Compositional neural network language models for agglutinative languages
Citation
Arisoy, E., Saraclar, M., Compositional Neural Network Language Models for Agglutinative Languages. p. 3494-3498.Abstract
Continuous space language models (CSLMs) have been proven to be successful in speech recognition. With proper training of the word embeddings, words that are semantically or syntactically related are expected to be mapped to nearby locations in the continuous space. In agglutinative languages, words are made up of concatenation of stems and suffixes and, as a result, compositional modeling is important. However, when trained on word tokens, CSLMs do not explicitly consider this structure. In this paper, we explore compositional modeling of stems and suffixes in a long short-term memory neural network language model. Our proposed models jointly learn distributed representations for stems and endings (concatenation of suffixes) and predict the probability for stem and ending sequences. Experiments on the Turkish Broadcast news transcription task show that further gains on top of a state-of-theart stem-ending-based n-gram language model can be obtained with the proposed models.
Source
Conference: 17th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2016) Location: San Francisco, CA Date: SEP 08-12, 2016Related items
Showing items related by title, author, creator and subject.
-
Levels or stages of word knowledge
Bush, Jerome (Wiley, 2018)Vocabulary knowledge can be seen as existing on a continuum from unknown to mastery.How well a student knows a word has been referred to as “depth” of vocabularyknowledge, as opposed to “breadth” of knowledge, which is the ... -
Multi-stream long short-term memory neural network language model
Arısoy, Ebru; Saraçlar, Murat (2015)Long Short-Term Memory (LSTM) neural networks are recurrent neural networks that contain memory units that can store contextual information from past inputs for arbitrary amounts of time. A typical LSTM neural network ... -
The provocation of Jasper Johns: Pushing the representational limits of pictorial expression
Keki, Başak (2020)This paper explores the relationship between visuality and verbal language in the works of Jasper Johns roughly between the period of 1955-1965. Works such as Numbers in Colors (1958-59), Gray Alphabets (1956), False Start ...