Results 11 to 20 of about 16,255,542 (289)
N-grams are generalized words consisting of N consecutive symbols, as they are used in a text. This paper determines the rank-frequency distribution for redundant N-grams. For entire texts this is known to be Zipf's law (i.e., an inverse power law).
EGGHE, Leo
core +5 more sources
This is a review of Collocations and N-grams.
Freebury-Jones, Darren
core +4 more sources
Keywords in Context (Using n-grams) with Python
Like in Output Data as HTML File, this lesson takes the frequency pairs collected in Counting Frequencies and outputs them in HTML. This time the focus is on keywords in context (KWIC) which creates n-grams from the original document content – in this ...
William J. Turkel, Adam Crymble
doaj +1 more source
Inverse Document Frequency (IDF) is widely accepted term weighting scheme whose robustness is supported by many theoretical justifications. However, applying IDF to word N-grams (or simply N-grams) of any length without relying on heuristics has remained a challenging issue. This article describes a theoretical extension of IDF to handle N-grams. First,
Masumi Shirakawa +2 more
openaire +2 more sources
A collection of n-grams extracted from the IMP corpus of historical Slovene (cf. https://nl.ijs.si/imp/). Three sets of n-gram lists are provided for lowercased word n-grams of length 1 to 5: - extensive frequency lists of all extracted n-grams ...
Dobrovoljc, Kaja
core +8 more sources
Implicit n-grams Induced by Recurrence
Although self-attention based models such as Transformers have achieved remarkable successes on natural language processing (NLP) tasks, recent studies reveal that they have limitations on modeling sequential transformations (Hahn, 2020), which may prompt re-examinations of recurrent neural networks (RNNs) that demonstrated impressive results on ...
Xiaobing Sun 0002, Wei Lu 0011
openaire +3 more sources
N-gram Boosting: Improving Contextual Biasing with Normalized N-gram Targets
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 likely to be under-represented in text and audio training data, creating a significant challenge in this domain ...
Wang Yau Li +7 more
openaire +2 more sources
Pseudo-Conventional N-Gram Representation of the Discriminative N-Gram Model for LVCSR [PDF]
The discriminative n-gram modeling approach re-ranks the N-best hypotheses generated during decoding and can effectively improve the performance of large-vocabulary continuous speech recognition (LVCSR). This work recasts the discriminative n-gram model as a pseudo-conventional n-gram model.
Zhengyu Zhou, Helen M. Meng
openaire +1 more source
Computing n-gram statistics in MapReduce [PDF]
Statistics about n-grams (i.e., sequences of contiguous words or other tokens in text documents or other string data) are an important building block in information retrieval and natural language processing. In this work, we study how n-gram statistics, optionally restricted by a maximum n-gram length and minimum collection frequency, can be computed ...
Berberich, K., Bedathur, S.
openaire +6 more sources
Variable word rate N-grams [PDF]
4 pages, 4 figures, ICASSP ...
Yoshihiko Gotoh, Steve Renals
openaire +4 more sources

