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, 2016Collections
Related items
Showing items related by title, author, creator and subject.
-
Engaging students in a flipped language learning environment: stories from the english language preparatory program
Şahin, Muhammed; Kurban, Caroline Fell (Emerald Group Publishing Ltd., 2016)… -
Flipping language, literature, and digital literacies: stories from the school of foreign languages
Şahin, Muhammed; Kurban, Caroline Fell (Emerald Group Publishing Ltd., 2016)…