Lenhart K. Schubert

Lenhart K. Schubert
University of Rochester | UR · Department of Computer Science

PhD

About

181
Publications
10,815
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
3,536
Citations
Citations since 2016
30 Research Items
443 Citations
2016201720182019202020212022020406080
2016201720182019202020212022020406080
2016201720182019202020212022020406080
2016201720182019202020212022020406080
Additional affiliations
August 1988 - December 2014
University of Rochester
Position
  • Professor
September 1973 - August 1989
University of Alberta
Position
  • Asst/Assoc/Full Professor

Publications

Publications (181)
Preprint
A schema-guided approach to dialogue management has been shown in recent work to be effective in creating robust customizable virtual agents capable of acting as friendly peers or task assistants. However, successful applications of these methods in open-ended, mixed-initiative domains remain elusive -- particularly within medical domains such as v...
Article
Full-text available
We present a conversational agent designed to provide realistic conversational practice to older adults at risk of isolation or social anxiety, and show the results of a content analysis on a corpus of data collected from experiments with elderly patients interacting with our system. The conversational agent, represented by a virtual avatar, is des...
Preprint
Full-text available
We present NESL (the Neuro-Episodic Schema Learner), an event schema learning system that combines large language models, FrameNet parsing, a powerful logical representation of language, and a set of simple behavioral schemas meant to bootstrap the learning process. In lieu of a pre-made corpus of stories, our dataset is a continuous feed of "situa...
Article
Full-text available
In this paper, we describe the iterative participatory design of SOPHIE, an online virtual patient for feedback-based practice of sensitive patient-physician conversations, and discuss an initial qualitative evaluation of the system by professional end users. The design of SOPHIE was motivated from a computational linguistic analysis of the transcr...
Article
Objective Communication difficulties negatively impact relationship quality and are associated with social isolation and loneliness in later life. There is a need for accessible communication interventions offered outside specialty mental health settings. Design Pilot randomized controlled trial. Setting Assessments in the laboratory and interven...
Conference Paper
Full-text available
We present the design of an online social skills development interface for teenagers with autism spectrum disorder (ASD). The interface is intended to enable private conversation practice anywhere , anytime using a web-browser. Users converse informally with a virtual agent, receiving feedback on nonverbal cues in real-time, and summary feedback. T...
Preprint
Full-text available
In this paper, we describe the iterative participatory design of SOPHIE, an online virtual patient for feedback-based practice of sensitive patient-physician conversations, and discuss an initial qualitative evaluation of the system by professional end users. The design of SOPHIE was motivated from a computational linguistic analysis of the transcr...
Chapter
Full-text available
Task-oriented dialogue-based spatial reasoning systems need to maintain history of the world/discourse states in order to convey that the dialogue agent is mentally present and engaged with the task, as well as to be able to refer to earlier states, which may be crucial in collaborative planning (e.g., for diagnosing a past misstep). We approach th...
Article
Full-text available
Discoplan is a durable and efficient system for inferring state constraints (invariants) in planning domains, specified in the PDDL language. It is exceptional in the range of constraint types it can discover and verify, and it directly allows for conditional effects in action operators. However, although various aspects of Discoplan have been prev...
Preprint
It is essential for dialogue-based spatial reasoning systems to maintain memory of historical states of the world. In addition to conveying that the dialogue agent is mentally present and engaged with the task, referring to historical states may be crucial for enabling collaborative planning (e.g., for planning to return to a previous state, or dia...
Preprint
The blocks world is a classic toy domain that has long been used to build and test spatial reasoning systems. Despite its relative simplicity, tackling this domain in its full complexity requires the agent to exhibit a rich set of functional capabilities, ranging from vision to natural language understanding. There is currently a resurgence of inte...
Preprint
Full-text available
We present some results concerning the dialogue behavior and inferred sentiment of a group of older adults interacting with a computer-based avatar. Our avatar is unique in its ability to hold natural dialogues on a wide range of everyday topics---27 topics in three groups, developed with the help of gerontologists. The three groups vary in ``degre...
Preprint
A growing interest in tasks involving language understanding by the NLP community has led to the need for effective semantic parsing and inference. Modern NLP systems use semantic representations that do not quite fulfill the nuanced needs for language understanding: adequately modeling language semantics, enabling general inferences, and being acc...
Preprint
Full-text available
We address the problem of designing a conversational avatar capable of a sequence of casual conversations with older adults. Users at risk of loneliness, social anxiety or a sense of ennui may benefit from practicing such conversations in private, at their convenience. We describe an automatic spoken dialogue manager for LISSA, an on-screen virtual...
Preprint
Full-text available
We present the design of an online social skills development interface for teenagers with autism spectrum disorder (ASD), who often lack access to social skills training. The interface is intended to enable private conversation practice anywhere, anytime using a browser. Users converse informally with an on-screen persona, receiving feedback on non...
Conference Paper
Full-text available
We summarize an exploratory investigation into using an autonomous conversational agent for improving the communication skills of teenagers with autism. The system conducts a natural conversation with the user and gives real-time and post-session feedback on the user’s nonverbal behavior. We obtained promising results and ideas for improvements in...
Conference Paper
Full-text available
This paper presents a rule-based approach to constructing lexical axioms from WordNet verb entries in an expressive semantic representation, Episodic Logic (EL). EL differs from other representations in being syntactically close to natural language and covering phenomena such as generalized quantification, modification, and intensionality while sti...
Conference Paper
There is ample evidence that human understanding of ordinary language relies in part on a rich capacity for imagistic mental modeling. We argue that genuine language understanding in machines will similarly require an imagistic modeling capacity enabling fast construction of instances of prototypical physical situations and events, whose participan...
Article
We present a flexible initial framework for defining self-motivated, self-aware agents in simulated worlds, planning continuously so as to maximize long-term rewards. While such agents employ reasoned exploration of feasible sequences of actions and corresponding states, they also behave opportunistically and recover from failure, thanks to their c...
Article
Recent implementations of Natural Logic (NLog) have shown that NLog provides a quite direct means of going from sentences in ordinary language to many of the obvious entailments of those sentences. We show here that Episodic Logic (EL) and its Epilog implementation are well-adapted to capturing NLog-like inferences, but beyond that, also support in...
Conference Paper
Full-text available
Word Net provides a semantic hierarchy with broad lexical coverage, which has proved sufficiently precise to boost performance at many tasks involving natural language. However, it has not yet been formalized for use in a general reasoning system. In this paper, we present such a formalization. We use a semi-automatic annotation of Word Net with le...
Article
Full-text available
We describe the goals, architecture, and functioning of the TRAINS-93 system, with emphasis on the representational issues involved in putting together a complex language processing and reasoning agent. The system is intended as an experimental prototype of an intelligent, conversationally proficient planning advisor in a dynamic domain of cargo tr...
Article
Full-text available
We characterize probabilities in Bayesian networks in terms of algebraic expressions called quasi-probabilities. These are arrived at by casting Bayesian networks as noisy AND-OR-NOT networks, and viewing the subnetworks that lead to a node as arguments for or against a node. Quasi-probabilities are in a sense the "natural" algebra of Bayesian netw...
Conference Paper
Commonsense reasoning requires knowledge about the frequency with which ordinary events and activities occur: How often do people eat a sandwich, go to sleep, write a book, or get married? This paper introduces work to acquire a knowledge base pairing factoids about such events with frequency categories learned from simple textual patterns. We are...
Article
Full-text available
Our approach to mind-design derives from the view of lan-guage as a mirror of mind – a view compatible with the linguis-tic orientation of the Turing Test, and more concretely, with the remarkably tight coupling between linguistic structure and semantic entailment demonstrated by Richard Montague. Ad-ditional evidence for the power of this perspect...
Conference Paper
In this paper we present the tree to tree transduction language, TTT. We motivate the overall "template-to-template" approach to the design of the language, and outline its constructs, also providing some examples. We then show that TTT allows transparent formalization of rules for parse tree refinement and correction, logical form refinement and p...
Conference Paper
Reasoning about ordinary human situations and activities requires the availability of diverse types of knowledge, including expectations about the probable results of actions and the lexical entailments for many predicates. We describe initial work to acquire such a collection of conditional (if--then) knowledge by exploiting presuppositional disco...
Chapter
The TRAINS project is a long-term research effort on building an intelligent planning assistant that is conversationally-proficient in natural language. The TRAINS project serves as an umbrella for research that involves pushing the state of the art in planning, natural language understanding, natural language dialog, and discourse modelling. Signi...
Article
Full-text available
There are two extreme stances in mechanizing natural language inference. One seeks to reformulate a raw message so as to conform with the syntax and semantics of some formal logical system (such as FOL) suited for reliable, potentially deep general reasoning. The other uses what has become known as Natural Logic—an easy but shallow way of treating...
Article
Full-text available
NAACL 2010 Workshop on Creating Speech and Language Data with Amazon's Mechanical Turk Efforts to automatically acquire world knowledge from text suffer from the lack of an easy means of evaluating the resulting knowledge. We describe initial experiments using Mechanical Turk to crowdsource evaluation to non-experts for little cost, resulting in a...
Conference Paper
Full-text available
We present our preliminary work on our framework for building self-motivated, self-aware agents that plan continuously so as to maximize long-term rewards. While such agents employ reasoned exploration of feasible sequences of actions and corresponding states, they also behave opportunistically and recover from failure, thanks to their quest for re...
Article
Recent work on entailment suggests that natural logics are well-suited to determining whether one sentence lexically entails another. We show how the EPILOG reasoning engine, designed for a natural language-like meaning representation (Episodic Logic, or EL), can be used to emulate natural logic inferences, while also enabling more general inferenc...
Article
Full-text available
AAAI 2010 Workshop on Collaboratively-built Knowledge Sources and Artificial Intelligence (WikiAI 2010) The quality and nature of knowledge that can be found by an automated knowledge-extraction system depends on its inputs. For systems that learn by reading text, the Web offers a breadth of topics and currency, but it also presents the problems of...
Article
Full-text available
AAAI 2010 Fall Symposium on Commonsense Knowledge. The KNEXT system produces a large volume of factoids from text, expressing possibilistic general claims such as that ‘A PERSON MAY HAVE A HEAD’ or ‘PEOPLE MAY SAY SOME- THING’. We present a rule-based method to sharpen certain classes of factoids into stronger, quantified claims such as ‘ALL OR MOS...
Article
Full-text available
Most work on self-motivated agents has focused on ac- quiring utility-optimizing mappings from states to ac- tions. But such mappings do not allow for explicit, rea- soned anticipation and planned achievement of future states and rewards, based on symbolic knowledge about the environment and about the consequences of the agent's own behavior. In es...
Conference Paper
Full-text available
We describe the use of a weakly supervised bootstrapping algorithm in discovering con- trasting semantic categories from a source lex- icon with little training data. Our method pri- marily exploits the patterns in sentential con- texts where different categories of words may appear. Experimental results are presented showing that such automaticall...
Conference Paper
Full-text available
Fifth International Conference on Knowledge Capture (K-CAP 2009) Knowledge extraction (KE) efforts have often used corpora of heavily edited writing and sources written to provide the desired knowledge (e.g., newspapers or textbooks). However, the proliferation of diverse, up-to-date, unedited writing on the Web, especially in weblogs, offers new c...
Conference Paper
Full-text available
Existing work in the extraction of com- monsense knowledge from text has been primarily restricted to factoids that serve as statements about what may possibly ob- tain in the world. We present an ap- proach to deriving stronger, more general claims by abstracting over large sets of factoids. Our goal is to coalesce the ob- served nominals for a gi...
Article
Full-text available
It can be quite hard to objectively evaluate a reasoner geared towards commonsense problems and natural language appli- cations if it uses a nonstandard logical language for which there exist no publicly available datasets. We describe here the evaluation of our recent improvements of the EPILOG system, a reasoner for Episodic Logic, a superset of...
Conference Paper
Full-text available
We report on the large-scale acquisition of class attributes with and without the use of lists of representative instances, as well as the discovery of unary attributes, such as typically expressed in English through prenominal adjectival modifica- tion. Our method employs a system based on compositional language processing, as applied to the Briti...
Article
Full-text available
We present results for a system designed to perform Open Knowledge Extraction, based on a tradition of compositional lan-guage processing, as applied to a large collection of text derived from the Web. Evaluation through manual assessment shows that well-formed propositions of reasonable quality, representing general world knowledge, given in a log...
Article
Full-text available
Our goal is the accumulation of general knowledge, such as that a room may have windows; people may want to be rid of a dictator; when a person enters a room, it is generally through a door; and when a car crashes, the driver and passengers may well be hurt or killed. The applications we are working on are (1) improved guidance of a parser; (2) sup...
Article
Full-text available
In this paper we summarise our progress towards building a self-aware agent based on the definition of explicit self- awareness. An explicit self-aware agent is characterised by 1) being based on an extensive and human-like knowledge base, 2) being transparent both in its behaviour and in how the knowledge is represented and used, and 3) being able...
Article
Full-text available
This report proposes a generalization of Dynamic Predicate Logic that allows a straightforward treatment of functional anaphora in texts such as "Most men had a gun, but only a few used it," or "If all of the graduates received a job offer, then all of them accepted their offer." The approach dynamically assigns (partial) functions as values of var...
Conference Paper
Full-text available
We propose methods of employing autocognitive inferenceas a realistic, feasible way for an agent to make many inferences about its own mind and about the world that have often been regarded in the past as depending on nonmonotonic reason- ing. The keys to realism are (1) to use a computable notion of knowing (without sacrificing expressiveness), ra...
Chapter
Full-text available
We extend our theory of English tense, aspect and time adverbials [Hwang and Schubert, 1992, 1993] to deal with a wider range of time adverbials, including many adverbials of frequency, cardinality, duration, and time span, and adverbials of temporal relation involving subordinating conjunctions such as after, since, and until. Our theory is fully...
Conference Paper
Full-text available
There is a set of clear-cut challenges, all center- ing around knowledge, that have received insufc ient atten- tion in AI, and whose solution could bring the realization of Turing's dream ñ the dream of a machine we can talk with just like a person, and which is therefore (at least) our intel- lectual equal. These challenges have to do with the re...
Article
Full-text available
Planning invariants are formulae that are true in every reachable state of a planning world. We describe a novel approach to the problem of discovering such invariants in propositional form---by analyzing only a set of reachable states of the planning domain, and not its operators. Our system works by exploiting perceived patterns of propositional...
Conference Paper
Full-text available
Planning invariants are formulae that are true in every reach- able state of a planning world. We describe a novel approach to the problem of discovering such invariants—by analyzing only a reachable state of the planning domain, and not its op- erators. Our system works by exploiting perceived patterns and anomalies in the state description: It hy...
Article
Full-text available
This paper motivates and defines a notion of explicit self- awareness, one that implies human-like scope of the self- model, and an explicit internal representation susceptible to general inference methods and permitting overt communi- cation about the self. The features proposed for knowl- edge representation and reasoning supporting explicit self...
Article
DISCOPLAN is an implemented set of efficient preplanning algorithms intended to enable faster domain-independent planning. It includes algorithms that use a hypothesize-and-test paradigm to discover and inductively verify state constraints (invariants) implicit in the structure of a given set of planning operators and initial state. Such state cons...
Conference Paper
Full-text available
We have been developing techniques for extracting general world knowledge from miscellaneous texts by a process of approximate interpretation and abstraction, focusing initially on the Brown corpus. We apply interpretive rules to clausal patterns and patterns of modification, and concurrently abstract general "possibilistic " propositions from the...
Article
this paper. Specifically, it does not have a closure requirement---the fact that belief in / can eventually follow from belief in Phi does not entail that the beliefs generated from Phi [ f/g in a certain amount of time are the same as those generated from Phi alone in the same amount of time. The tradeoff 15 is that in order to apply this form of...
Article
Full-text available
As one attack on the "knowledge acquisition bottleneck", we are attempting to exploit a largely untapped source of general knowledge in texts, lying at a level beneath the explicit assertional content. This knowledge consists of relationships implied to be possible in the world, or, under certain conditions, implied to be normal or commonplace in t...
Article
Full-text available
In this paper, we present a hybrid logic with a sound and complete tableau system for reasoning about situations. We identify our satisfaction relation between states and formulas with a characterization relation between situations and formulas and introduce a binary modality for reasoning about conjoined situations. 1 Describing eventualities This...
Article
Full-text available
We present a parsing system built from a handwritten lexicon and grammar, and trained on a selection of the Brown Corpus. On the sentences it can parse, the parser performs as well as purely corpus-based parsers. Its advantage lies in the fact that its syntactic analyses readily support semantic interpretation. Moreover, the system's hand-written f...
Article
Full-text available
this paper will be with the semantic rules that define immediate logical form, although we attempt to define this form in a way that minimizes the remaining gap to the deeper representation
Article
Full-text available
We present a new compositional tense-aspect deindexing mechanism that makes use of tense trees as components of discourse contexts. The mechanism allows reference episodes to be correctly identified even for embedded clauses and for discourse that involves shifts in temporal perspective, and permits deindexed logical forms to be automatically compu...
Article
Full-text available
It is argued that syntactic preference principles such as Right Association and Minimal Attachment are unsatisfactory as usually formulated. Among the difficulties are: (1) dependence on ill-specified or implausible principles of parser operation; (2) dependence on questionable assumptions about syntax; (3) lack of provision, even in principle, for...
Article
We describe a parser that draws from both extant corpora and linguistic knowledge sources, and thus is suitable as a front end for applications requiring both broad coverage and rich syntactic analysis. We detail many of the diculties and assumptions involved in combining these data and knowledge sources. We also describe the novel language model t...
Article
. The paper is concerned with the succinct axiomatization and ecient deduction of non-change, within McCarthy and Hayes' Situation Calculus. The idea behind the proposed approach is this: suppose that in a room containing a man, a robot and a cat as the only potential agents, the only action taken by the man within a certain time interval is to wal...
Article
WordNet is a lexical database that, among other things, arranges English nouns into a hierarchy ranked by specificity, providing links between a more general word and words that are specializations of it. For example, the word "mammal" is linked (transitively via some intervening words) to "dog" and to "cat." This hierarchy bears some resemblance t...
Article
Full-text available
This paper presents a grammatical and processing framework for handling speech repairs. The proposed framework has proved adequate for a collection of human-human task-oriented dialogs, both in a full manual examination of the corpus, and in tests with a parser capable of parsing some of that corpus. This parser can also correct a pre-parser speech...
Article
Full-text available
Mixed-initiative dialogs often contain interruptions in phrase structure such as repairs and backchannel responses. Phrase structure as traditionally defined does not accommodate such phenomena, so it is not surprising that phrase structure parsers are ill-equipped to handle them. This paper presents metarules that specify how the instantiations of...
Article
Full-text available
Most dialog systems ignore the problem of speech repairs and editing terms (um, uh, etc.) or use preprocessing techniques to eliminate them from the input. These systems also typically enforce a strict turn-taking protocol that does not allow speakers to interrupt each other. This paper describes a parser that can process input containing editing t...
Article
This paper presents a grammatical and processing framework for handling the repairs, hesitations, and other interruptions in natural human dialog. The proposed framework has proved adequate for a collection of human-human task-oriented dialogs, both in a full manual examination of the corpus, and in tests with a parser capable of parsing some of th...
Article
Full-text available
Mixed-initiative dialogs often contain interruptions in phrase structure such as repairs and backchannel responses. Phrase structure as traditionally defined does not accommodate such phenomena, so it is not surprising that phrase structure parsers are ill-equipped to handle them. This paper presents metarules that specify how phrase structure rule...
Article
Full-text available
We describe some new preprocessing techniques that enable faster domain-independent planning. The first set of techniques is aimed at inferring state constraints from the structure of planning operators and the initial state. Our methods consist of generating hypothetical state constraints by inspection of operator effects and preconditions, and ch...
Article
. I argue in favor of associating situations (events, episodes, eventualities, etc.) with arbitrarily complex sentences, not just atomic predicates, in NL interpretation. In that respect, a Situation Semantics approach to incorporating situations into semantic representations is preferable to a Davidsonian one. However, I will further argue that be...
Article