paper-with-me

Papers

Semi-Supervised Event Extraction with Paraphrase Clusters

2018-08-26 · NAACL 2018 6 · James Ferguson, Colin Lockard, Daniel S. Weld, Hannaneh Hajishirzi

Supervised event extraction systems are limited in their accuracy due to the lack of available training data. We present a method for self-training event extraction systems by bootstrapping additional training data. This is done by taking advantage of the occurrence of multiple mentions of the same event instances across newswire articles from multiple sources. If our system can make a highconfidence extraction of some mentions in such a cluster, it can then acquire diverse training examples by adding the other mentions as well. Our experiments show significant performance improvements on multiple event extractors over ACE 2005 and TAC-KBP 2015 datasets.

📄 PDF Abstract BibTeX arXiv:1808.08622

Code (0)

등록된 구현이 없습니다.

Tasks

ArticlesEvent Extraction

Similar Papers 제목 키워드 기반

Semi-supervised New Event Type Induction and Description via Contrastive Loss-Enforced Batch Attention

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Most event extraction methods have traditionally relied on an annotated set of event types. However, creating event ontologies and annotating supervised training data are expensive and time-consuming. Previous work has p…

Event Extraction

Semi-supervised New Event Type Induction and Description via Contrastive Loss-Enforced Batch Attention

2022-02-12 · Carl Edwards, Heng Ji

Most event extraction methods have traditionally relied on an annotated set of event types. However, creating event ontologies and annotating supervised training data are expensive and time-consuming. Previous work has p…

Event Extraction

Paraphrase Generation for Semi-Supervised Learning in NLU

2019-06-01 · WS 2019 6 · Eunah Cho, He Xie, William M. Campbell

Semi-supervised learning is an efficient way to improve performance for natural language processing systems. In this work, we propose Para-SSL, a scheme to generate candidate utterances using paraphrasing and methods fro…

Natural Language UnderstandingParaphrase Generation

Paraphrase Generation as Unsupervised Machine Translation

2021-09-07 · COLING 2022 10 · Xiaofei Sun, Yufei Tian, Yuxian Meng, Nanyun Peng 외

In this paper, we propose a new paradigm for paraphrase generation by treating the task as unsupervised machine translation (UMT) based on the assumption that there must be pairs of sentences expressing the same meaning …

Machine TranslationParaphrase GenerationSentenceSTS+2

Inducing Script Structure from Crowdsourced Event Descriptions via Semi-Supervised Clustering

2017-04-01 · WS 2017 4 · Lilian Wanzare, Aless Zarcone, ra, Stefan Thater 외

We present a semi-supervised clustering approach to induce script structure from crowdsourced descriptions of event sequences by grouping event descriptions into paraphrase sets (representing event types) and inducing th…

ClusteringQuestion AnsweringSemantic Role Labeling