Deep Semantic Analysis of Text

By James F. Allen, Mary D. Swift, William de Beaumont. 2008

118 citations recorded by the source corpus.

We describe a graphical logical form as a semantic representation for text understanding. This representation was designed to bridge the gap between highly expressive "deep" representations of logical forms and more shallow semantic encodings such as word senses and semantic relations. It preserves rich semantic content while allowing for compact ambiguity encoding and viable partial representations. We describe our system for semantic text processing, which has the TRIPS parser at the core, augmented with statistical preprocessing techniques and online lexical lookup. We also present an evaluation metric for the representation and use it to evaluate the performance of the TRIPS parser on the common task paragraphs.

Subfields: Artificial Intelligence, Natural Language Processing

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

1. Mohit Bansal
2. Jianfeng Gao
3. Yejin Choi
4. Devi Parikh
5. Percy Liang
6. Dhruv Batra
7. Noah A. Smith
8. Xiaodong He

In Natural Language Processing

1. Devi Parikh
2. Dhruv Batra
3. Yejin Choi
4. Nasrin Mostafazadeh
5. Jianfeng Gao
6. Mohit Bansal
7. Xiaodong He
8. Alexander Kuhnle

Citations in the corpus

• A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories (2016, background): “TRIPS parser (Allen et al., 2008) produces state-of-the-art logical forms for input stories, providing sense disambiguated and ontology-typed rich deep structures which enables event extraction together with semantic roles and coreference chains throughout the five sentences.”
• CaTeRS: Causal and Temporal Relation Scheme for Semantic Annotation of Event Structures (2016, methodology): “In order to make the event annotation less subjective, we specifically define an event to be any lexical entry under any of the following ontology types in the TRIPS ontology3 (Allen et al., 2008):”
• Smatch: an Evaluation Metric for Semantic Feature Structures (2013, background): “(Allen et al., 2008) propose a metric which computes the maximum score by any alignment between LF graphs, but they do not address how to determine the alignments.”
• Resources for building applications with Dependency Minimal Recursion Semantics (2016, background): “There have, of course, been earlier graph-based semantic representation languages, including some which support genuine logical forms (e.g., Allen et al. (2008)).”