Improving Open Information Extraction via Iterative Rank-Aware Learning
Open information extraction (IE) is the task of extracting open-domain assertions from natural language sentences. A key step in open IE is confidence modeling, ranking the extractions based on their estimated quality to adjust precision and recall of extracted assertions. We found that the extraction likelihood, a confidence measure used by current supervised open IE systems, is not well calibrated when comparing the quality of assertions extracted from different sentences. We propose an additional binary classification loss to calibrate the likelihood to make it more globally comparable, and an iterative learning process, where extractions generated by the open IE model are incrementally included as training samples to help the model learn from trial and error. Experiments on OIE2016 demonstrate the effectiveness of our method. Code and data are available at https://github.com/jzbjyb/oie_rank.
Code (1)
Tasks
Binary ClassificationGeneral ClassificationOpen Information ExtractionSimilar Papers 제목 키워드 기반
Answering Any-hop Open-domain Questions with Iterative Document Reranking
Existing approaches for open-domain question answering (QA) are typically designed for questions that require either single-hop or multi-hop reasoning, which make strong assumptions of the complexity of questions to be a…
Multi-hop Question AnsweringNatural QuestionsOpen-Domain Question AnsweringQuestion Answering+2MILLIE: Modular & Iterative Multilingual Open Information Extraction
Open Information Extraction (OpenIE) is the task of extracting $(subject, predicate, object)$ triples from natural language sentences. Current OpenIE systems extract all triple slots independently. In contrast, we invest…
Open Information ExtractionmilIE: Modular & Iterative Multilingual Open Information Extraction
Open Information Extraction (OpenIE) is the task of extracting (subject, predicate, object) triples from natural language sentences. Current OpenIE systems extract all triple slots independently. In contrast, we explore …
Open Information ExtractionTag and Correct: Question aware Open Information Extraction with Two-stage Decoding
Question Aware Open Information Extraction (Question aware Open IE) takes question and passage as inputs, outputting an answer tuple which contains a subject, a predicate, and one or more arguments. Each field of answer …
DecoderOpen Information ExtractionTAGOpenIE6: Iterative Grid Labeling and Coordination Analysis for Open Information Extraction
A recent state-of-the-art neural open information extraction (OpenIE) system generates extractions iteratively, requiring repeated encoding of partial outputs. This comes at a significant computational cost. On the other…
Open Information Extraction