Exploiting Duality in Open Information Extraction with Predicate Prompt
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913202312314880 |
|---|---|
| author | Chen, Zhen Liu, Jingping Yang, Deqing Xiao, Yanghua Xu, Huimin Wang, Zongyu Xie, Rui Xian, Yunsen |
| author_facet | Chen, Zhen Liu, Jingping Yang, Deqing Xiao, Yanghua Xu, Huimin Wang, Zongyu Xie, Rui Xian, Yunsen |
| contents | Open information extraction (OpenIE) aims to extract the schema-free triplets in the form of (\emph{subject}, \emph{predicate}, \emph{object}) from a given sentence. Compared with general information extraction (IE), OpenIE poses more challenges for the IE models, {especially when multiple complicated triplets exist in a sentence. To extract these complicated triplets more effectively, in this paper we propose a novel generative OpenIE model, namely \emph{DualOIE}, which achieves a dual task at the same time as extracting some triplets from the sentence, i.e., converting the triplets into the sentence.} Such dual task encourages the model to correctly recognize the structure of the given sentence and thus is helpful to extract all potential triplets from the sentence. Specifically, DualOIE extracts the triplets in two steps: 1) first extracting a sequence of all potential predicates, 2) then using the predicate sequence as a prompt to induce the generation of triplets. Our experiments on two benchmarks and our dataset constructed from Meituan demonstrate that DualOIE achieves the best performance among the state-of-the-art baselines. Furthermore, the online A/B test on Meituan platform shows that 0.93\% improvement of QV-CTR and 0.56\% improvement of UV-CTR have been obtained when the triplets extracted by DualOIE were leveraged in Meituan's search system. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_11107 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Exploiting Duality in Open Information Extraction with Predicate Prompt Chen, Zhen Liu, Jingping Yang, Deqing Xiao, Yanghua Xu, Huimin Wang, Zongyu Xie, Rui Xian, Yunsen Computation and Language Information Retrieval Open information extraction (OpenIE) aims to extract the schema-free triplets in the form of (\emph{subject}, \emph{predicate}, \emph{object}) from a given sentence. Compared with general information extraction (IE), OpenIE poses more challenges for the IE models, {especially when multiple complicated triplets exist in a sentence. To extract these complicated triplets more effectively, in this paper we propose a novel generative OpenIE model, namely \emph{DualOIE}, which achieves a dual task at the same time as extracting some triplets from the sentence, i.e., converting the triplets into the sentence.} Such dual task encourages the model to correctly recognize the structure of the given sentence and thus is helpful to extract all potential triplets from the sentence. Specifically, DualOIE extracts the triplets in two steps: 1) first extracting a sequence of all potential predicates, 2) then using the predicate sequence as a prompt to induce the generation of triplets. Our experiments on two benchmarks and our dataset constructed from Meituan demonstrate that DualOIE achieves the best performance among the state-of-the-art baselines. Furthermore, the online A/B test on Meituan platform shows that 0.93\% improvement of QV-CTR and 0.56\% improvement of UV-CTR have been obtained when the triplets extracted by DualOIE were leveraged in Meituan's search system. |
| title | Exploiting Duality in Open Information Extraction with Predicate Prompt |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2401.11107 |