The Good‚ the Bad‚ and the Unknown: Morphosyllabic Sentiment Tagging of Unseen Words
The omnipresence of unknown words is a problem that any NLP component needs to address in some form. While there exist many established techniques for dealing with unknown words in the realm of POS-tagging, for example, guessing unknown words' semantic properties is a less-explored area with gr...
| Main Authors: | , |
|---|---|
| Format: | Conference item |
| Published: |
2015
|
| _version_ | 1826294813769596928 |
|---|---|
| author | Moilanen, K Pulman, S |
| author_facet | Moilanen, K Pulman, S |
| author_sort | Moilanen, K |
| collection | OXFORD |
| description | The omnipresence of unknown words is a problem that any NLP component needs to address in some form. While there exist many established techniques for dealing with unknown words in the realm of POS-tagging, for example, guessing unknown words' semantic properties is a less-explored area with greater challenges. In this paper, we study the semantic field of sentiment and propose five methods for assigning prior sentiment polarities to unknown words based on known sentiment carriers. Tested on 2000 cases, the methods mirror human judgements closely in three- and two-way polarity classification tasks, and reach accuracies above 63% and 81%, respectively. |
| first_indexed | 2024-03-07T03:51:28Z |
| format | Conference item |
| id | oxford-uuid:c16a6fb0-7861-4c80-a8c6-878c4a303f1c |
| institution | University of Oxford |
| last_indexed | 2024-03-07T03:51:28Z |
| publishDate | 2015 |
| record_format | dspace |
| spelling | oxford-uuid:c16a6fb0-7861-4c80-a8c6-878c4a303f1c2022-03-27T06:01:15ZThe Good‚ the Bad‚ and the Unknown: Morphosyllabic Sentiment Tagging of Unseen WordsConference itemhttp://purl.org/coar/resource_type/c_5794uuid:c16a6fb0-7861-4c80-a8c6-878c4a303f1cDepartment of Computer Science2015Moilanen, KPulman, SThe omnipresence of unknown words is a problem that any NLP component needs to address in some form. While there exist many established techniques for dealing with unknown words in the realm of POS-tagging, for example, guessing unknown words' semantic properties is a less-explored area with greater challenges. In this paper, we study the semantic field of sentiment and propose five methods for assigning prior sentiment polarities to unknown words based on known sentiment carriers. Tested on 2000 cases, the methods mirror human judgements closely in three- and two-way polarity classification tasks, and reach accuracies above 63% and 81%, respectively. |
| spellingShingle | Moilanen, K Pulman, S The Good‚ the Bad‚ and the Unknown: Morphosyllabic Sentiment Tagging of Unseen Words |
| title | The Good‚ the Bad‚ and the Unknown: Morphosyllabic Sentiment Tagging of Unseen Words |
| title_full | The Good‚ the Bad‚ and the Unknown: Morphosyllabic Sentiment Tagging of Unseen Words |
| title_fullStr | The Good‚ the Bad‚ and the Unknown: Morphosyllabic Sentiment Tagging of Unseen Words |
| title_full_unstemmed | The Good‚ the Bad‚ and the Unknown: Morphosyllabic Sentiment Tagging of Unseen Words |
| title_short | The Good‚ the Bad‚ and the Unknown: Morphosyllabic Sentiment Tagging of Unseen Words |
| title_sort | good the bad and the unknown morphosyllabic sentiment tagging of unseen words |
| work_keys_str_mv | AT moilanenk thegoodthebadandtheunknownmorphosyllabicsentimenttaggingofunseenwords AT pulmans thegoodthebadandtheunknownmorphosyllabicsentimenttaggingofunseenwords AT moilanenk goodthebadandtheunknownmorphosyllabicsentimenttaggingofunseenwords AT pulmans goodthebadandtheunknownmorphosyllabicsentimenttaggingofunseenwords |