RECORD
Ontology-Enhanced Slot Filling
Computation and Language · Submitted 25 Aug 2021
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Experimental results showed that our ontology-enhanced dialogue state tracker improves the joint goal accuracy (slot F1) from 52.63% (91.64%) to 53.91% (92%) on MultiWOZ 2.1 corpus.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Slot filling is a fundamental task in dialog state tracking in task-oriented dialog systems. In multi-domain task-oriented dialog system, user utterances and system responses may mention multiple named entities and attributes values. A system needs to select those that are confirmed by the user and fill them into destined slots. One difficulty is that since a dialogue session contains multiple system-user turns, feeding in all the tokens into a deep model such as BERT can be challenging due to limited capacity of input word tokens and GPU memory. In this paper, we investigate an ontology-enhanced approach by matching the named entities occurred in all dialogue turns using ontology. The matched entities in the previous dialogue turns will be accumulated and encoded as additional inputs to a BERT-based dialogue state tracker. In addition, our improvement includes ontology constraint checking and the correction of slot name tokenization. Experimental results showed that our ontology-enhanced dialogue state tracker improves the joint goal accuracy (slot F1) from 52.63% (91.64%) to 53.91% (92%) on MultiWOZ 2.1 corpus.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Slot filling is a fundamental task in dialog state tracking in task-oriented dialog systems. | background 1.00 | 0.04 | 0.02 | asserted 1.00 |
| s1 | In multi-domain task-oriented dialog system, user utterances and system responses may mention multiple named entities and attributes values. | background 1.00 | 0.06 | 0.02 | hedged possibility 0.97 |
| s2 | A system needs to select those that are confirmed by the user and fill them into destined slots. | background 1.00 | 0.05 | 0.02 | asserted 1.00 |
| s3 | One difficulty is that since a dialogue session contains multiple system-user turns, feeding in all the tokens into a deep model such as BERT can be challenging due to limited capacity of input word tokens and GPU memory. | background 0.81 | 0.11 | 0.02 | asserted 0.79 |
| s4 | In this paper, we investigate an ontology-enhanced approach by matching the named entities occurred in all dialogue turns using ontology. | method 0.56 | 0.78 | 0.06 | asserted 0.90 |
| s5 | The matched entities in the previous dialogue turns will be accumulated and encoded as additional inputs to a BERT-based dialogue state tracker. | method 0.99 | 0.89 | 0.05 | asserted 1.00 |
| s6 | In addition, our improvement includes ontology constraint checking and the correction of slot name tokenization. | method 0.65 | 0.89 | 0.03 | asserted 0.99 |
| s7 | Experimental results showed that our ontology-enhanced dialogue state tracker improves the joint goal accuracy (slot F1) from 52.63% (91.64%) to 53.91% (92%) on MultiWOZ 2.1 corpus. | result 1.00 | 0.96 | 0.85 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Slot filling is a fundamental task in dialog state tracking in task-oriented dialog systems. In multi-domain task-oriented dialog system, user utterances and system responses may mention multiple named entities and attributes values. A system needs to select those that are confirmed by the user and fill them into destined slots. One difficulty is that since a dialogue session contains multiple system-user turns, feeding in all the tokens into a deep model such as BERT can be challenging due to limited capacity of input word tokens and GPU memory. In this paper, we investigate an ontology-enhanced approach by matching the named entities occurred in all dialogue turns using ontology. The matched entities in the previous dialogue turns will be accumulated and encoded as additional inputs to a BERT-based dialogue state tracker. In addition, our improvement includes ontology constraint checking and the correction of slot name tokenization. Experimental results showed that our ontology-enhanced dialogue state tracker improves the joint goal accuracy (slot F1) from 52.63% (91.64%) to 53.91% (92%) on MultiWOZ 2.1 corpus.
Human review
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.