Revisiting the Prepositional-Phrase Attachment Problem Using Explicit Commonsense Knowledge

by   Yida Xin, et al.

We revisit the challenging problem of resolving prepositional-phrase (PP) attachment ambiguity. To date, proposed solutions are either rule-based, where explicit grammar rules direct how to resolve ambiguities; or statistical, where the decision is learned from a corpus of labeled examples. We argue that explicit commonsense knowledge bases can provide an essential ingredient for making good attachment decisions. We implemented a module, named Patch-Comm, that can be used by a variety of conventional parsers, to make attachment decisions. Where the commonsense KB does not provide direct answers, we fall back on a more general system that infers "out-of-knowledge-base" assertions in a manner similar to the way some NLP systems handle out-of-vocabulary words. Our results suggest that the commonsense knowledge-based approach can provide the best of both worlds, integrating rule-based and statistical techniques. As the field is increasingly coming to recognize the importance of explainability in AI, a commonsense approach can enable NLP developers to better understand the behavior of systems, and facilitate natural dialogues with end users.


page 1

page 2

page 3

page 4


Semantically Enhanced Models for Commonsense Knowledge Acquisition

Commonsense knowledge is paramount to enable intelligent systems. Typica...

Improving Question Answering by Commonsense-Based Pre-Training

Although neural network approaches achieve remarkable success on a varie...

Augmenting End-to-End Dialog Systems with Commonsense Knowledge

Building dialog agents that can converse naturally with humans is a chal...

CogNet: Bridging Linguistic Knowledge, World Knowledge and Commonsense Knowledge

In this paper, we present CogNet, a knowledge base (KB) dedicated to int...

MCScript2.0: A Machine Comprehension Corpus Focused on Script Events and Participants

We introduce MCScript2.0, a machine comprehension corpus for the end-to-...

BIG MOOD: Relating Transformers to Explicit Commonsense Knowledge

We introduce a simple yet effective method of integrating contextual emb...

Selection Strategies for Commonsense Knowledge

Selection strategies are broadly used in first-order logic theorem provi...