Andrew Kehler

Coherence and the Resolution of Ellipsis

Despite the attention that various forms of ellipsis have received inthe literature, the conditions under which a representation of anutterance may serve as a suitable referent for interpreting subsequentelliptical forms remain poorly understood. This fundamental questionremains as a point of contention, particularly because there are datato support various conflicting approaches that attempt to characterizethese conditions within a single module of language processing. Weshow a previously unnoticed pattern in VP-ellipsis data with respectto the type of coherence relation extant between the antecedentand elided clauses. This pattern is explained by an account of howellipsis resolution processes interact with the inference processesunderlying the establishment of these relations. The analysis alsoexplains a similar yet distinct pattern in gapping constructions whichare not accounted for by purely syntactic approaches. Finally, wediscuss event reference and compare the resulting account to thedichotomy of types of anaphora posited by HanSag.

Automatic speech recognition in machine-aided translation

Abstract It has been observed that humans can translate nearly four times as quickly with little loss in accuracy simply by dictating, as opposed to typing, their translations. In this paper, we consider the integration of speech recognition into a translators workstation. In particular, we show how to combine statistical models of speech, language and translation into a single system that decodes a sequence of words in a target language from a sequence of words in a source language together with an utterance of the target language sequence. Results are provided which demonstrate that the difficulty of the speech recognition task can be reduced by making use of information contained in the source text being translated.

A probabilistic reconciliation of coherence-driven and centering-driven theories of pronoun interpretation

Abstract Two classic theories of pronoun interpretation have each sought to specify the relationship between pronoun use and discourse coherence, but make seemingly irreconcilable claims. According to Hobbs (1979, 1990), pronoun interpretation is not governed by an independent mechanism, but instead comes about as a by-product of utilizing world knowledge during the inferential establishment of discourse coherence relations. Factors pertaining to the grammatical form and information structure of utterances do not come into play. According to Centering Theory (Grosz, Joshi & Weinstein 1995; inter alia), on the other hand, pronoun interpretation is predominantly determined by information structural relationships within and between utterances (e.g., topic transitions) and the grammatical roles occupied by potential referents. Factors pertaining to world knowledge and the establishment of informational coherence relations do not come into play. In this paper, we describe a series of psycholinguistic experiments that ultimately suggest a reconciliation of these diverse approaches. These experiments reveal a definitive role for coherence relationships of the Hobbsian sort, demonstrating that pronoun interpretation is affected by (i) probabilistic expectations that comprehenders have about what coherence relationships will ensue, and (ii) their expectations about what entities will be mentioned next which, crucially, are conditioned on those coherence relationships. However, these experiments also reveal a role played by the topichood status of potential referents. These data are reconciled by a probabilistic model that combines the comprehenders prior coherence-driven expectations about what entities will be referred to next and Centering-driven likelihoods that govern the speakers choice of referential form. The approach therefore situates pronoun interpretation within a larger body of work in psycholinguistics, according to which language interpretation results when top-down predictions about the ensuing message meet bottomup linguistic evidence.

Grammatical and information-structural influences on pronoun production

A standard assumption in psycholinguistic research on pronoun interpretation is that production and interpretation are guided by the same set of contextual factors. A line of recent research has suggested otherwise, however, arguing instead that pronoun production is insensitive to a class of semantically driven contextual biases that have been shown to influence pronoun interpretation. The work reported in this paper addresses three fundamental questions that have been left unresolved by this research. First, research demonstrating the insensitivity of production to semantic biases has relied on referentially unambiguous settings in which the comprehenders ability to resolve the pronoun is not actually at stake. Experiment 1, a story continuation study, demonstrates that pronoun production is also insensitive to semantic biases in settings in which a pronoun would be referentially ambiguous. Second, previous research has not distinguished between accounts in which production biases are driven by grammatical properties of intended referents (e.g., subject position) or by information-structural factors (specifically, topichood) that are inherently pragmatic in nature. Experiment 2 examines this question with a story continuation study that manipulates the likelihood of potential referents being the topic while keeping grammatical role constant. A significant effect of the manipulation on rate of pronominalisation supports the claim that pronoun production is influenced by the likelihood that the referent is the current topic. Lastly, the predictions of Kehler et al.s Bayesian analysis of the relationship between production and interpretation have never been quantitatively examined. The results of both experiments are shown to support the analysis over two competing models.

THE EFFECT OF ESTABLISHING COHERENCE IN ELLIPSIS AND ANAPHORA RESOLUTION

This paper presents a new model of anaphoric processing that utilizes the establishment of coherence relations between clauses in a discourse. We survey data that comprises a currently stalemated argument over whether VP-ellipsis is an inherently syntactic or inherently semantic phenomenon, and show that the data can be handled within a uniform discourse processing architecture. This architecture, which revises the dichotomy between ellipsis vs. Model Interpretive Anaphora given by Sag and Hankamer (1984), is also able to accommodate divergent theories and data for pronominal reference resolution. The resulting architecture serves as a baseline system for modeling the role of cohesive devices in natural language.

A discourse copying algorithm for ellipsis and anaphora resolution

We give an analysis of ellipsis resolution in terms of a straightforward discourse copying algorithm that correctly predicts a wide range of phenomena. The treatment does not suffer from problems inherent in identity-of-relations analyses. Furthermore, in contrast to the approach of Dalrymple et al. [1991], the treatment directly encodes the intutive distinction between full NPs and the referential elements that corefer with them through what we term role linking. The correct predictions for several problematic examples of ellipsis naturally result. Finally, the analysis extends directly to other discourse copying phenomena.

A Theory of Parallelism and the Case of VP Ellipsis

We provide a general account of parallelism in discourse, and apply it to the special case of resolving possible readings for instances of VP ellipsis. We show how several problematic examples are accounted for in a natural and straightforward fashion. The generality of the approach makes it directly applicable to a variety of other types of ellipsis and reference.

COMMON TOPICS AND COHERENT SITUATIONS: INTERPRETING ELLIPSIS IN THE CONTEXT OF DISCOURSE INFERENCE

It is claimed that a variety of facts concerning ellipsis, event reference, and interclausal coherence can be explained by two features of the linguistic form in question: (1) whether the form leaves behind an empty constituent in the syntax, and (2) whether the form is anaphoric in the semantics. It is proposed that these features interact with one of two types of discourse inference, namely Common Topic inference and Coherent Situation inference. The differing ways in which these types of inference utilize syntactic and semantic representations predicts phenomena for which it is otherwise difficult to account.

Discourse topics, sentence topics, and coherence

In his contribution ‘‘Discourse Topic’’, Nicholas Asher questions the desirability of pursuing a general and unified notion of discourse topic, arguing that ‘‘di¤erent coherence relations make di¤erent demands on what topics should do’’. He and I are of like minds with respect to the inclination to view this question from the perspective of a theory of discourse coherence that involves the inference of relations as holding among discourse segments. As there is ample independent evidence that such inference processes are an essential part of discourse comprehension, it is only fruitful to assess the status of discourse topic over and above the work already done by coherence establishment: Is a separate notion of discourse topic necessary, or does it emerge purely as an epiphenomenon? Asher draws the conclusion that topics are not needed when most coherence relations are operative – they emerge naturally from the semantics of relations like Parallel and Contrast, and are superfluous for causal and subordinating relations – but that the construction of a topic is an essential part of establishing Narration. My contribution is divided into two parts. I will first briefly explain why the evidence that Narration is di¤erent from other relations is not compelling enough for me to abandon the idea that discourse topichood is entirely emergent from discourse coherence. I then follow with what I consider to be evidence for an interaction between a more local notion of topic and coherence establishment.

TEMPORAL RELATIONS: REFERENCE OR DISCOURSE COHERENCE?

The temporal relations that hold between events described by successive utterances are often left implicit or underspecified. We address the role of two phenomena with respect to the recovery of these relations: (1) the referential properties of tense, and (2) the role of temporal constraints imposed by coherence relations. We account for several facets of the identification of temporal relations through an integration of these.