This article presents our work on constructing a corpus of news articles in which events are annotated for estimated bounds on their duration, and automatically learning from this corpus. We describe the annotation guidelines, the event classes we categorized to reduce gross discrepancies in inter-annotator judgments, and our use of normal distributions to model vague and implicit temporal information and to measure inter-annotator agreement for these event duration distributions. We then show that machine learning techniques applied to this data can produce coarse-grained event duration information automatically, considerably outperforming a baseline and approaching human performance. The methods described here should be applicable to other kinds of vague but substantive information in texts.

Early proposals for the deep understanding of natural language text advocated an approach of “interpretation as abduction,” where the meaning of a text was derived as an explanation that logically entailed the input words, given a knowledge base of lexical and commonsense axioms. While most subsequent NLP research has instead pursued statistical and data-driven methods, the approach of interpretation as abduction has seen steady advancements in both theory and software implementations. In this paper, we summarize advances in deriving the logical form of the text, encoding commonsense knowledge, and technologies for scalable abductive reasoning. We then explore the application of these advancements to the deep understanding of a paragraph of news text, where the subtle meaning of words and phrases are resolved by backward chaining on a knowledge base of 80 hand-authored axioms.

This corpus and its creation is described in the following publication:Jonathan Gordon, Jerry R. Hobbs, Jonathan May, Michael Mohler, Fabrizio Morbini, Bryan Rink, Marc Tomlinson, and Suzanne Wertheim. 2015. “A Corpus of Rich Metaphor Annotation”. In Proceedings of the Third Workshop on Metaphor in NLP.When linking to this data, please use the URL http://purl.org/net/metaphor-corpus, which will point to its current location.Data Attribution RequirementPlease insert the following statement in any product, report, publication, presentation and/or document that includes or references the data:This effort contains or makes use of the the IARPA-funded Metaphor Program USC/ISI annotated metaphorical language collection, release iarpa_metaphor_isi.edu_metaphor_corpus_2015-04-03.

A summary is not available for this content so a preview has been provided. Please use the Get access link above for information on how to access this content.

A summary is not available for this content so a preview has been provided. Please use the Get access link above for information on how to access this content.

Commonsense psychology refers to the implicit theories that we all use to make sense of people's behavior in terms of their beliefs, goals, plans, and emotions. These are also the theories we employ when we anthropomorphize complex machines and computers as if they had humanlike mental lives. In order to successfully cooperate and communicate with people, these theories will need to be represented explicitly in future artificial intelligence systems. This book provides a large-scale logical formalization of commonsense psychology in support of humanlike artificial intelligence. It uses formal logic to encode the deep lexical semantics of the full breadth of psychological words and phrases, providing fourteen hundred axioms of first-order logic organized into twenty-nine commonsense psychology theories and sixteen background theories. This in-depth exploration of human commonsense reasoning for artificial intelligence researchers, linguists, and cognitive and social psychologists will serve as a foundation for the development of humanlike artificial intelligence.

Commonsense psychology refers to the implicit theories that we all use to make sense of people's behavior in terms of their beliefs, goals, plans, and emotions. These are also the theories we employ when we anthropomorphize complex machines and computers as if they had humanlike mental lives. In order to successfully cooperate and communicate with people, these theories will need to be represented explicitly in future artificial intelligence systems. This book provides a large-scale logical formalization of commonsense psychology in support of humanlike artificial intelligence. It uses formal logic to encode the deep lexical semantics of the full breadth of psychological words and phrases, providing fourteen hundred axioms of first-order logic organized into twenty-nine commonsense psychology theories and sixteen background theories. This in-depth exploration of human commonsense reasoning for artificial intelligence researchers, linguists, and cognitive and social psychologists will serve as a foundation for the development of humanlike artificial intelligence.

A summary is not available for this content so a preview has been provided. Please use the Get access link above for information on how to access this content.

A summary is not available for this content so a preview has been provided. Please use the Get access link above for information on how to access this content.

By the time we have become fluent speakers of our native languages, we have learned to use thousands of words and phrases to refer to mental states and processes of ourselves and others. This richness in vocabulary parallels the complexity of the commonsense psychological model that defines the deep lexical semantics of these linguistic expressions. By studying the richness of psychological language, we learn about the various facets of the knowledge representation challenge, and its overall breadth of scope.

A summary is not available for this content so a preview has been provided. Please use the Get access link above for information on how to access this content.

Despite the attention that various forms of ellipsis have received in the liter ature, the conditions under which a representation of an utterance may serve as a suitable referent for interpreting subsequent elliptical forms remain poorly understood. This fun damental question remains as a point of contention, particularly because there are data to support various conflicting approaches that attempt to characterize these conditions within a single module of language processing. We show a previously unnoticed pattern in VP ellipsis data with respect to the type of coherence relation extant between the antecedent and elided clauses. This pattern is explained by an account of how ellipsis resolution pro cesses interact with the inference processes underlying the establishment of these relations. The analysis also explains a similar yet distinct pattern in gapping constructions which are not accounted for by purely syntactic approaches. Finally, we discuss event reference and compare the resulting account to the dichotomy of types of anaphora posited by Hankamer and Sag (1976).

Metaphor is a central phenomenon of language, and thus a central problem for natural language understanding.Previous work on the analysis of metaphors has identified which target concepts are being thought of and described in terms of which source concepts, but this is not adequate to explain what motivates the use of particular metaphors.This work proposes the use of conceptual schemas to represent the underspecified scenarios that motivate a metaphoric mapping.To support the creation of systems that can understand metaphors in this way, we have created and are publicly releasing a corpus of manually validated metaphor annotations.

Metaphor is a cognitive phenomenon exhibited in language, where one conceptual domain (the target) is thought of in terms of another (the source). The first level of metaphor interpretation is the mapping of linguistic metaphors to pairs of source and target concepts. Based on the abductive approach to metaphor interpretation proposed by Hobbs (1992) and implemented in the open-source Metaphor-ADP system (Ovchinnikova et al., 2014), we present work to automatically learn knowledge bases to support high-precision conceptual metaphor mapping in English, Spanish, Farsi, and Russian.

Metaphor is a cognitive phenomenon exhibited in language, where one conceptual domain (the target) is thought of in terms of another (the source). The first level of metaphor interpretation is the mapping of linguistic metaphors to pairs of source and target concepts. Based on the abductive approach to metaphor interpretation proposed by Hobbs (1992) and implemented in the open-source Metaphor-ADP system (Ovchinnikova et al., 2014), we present work to automatically learn knowledge bases to support high-precision conceptual metaphor mapping in English, Spanish, Farsi, and Russian.

We present a method for finding (STATE, EVENT) pairs where EVENT can change STATE. For example, the event “realize” can put an end to the states “be unaware”, “be confused”, and “be happy”; while it can rarely affect “being hungry”. We extract these pairs from a large corpus using a fixed set of syntactic dependency patterns. We then apply a supervised Machine Learning algorithm to clean the results using syntactic and collocational features, achieving a precision of 78% and a recall of 90%. We observe 3 different relations between states and events that change them and present a method for using Mechanical Turk to differentiate between these relations

This paper presents a metaphor interpretation pipeline based on abductive inference. In this framework following (Hobbs, 1992) metaphor interpretation is modelled as a part of the general discourse processing problem, such that the overall discourse coherence is supported. We present an experimental evaluation of the proposed approach using linguistic data in English and Russian.

We have been engaged in the project of encoding commonsense theories of cognition, or how we think we think, in a logical representation. In this paper we use the concept of a "serious threat" as our prime example, and examine the infrastructure required for capturing the meaning of this complex concept. It is one of many examples we could have used, but it is particularly interesting because building up to this concept from fundamentals, such as causality and scalar notions, highlights a number of representational issues that have to be faced along the way, where the complexity of the target concepts strongly influences how we resolve those issues. We first describe our approach to definition, defeasibility, and reification, where hard decisions have to bemade to get the enterprise off the ground.We then sketch our approach to causality, scalar notions, goals, and importance. Finally we use all this to characterize what it is to be a serious threat. All of this is necessarily sketchy, but the key ideas essential to the target concept should be clear.

Three major contributions that Charles Fillmore made in linguistics play an important role in the enterprise of deep lexical semantics, which is the effort to link lexical meaning to underlying abstract core theories. I will discuss how case relates to lexical decompositions, how motivated constructions span the borderline between syntax and semantics, and how the frames of FrameNet provide an excellent first step in deep inference.