Syntactic Search by Example
By Micah Shlain, Hillel Taub-Tabib, Shoval Sadde, Yoav Goldberg. 2020
37 citations recorded by the source corpus.
We present a system that allows a user to search a large linguistically annotated corpus using syntactic patterns over dependency graphs. In contrast to previous attempts to this effect, we introduce a light-weight query language that does not require the user to know the details of the underlying syntactic representations, and instead to query the corpus by providing an example sentence coupled with simple markup. Search is performed at an interactive speed due to efficient linguistic graph-indexing and retrieval engine. This allows for rapid exploration, development and refinement of syntax-based queries. We demonstrate the system using queries over two corpora: the English wikipedia, and a collection of English pubmed abstracts. A demo of the wikipedia system is available at https://allenai.github.io/spike/ .
Subfields: Artificial Intelligence, Information Retrieval & Search
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Yonatan Belinkov
- Hinrich Schütze
- Yoav Goldberg
- Mohit Bansal
- Eduard H. Hovy
- Abhilasha Ravichander
- Yanai Elazar
- Luke S. Zettlemoyer
In Information Retrieval & Search
- Hinrich Schütze
- Eduard H. Hovy
- Yonatan Belinkov
- Yoav Goldberg
- Gabriel Stanovsky
- Abhilasha Ravichander
- Nora Kassner
- Patrick Pantel
Citations in the corpus
- Measuring and Improving Consistency in Pretrained Language Models (2021, methodology): “(3) Using SPIKE (Shlain et al., 2020), 5 a search engine over Wikipedia sentences that supports syntax-based queries, we searched for additional patterns that appeared in Wikipedia and added them to P ARA R EL .”
- Measuring Causal Effects of Data Statistics on Language Model's 'Factual' Predictions (2022, methodology): “Data Statistics To collect statistics on the variables related to the training data, we use SPIKE (Shlain et al., 2020), a syntactic search engine that allows fast syntactic search across an indexed corpus of text.”
- Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translation (2021, methodology): “, 2018), specifically designed to to be challenging for coreference and machine translation (top), extract syntactic patterns focusing on the salient entities in the artificial sentences (middle), and query real-world datasets for matching texts, using SPIKE (Shlain et al., 2020).”