paper-with-me

홈 › Papers

Do Transformer Networks Improve the Discovery of Rules from Text?

2022-06-01 · LREC 2022 6 · Mahdi Rahimi, Mihai Surdeanu

With their Discovery of Inference Rules from Text (DIRT) algorithm, Lin and Pantel (2001) made a seminal contribution to the field of rule acquisition from text, by adapting the distributional hypothesis of Harris (1954) to rules that model binary relations such as X treat Y. DIRT’s relevance is renewed in today’s neural era given the recent focus on interpretability in the field of natural language processing. We propose a novel take on the DIRT algorithm, where we implement the distributional hypothesis using the contextualized embeddings provided by BERT, a transformer-network-based language model (Vaswani et al. 2017; Devlin et al. 2018). In particular, we change the similarity measure between pairs of slots (i.e., the set of words matched by a rule) from the original formula that relies on lexical items to a formula computed using contextualized embeddings. We empirically demonstrate that this new similarity method yields a better implementation of the distributional hypothesis, and this, in turn, yields rules that outperform the original algorithm in the question answering-based evaluation proposed by Lin and Pantel (2001).

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingQuestion Answering

Similar Papers 제목 키워드 기반

Neural-Guided Equation Discovery

2025-03-21 · Jannis Brugger, Mattia Cerrato, David Richter, Cedric Derstroff 외

Deep learning approaches are becoming increasingly attractive for equation discovery. We show the advantages and disadvantages of using neural-guided equation discovery by giving an overview of recent papers and the resu…

Contrastive LearningEquation Discoveryreinforcement-learningReinforcement Learning

AbductionRules: Training Transformers to Explain Unexpected Inputs

2022-03-23 · Findings (ACL) 2022 5 · Nathan Young, Qiming Bao, Joshua Bensemann, Michael Witbrock

Transformers have recently been shown to be capable of reliably performing logical reasoning over facts and rules expressed in natural language, but abductive reasoning - inference to the best explanation of an unexpecte…

Common Sense ReasoningLogical Reasoningscientific discovery

AbductionRules: Training Transformers to Explain Unexpected Inputs

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

Transformers have recently been shown to be capable of reliably performing logical reasoning over facts and rules expressed in natural language, but abductive reasoning - inference to the best explanation of an unexpecte…

Common Sense ReasoningLogical Reasoningscientific discovery

Automatic Rule Induction for Interpretable Semi-Supervised Learning

2022-05-18 · Reid Pryzant, ZiYi Yang, Yichong Xu, Chenguang Zhu 외

Semi-supervised learning has shown promise in allowing NLP models to generalize from small amounts of labeled data. Meanwhile, pretrained transformer models act as black-box correlation engines that are difficult to expl…

Relation Extraction

Online false discovery rate control for anomaly detection in time series

2021-12-06 · NeurIPS 2021 12 · Quentin Rebjock, Barış Kurt, Tim Januschowski, Laurent Callot

This article proposes novel rules for false discovery rate control (FDRC) geared towards online anomaly detection in time series. Online FDRC rules allow to control the properties of a sequence of statistical tests. In t…

Anomaly DetectionTime SeriesTime Series Analysis