Recurrent Neural Network Language Model (RNNLM) Morphological Analysis System
Jump to navigation
Jump to search
A Recurrent Neural Network Language Model (RNNLM) Morphological Analysis System is a Morphological Analysis System that can solve a Recurrent Neural Network Language Model (RNNLM) Morphological Analysis Task.
- AKA: RNNLM Morphological Analysis System.
- Examples:
- Counter-Example(s):
- an Associative Model Morphological Analysis System,
- a Corpus-Based Morphological Analysis System,
- a Finite State Transducers (FST) Morphological Analysis System,
- a Directed Acrylic Word Graph (DAWG) Morphological Analysis System,
- a Finite State Automata (FSA) Morphological Analysis System,
- a MAGEA Morphological Analysis System,
- a Mininum Description Lenth Morphological Analysis System,
- a Paradigm Based Morphological Analysis System,
- a Two-Level Morphological Analysis System,
- a Stemmer Morphological Analysis System,
- See: Recurrent Neural Network Language Model, Natural Language Syntactic Analysis System, Morphological Tag, Morphological Inflection, Morphological Derivation, Part-of-Speech Tagging System, Word Sense Disambiguation, Non-concatenative Morphology, Allomorphy, Morphophonology.
References
- (Morita et al., 2015) ⇒ Hajime Morita, Daisuke Kawahara, and Sadao Kurohashi. (2015). “Morphological Analysis for Unsegmented Languages Using Recurrent Neural Network Language Model.” In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing.
- QUOTE: We propose a new morphological analysis model that considers semantic plausibility of word sequences by using RNNLM. We integrate RNNLM into morphological analysis (Figure 2). We train the RNNLM using both an automatically analyzed corpus and a manually labeled corpus (...)
For our base model, we adopt a model for supervised morphological analysis, which performs segmentation, lemmatization and POS tagging jointly. We train this model using a tagged corpus of tens of thousands of sentences that contain gold segmentations, lemmas, inflection forms and POS tags. To predict the most probable sequence of words with lemmas and POS tags given an input sentence, we execute the following procedure:
- QUOTE: We propose a new morphological analysis model that considers semantic plausibility of word sequences by using RNNLM. We integrate RNNLM into morphological analysis (Figure 2). We train the RNNLM using both an automatically analyzed corpus and a manually labeled corpus (...)
- 1. Look up the string of the input sentence using a dictionary.
- 2. Make a word lattice.
- 3. Search for the path with the highest score from the lattice.