Person:

Shieber, Stuart

This paper proposes a finite-state model for detecting harmonic cycles as described by neo-Riemannian theorists. Given a string of triads representing a harmonic analysis of a piece, the task is to identify and label all substrings corresponding to these cycles with high accuracy. The solution method uses a noisy channel model implemented with weighted finitestate transducers. On a dataset of four works by Franz Schubert, our model predicted cycles in the same regions as cycles in the ground truth with a precision of 0.18 and a recall of 1.0. The recalled cycles had an average edit distance of 3.2 insertions or deletions from the ground truth cycles, which average 6.4 labeled triads in length. We suggest ways in which our model could be used to contribute to current work in music theory, and be generalized to other music pattern-finding applications.

In his book The Most Human Human, Brian Christian extrapolates from his experiences at the 2009 Loebner Prize competition, a competition among chatbots (computer programs that engage in conversation with people) to see which is "most human." In doing so, he demonstrates once again that the human being may be the only animal that overinterprets.

This paper describes a challenging plan recognition problem that arises in environments in which agents engage widely in exploratory behavior, and presents new algorithms for effective plan recognition in such settings. In exploratory domains, agentsʼ actions map onto logs of behavior that include switching between activities, extraneous actions, and mistakes. Flexible pedagogical software, such as the application considered in this paper for statistics education, is a paradigmatic example of such domains, but many other settings exhibit similar characteristics. The paper establishes the task of plan recognition in exploratory domains to be NP-hard and compares several approaches for recognizing plans in these domains, including new heuristic methods that vary the extent to which they employ backtracking, as well as a reduction to constraint-satisfaction problems. The algorithms were empirically evaluated on peopleʼs interaction with flexible, open-ended statistics education software used in schools. Data was collected from adults using the software in a lab setting as well as middle school students using the software in the classroom. The constraint satisfaction approaches were complete, but were an order of magnitude slower than the heuristic approaches. In addition, the heuristic approaches were able to perform within 4% of the constraint satisfaction approaches on student data from the classroom, which reflects the intended user population of the software. These results demonstrate that the heuristic approaches offer a good balance between performance and computation time when recognizing peopleʼs activities in the pedagogical domain of interest.

In the line of research extending statistical parsing to more expressive grammar formalisms, we demonstrate for the first time the use of tree-adjoining grammars (TAG). We present a Bayesian nonparametric model for estimating a probabilistic TAG from a parsed corpus, along with novel block sampling methods and approximation transformations for TAG that allow efficient parsing. Our work shows performance improvements on the Penn Treebank and finds more compact yet linguistically rich representations of the data, but more importantly provides techniques in grammar transformation and statistical inference that make practical the use of these more expressive systems, thereby enabling further experimentation along these lines.

We present a Bayesian nonparametric model for estimating tree insertion grammars (TIG), building upon recent work in Bayesian inference of tree substitution grammars (TSG) via Dirichlet processes. Under our general variant of TIG, grammars are estimated via the Metropolis-Hastings algorithm that uses a context free grammar transformation as a proposal, which allows for cubic-time string parsing as well as tree-wide joint sampling of derivations in the spirit of Cohn and Blunsom (2010). We use the Penn treebank for our experiments and find that our proposal Bayesian TIG model not only has competitive parsing performance but also finds compact yet linguistically rich TIG representations of the data.

A major challenge in the field of automatic recognition of emotion and affect in speech is the subjective nature of affect labels. The most common approach to acquiring affect labels is to ask a panel of listeners to rate a corpus of spoken utterances along one or more dimensions of interest. For applications ranging from educational technology to voice search to dictation, a speaker’s level of certainty is a primary dimension of interest. In such applications, we would like to know the speaker’s actual level of certainty, but past research has only revealed listeners’ perception of the speaker’s level of certainty. In this paper, we present a method for eliciting spoken utterances using stimuli that we design such that they have a quantitative, crowdsourced legibility score. While we cannot control a speaker’s actual internal level of certainty, the use of these stimuli provides a better estimate of internal certainty compared to existing speech corpora. The Harvard Uncertainty Speech Corpus, containing speech data, certainty annotations, and prosodic features, is made available to the research community.

We tend to think of the study of language as proceeding by characterizing the strings and structures of a language, and we think of natural language processing as using those structures to build systems of utility in manipulating the language. But many language-related problems are more fruitfully viewed as requiring the specification of a relation between two languages, rather than the specification of a single language. We provide a synthesis and extension of work that unifies two approaches to such language relations: the automata-theoretic approach based on tree transducers that transform trees to their counterparts in the relation, and the grammatical approach based on synchronous grammars that derive pairs of trees in the relation. In particular, we characterize synchronous tree-substitution grammars and synchronous tree-adjoining grammars in terms of bimorphisms, which have previously been used to characterize tree transducers. In the process, we provide new approaches to formalizing the various concepts: a metanotation for describing varieties of tree automata and transducers in equational terms; a rigorous formalization of tree-adjoining and tree-substitution grammars and their synchronous counterparts, using trees over ranked alphabets; and generalizations of tree-adjoining grammar allowing multiple adjunction.

Anti-behaviorist arguments against the validity of the Turing Test as a sufficient condition for attributing intelligence are based on a memorizing machine, which has recorded within it responses to every possible Turing Test interaction of up to a fixed length. The mere possibility of such a machine is claimed to be enough to invalidate the Turing Test.

I consider the nomological possibility of memorizing machines, and how long a Turing Test they can pass. I replicate my previous analysis of this critical Turing Test length based on the age of the universe, show how considerations of communication time shorten that estimate and allow eliminating the sole remaining contingent assumption, and argue that the bound is so short that it is incompatible with the very notion of the Turing Test. I conclude that the memorizing machine objection to the Turing Test as a sufficient condition for attributing intelligence is invalid.