Röttger , Debora Nozza , Federico Bianchi , Dirk Hovy

Stopwords carry little semantic information and are often removed from text data to reduce dataset size and improve machine learning model performance. Consequently, researchers have sought to develop techniques for generating effective…

计算与语言 · 计算机科学 2022-09-07 Daniel M. DiPietro

Grammar Detection, also referred to as Parts of Speech Tagging of raw text, is considered an underlying building block of the various Natural Language Processing pipelines like named entity recognition, question answering, and sentiment…

计算与语言 · 计算机科学 2022-12-06 Surya Teja Chavali , Charan Tej Kandavalli , Sugash T M

Despite its simplicity, bag-of-n-grams sen- tence representation has been found to excel in some NLP tasks. However, it has not re- ceived much attention in recent years and fur- ther analysis on its properties is necessary. We propose a…

计算与语言 · 计算机科学 2018-09-19 Qi Huang , Zhanghao Chen , Zijie Lu , Yuan Ye

We introduce the notion of relevant information loss for the purpose of casting the signal enhancement problem in information-theoretic terms. We show that many algorithms from machine learning can be reformulated using relevant information…

信息论 · 计算机科学 2013-12-20 Bernhard C. Geiger , Gernot Kubin

In order to simplify a sentence, human editors perform multiple rewriting transformations: they split it into several shorter sentences, paraphrase words (i.e. replacing complex words or phrases by simpler synonyms), reorder components,…

计算与语言 · 计算机科学 2020-05-04 Fernando Alva-Manchego , Louis Martin , Antoine Bordes , Carolina Scarton , Benoît Sagot , Lucia Specia

A sentence is typically treated as the minimal syntactic unit used for extracting valuable information from a longer piece of text. However, in written Thai, there are no explicit sentence markers. We proposed a deep learning model for the…

计算与语言 · 计算机科学 2019-08-27 Chanatip Saetia , Ekapol Chuangsuwanich , Tawunrat Chalothorn , Peerapon Vateekul

An effective method to generate a large number of parallel sentences for training improved neural machine translation (NMT) systems is the use of the back-translations of the target-side monolingual data. The standard back-translation…

计算与语言 · 计算机科学 2021-11-04 Idris Abdulmumin , Bashir Shehu Galadanci , Aliyu Garba

Obtaining high-quality speaker embeddings in multi-speaker conditions is crucial for many applications. A recently proposed guided speaker embedding framework, which utilizes speech activities of target and non-target speakers as clues,…

音频与语音处理 · 电气工程与系统科学 2025-06-17 Shota Horiguchi , Takanori Ashihara , Marc Delcroix , Atsushi Ando , Naohiro Tawara

Neural word representations have proven useful in Natural Language Processing (NLP) tasks due to their ability to efficiently model complex semantic and syntactic word relationships. However, most techniques model only one representation…

计算与语言 · 计算机科学 2015-11-23 Andrew Trask , Phil Michalak , John Liu

We discuss combining knowledge-based (or rule-based) and statistical part-of-speech taggers. We use two mature taggers, ENGCG and Xerox Tagger, to independently tag the same text and combine the results to produce a fully disambiguated…

cmp-lg · 计算机科学 2008-02-03 Pasi Tapanainen , Atro Voutilainen

Rare word recognition can be improved by adapting ASR models to synthetic data that includes these words. Further improvements can be achieved through contextual biasing, which trains and adds a biasing module into the model architecture to…

计算与语言 · 计算机科学 2025-09-12 Chin Yuen Kwok , Jia Qi Yip , Eng Siong Chng

In this paper we present a clean, yet effective, model for word sense disambiguation. Our approach leverage a bidirectional long short-term memory network which is shared between all words. This enables the model to share statistical…

计算与语言 · 计算机科学 2016-11-22 Mikael Kågebäck , Hans Salomonsson

In a lexicalized grammar formalism such as Lexicalized Tree-Adjoining Grammar (LTAG), each lexical item is associated with at least one elementary structure (supertag) that localizes syntactic and semantic dependencies. Thus a parser for a…

cmp-lg · 计算机科学 2008-02-03 Aravind K. Joshi , B. Srinivas

In terms of signal samples, we propose and justify a new rank reduced multi-term transform, abbreviated as MTT, which, under certain conditions, may provide better-associated accuracy than that of known optimal rank reduced transforms. The…

最优化与控制 · 数学 2021-11-11 Pablo Soto-Quiros , Anatoli Torokhti

A new language model for speech recognition inspired by linguistic analysis is presented. The model develops hidden hierarchical structure incrementally and uses it to extract meaningful information from the word history - thus enabling the…

计算与语言 · 计算机科学 2007-05-23 Ciprian Chelba , Frederick Jelinek

Modeling topics effectively in short texts, such as tweets and news snippets, is crucial to capturing rapidly evolving social trends. Existing topic models often struggle to accurately capture the underlying semantic patterns of short…

计算与语言 · 计算机科学 2025-02-18 Shuyu Chang , Rui Wang , Peng Ren , Qi Wang , Haiping Huang