Reading to Learn: Constructing Features from Semantic Abstracts

By Jacob Eisenstein, James Clarke, Dan Goldwasser, Dan Roth. 2009

44 citations recorded by the source corpus.

Machine learning offers a range of tools for training systems from data, but these methods are only as good as the underlying representation. This paper proposes to acquire representations for machine learning by reading text written to accommodate human learning. We propose a novel form of semantic analysis called reading to learn, where the goal is to obtain a high-level semantic abstract of multiple documents in a representation that facilitates learning. We obtain this abstract through a generative model that requires no labeled data, instead leveraging repetition across multiple documents. The semantic abstract is converted into a transformed feature space for learning, resulting in improved generalization on a relational learning task.

Subfields: Artificial Intelligence, Natural Language Processing, Representation & Self-Supervised Learning

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

In Natural Language Processing

In Representation & Self-Supervised Learning

Citations in the corpus

Joint Concept Learning and Semantic Parsing from Natural Language Explanations (2017, background): “Natural instructions have been studied in game playing frameworks (Branavan et al., 2012; Eisenstein et al., 2009).”
Language Understanding for Text-based Games using Deep Reinforcement Learning (2015, background): “, 2013; Andreas and Klein, 2015) and playing computer games (Eisenstein et al., 2009; Branavan et al., 2011a).”
Learning to Solve Arithmetic Word Problems with Verb Categorization (2014, background): “More recent work (Eisenstein et al., 2009; Kate and Mooney, 2007; Goldwasser and Roth, 2011; Poon and Domingos, 2009; Goldwasser et al., 2011; Kushman and Barzilay, 2013) reduce the amount of required supervision in mapping sentences to meaning representations while taking advantage of special…”
Learning Dependency-Based Compositional Semantics (2011, background): “There have been several papers that induce programs in this setting: Eisenstein et al. (2009) induce conjunctive formulae from natural language instructions, Piantadosi et al. (2008) induce first-order logic formulae using CCG in a small domain assuming observed lexical semantics, and Clarke et al.…”
Neural Programmer: Inducing Latent Programs with Gradient Descent (2015, background): “Methods such as Piantadosi et al. (2008); Eisenstein et al. (2009); Clarke et al. (2010) learn a compositional semantic model without hand engineered compositional grammar, but still requiring a hand labeled lexical mapping of words to the operations.”
A Survey of Reinforcement Learning Informed by Natural Language (2019, background): “Some signiﬁcant work, especially in language-assisted RL, has been done prior to the surge of deep learning methods [ Eisenstein et al. , 2009; Branavan et al. , 2012], and is worth revisiting.”
Learning to Win by Reading Manuals in a Monte-Carlo Framework (2011, methodology): “Eisenstein et al. (2009) aim to automatically extract information from a collection of documents to help identify the rules of a game.”
A Game-Theoretic Approach to Generating Spatial Descriptions (2010, background): “Along similar lines, past work has also focused on interpreting natural language instructions (Branavan et al., 2009; Eisenstein et al., 2009; Kollar et al., 2010), which takes into account the goal of the communication.”
Solving Geometry Problems: Combining Text and Diagram Interpretation (2015, background): “Semantic parsing is an important area of NLP research (Zettlemoyer and Collins, 2005; Ge and Mooney, 2006; Flanigan et al., 2014; Eisenstein et al., 2009; Kate and Mooney, 2007; Goldwasser and Roth, 2011; Poon and Domingos, 2009; Berant and Liang, 2014; Kwiatkowski et al., 2013; Reddy et al., 2014).”
Learning to Learn Semantic Parsers from Natural Language Supervision (2019, methodology): “…autonomous agent learns to complete a task in an environment, for example, learning to play games by utilizing text manuals (Branavan et al., 2012; Eisenstein et al., 2009; Narasimhan et al., 2015) and guiding policy learning using high-level human advice (Kuhlmann et al., 2004; Squire et al.,…”