Elastic CRFs for Open-ontology Slot Filling
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2018
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914815864209408 |
|---|---|
| author | Dai, Yinpei Zhang, Yichi Liu, Hong Ou, Zhijian Huang, Yi Feng, Junlan |
| author_facet | Dai, Yinpei Zhang, Yichi Liu, Hong Ou, Zhijian Huang, Yi Feng, Junlan |
| contents | Slot filling is a crucial component in task-oriented dialog systems that is used to parse (user) utterances into semantic concepts called slots. An ontology is defined by the collection of slots and the values that each slot can take. The most widely used practice of treating slot filling as a sequence labeling task suffers from two main drawbacks. First, the ontology is usually pre-defined and fixed and therefore is not able to detect new labels for unseen slots. Second, the one-hot encoding of slot labels ignores the correlations between slots with similar semantics, which makes it difficult to share knowledge learned across different domains. To address these problems, we propose a new model called elastic conditional random field (eCRF), where each slot is represented by the embedding of its natural language description and modeled by a CRF layer. New slot values can be detected by eCRF whenever a language description is available for the slot. In our experiment, we show that eCRFs outperform existing models in both in-domain and cross-domain tasks, especially in predicting unseen slots and values. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_1811_01331 |
| institution | arXiv |
| publishDate | 2018 |
| record_format | arxiv |
| spellingShingle | Elastic CRFs for Open-ontology Slot Filling Dai, Yinpei Zhang, Yichi Liu, Hong Ou, Zhijian Huang, Yi Feng, Junlan Computation and Language Slot filling is a crucial component in task-oriented dialog systems that is used to parse (user) utterances into semantic concepts called slots. An ontology is defined by the collection of slots and the values that each slot can take. The most widely used practice of treating slot filling as a sequence labeling task suffers from two main drawbacks. First, the ontology is usually pre-defined and fixed and therefore is not able to detect new labels for unseen slots. Second, the one-hot encoding of slot labels ignores the correlations between slots with similar semantics, which makes it difficult to share knowledge learned across different domains. To address these problems, we propose a new model called elastic conditional random field (eCRF), where each slot is represented by the embedding of its natural language description and modeled by a CRF layer. New slot values can be detected by eCRF whenever a language description is available for the slot. In our experiment, we show that eCRFs outperform existing models in both in-domain and cross-domain tasks, especially in predicting unseen slots and values. |
| title | Elastic CRFs for Open-ontology Slot Filling |
| topic | Computation and Language |
| url | https://arxiv.org/abs/1811.01331 |