Recurrent Neural Network Language Model (RNNLM) Morphological Analysis Task

A Recurrent Neural Network Language Model (RNNLM) Morphological Analysis Task is a Morphological Analysis Task that is based on the Recurrent Neural Network Language Model.

• AKA: RNNLM Morphological Analysis Task.
• Context:
  • It can be solved by a Recurrent Neural Network Language Model (RNNLM) Morphological Analysis System by implementing a Recurrent Neural Network Language Model (RNNLM) Morphological Analysis Algorithm.
• Example(s):
  • Morita-Kawahara-Kurohashi Morphological Analyzer.
  • …
• Counter-Example(s):
  • an Associative Model Morphological Analysis Task,
  • a Corpus-Based Morphological Analysis Task,
  • a Finite State Transducers (FST) Morphological Analysis Task,
  • a Directed Acrylic Word Graph (DAWG) Morphological Analysis Task,
  • a Finite State Automata (FSA) Morphological Analysis Task,
  • a Mininum Description Lenth Morphological Analysis Task,
  • a Paradigm Based Morphological Analysis Task,
  • a Two-Level Morphological Analysis Task,
  • a Stemmer Morphological Analysis Task,
• See: Recurrent Neural Network Language Model, Natural Language Syntactic Analysis Task, Morphological Tag, Morphological Inflection, Morphological Derivation, Part-of-Speech Tagging System, Word Sense Disambiguation, Non-concatenative Morphology, Allomorphy, Morphophonology, .

---

---

References

2015

• (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:

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.

---