A Hierarchical Pitman-Yor Process HMM for Unsupervised Part of Speech Induction.
In this work we address the problem of unsupervised part-of-speech induction by bringing together several strands of research into a single model. We develop a novel hidden Markov model incorporating sophisticated smoothing using a hierarchical Pitman-Yor processes prior, providing an elegant and pr...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Conference item |
| Published: |
Association for Computer Linguistics
2011
|
| _version_ | 1826284117348581376 |
|---|---|
| author | Blunsom, P Cohn, T |
| author2 | Lin, D |
| author_facet | Lin, D Blunsom, P Cohn, T |
| author_sort | Blunsom, P |
| collection | OXFORD |
| description | In this work we address the problem of unsupervised part-of-speech induction by bringing together several strands of research into a single model. We develop a novel hidden Markov model incorporating sophisticated smoothing using a hierarchical Pitman-Yor processes prior, providing an elegant and principled means of incorporating lexical characteristics. Central to our approach is a new type-based sampling algorithm for hierarchical Pitman-Yor models in which we track fractional table counts. In an empirical evaluation we show that our model consistently out-performs the current state-of-the-art across 10 languages. © 2011 Association for Computational Linguistics. |
| first_indexed | 2024-03-07T01:09:03Z |
| format | Conference item |
| id | oxford-uuid:8c583b0f-8998-4c07-8dd7-49f9b7e37ce9 |
| institution | University of Oxford |
| last_indexed | 2024-03-07T01:09:03Z |
| publishDate | 2011 |
| publisher | Association for Computer Linguistics |
| record_format | dspace |
| spelling | oxford-uuid:8c583b0f-8998-4c07-8dd7-49f9b7e37ce92022-03-26T22:44:02ZA Hierarchical Pitman-Yor Process HMM for Unsupervised Part of Speech Induction.Conference itemhttp://purl.org/coar/resource_type/c_5794uuid:8c583b0f-8998-4c07-8dd7-49f9b7e37ce9Symplectic Elements at OxfordAssociation for Computer Linguistics2011Blunsom, PCohn, TLin, DMatsumoto, YMihalcea, RIn this work we address the problem of unsupervised part-of-speech induction by bringing together several strands of research into a single model. We develop a novel hidden Markov model incorporating sophisticated smoothing using a hierarchical Pitman-Yor processes prior, providing an elegant and principled means of incorporating lexical characteristics. Central to our approach is a new type-based sampling algorithm for hierarchical Pitman-Yor models in which we track fractional table counts. In an empirical evaluation we show that our model consistently out-performs the current state-of-the-art across 10 languages. © 2011 Association for Computational Linguistics. |
| spellingShingle | Blunsom, P Cohn, T A Hierarchical Pitman-Yor Process HMM for Unsupervised Part of Speech Induction. |
| title | A Hierarchical Pitman-Yor Process HMM for Unsupervised Part of Speech Induction. |
| title_full | A Hierarchical Pitman-Yor Process HMM for Unsupervised Part of Speech Induction. |
| title_fullStr | A Hierarchical Pitman-Yor Process HMM for Unsupervised Part of Speech Induction. |
| title_full_unstemmed | A Hierarchical Pitman-Yor Process HMM for Unsupervised Part of Speech Induction. |
| title_short | A Hierarchical Pitman-Yor Process HMM for Unsupervised Part of Speech Induction. |
| title_sort | hierarchical pitman yor process hmm for unsupervised part of speech induction |
| work_keys_str_mv | AT blunsomp ahierarchicalpitmanyorprocesshmmforunsupervisedpartofspeechinduction AT cohnt ahierarchicalpitmanyorprocesshmmforunsupervisedpartofspeechinduction AT blunsomp hierarchicalpitmanyorprocesshmmforunsupervisedpartofspeechinduction AT cohnt hierarchicalpitmanyorprocesshmmforunsupervisedpartofspeechinduction |