Meaning Genesis: Functional dynamic modeling of semantic structures for Discourse Analysis (original) (raw)

Can Discourse Relations be Identified Incrementally?

2017

Humans process language word by word and construct partial linguistic structures on the fly before the end of the sentence is perceived. Inspired by this cognitive ability, incremental algorithms for natural language processing tasks have been proposed and demonstrated promising performance. For discourse relation (DR) parsing, however, it is not yet clear to what extent humans can recognize DRs incrementally, because the latent ‘nodes’ of discourse structure can span clauses and sentences. To answer this question, this work investigates incrementality in discourse processing based on a corpus annotated with DR signals. We find that DRs are dominantly signaled at the boundary between the two constituent discourse units. The findings complement existing psycholinguistic theories on expectation in discourse processing and provide direction for incremental discourse parsing.

Proceedings of the 2nd Workshop on Computational Approaches to Discourse

2021

Welcome to the 2nd Workshop on Computational Approaches to Discourse, CODI 2021! CODI is intended to provide a venue for researchers working on all aspects of discourse. Our aim is to provide a venue for the entire discourse processing community where we can present and exchange our theories, algorithms, software, datasets, and tools. The workshop consists of invited talks, contributed paper and demo presentations, and discussion sessions. We received paper submissions that span a wide range of topics, addressing issues related to discourse representation and parsing, anaphora and coreference resolution, dialogue, applications, and more. As the workshop is hybrid this year, papers are presented live either in person or remotely and discussed during live Q&A sessions. There will also be prerecorded videos available. We are happy that CODI 2021 features two shared tasks. The CODI-CRAC 2021 shared task on anaphora, bridging, and discourse deixis resolution in dialogue is a joint shared task between the CODI and CRAC workshops at EMNLP. This shared task goes beyond previous ones as its input is transcribed spoken dialogue, and in that it includes anaphoric relations beyond coreference. This effort is spearheaded by Carolyn Rosé. The DISRPT 2021 shared task continues a series of successful DISRPT shared tasks on discourse segmentation, relation classification and connective detection. The organization team is led by Amir Zeldes. As we hope that the next CODI workshops will also feature shared tasks and other special events, the workshop also includes a discussion on future shared tasks, special sessions on discourse representation and parsing, coreference resolution, and multilingual discourse processing. We thank our invited speakers, Jackie Chi Kit Cheung, McGill University, who works on language understanding and question answering in context, and Vera Demberg, Saarland University, who works on computational and cognitive models of text generation and understanding. We would also like to thank our reviewers for their thoughtful and instructive comments. They helped us to prepare an inclusive workshop program. Finally we would like to thank the EMNLP 2021 workshop chairs Parisa Kordjamshidi and Minlie Huang who organized the EMNLP workshop program under very challenging circumstances.

A SY}~ACTIC APPROACH TO DISCOURSE SEMANTICS

A correct structural analysis of a discourse is a prerequisite for understanding it. This paper sketches the outline of a discourse grammar which acknowledges several different levels of structure. This gram~nar, the "Dynamic Discourse Model", uses an Augmented Transition Network parsing mechanism to build a representation of the semantics of a discourse in a stepwise fashion, from left to right, on the basis of the semantic representations of the individual clauses which constitute the discourse. The intermediate states of the parser model the intermediate states of the social situation which generates the discourse.

The Many Functions of Discourse Particles: A Computational Model of Pragmatic Interpretation

We present a connectionist model for the interpretation of discourse particles in real dialogues that is based on neuronal principles of categorization (categorical perception, prototype formation, contextual interpretation). It can be shown that discourse particles operate just like other morphological and lexical items with respect to interpretation processes. The description proposed locates discourse particles in an elaborate model of communication which incorporates many different aspects of the communicative situation. We therefore also attempt to explore the content of the category discourse particle. We present a detailed analysis of the meaning assignment problem and show that 80% -90% correctness for unseen discourse particles can be reached with the feature analysis provided. Furthermore, we show that 'analogical transfer' from one discourse particle to another is facilitated if prototypes are computed and used as the basis for generalization. We conclude that the interpretation processes which are a part of the human cognitive system are very similar with respect to different linguistic items. However, the analysis of discourse particles shows clearly that any explanatory theory of language needs to incorporate a theory of communication processes.

Computational Approaches to Discourse and Document Processing

TAL, 2006

This introduction tracks the evolution of the definition and role of discourse issues in NLP from the knowledge-intensive "discourse understanding" methods of the 80's to the recent concern with "accessing contents" in vast document bases via data-intensive methods. As text/discourse linguistics moves toward corpus approaches, also in connection with the development of large text bases and of computational instruments, we explore potential new forms of convergence.

Bridging computational, formal and psycholinguistic approaches to language

We compare our model of unsupervised learning of linguistic structures, ADIOS , to some recent work in computational linguistics and in grammar theory. Our approach resembles the Construction Grammar in its general philosophy (e.g., in its reliance on structural generalizations rather than on syntax projected by the lexicon, as in the current generative theories), and the Tree Adjoining Grammar in its computational characteristics (e.g., in its apparent affinity with Mildly Context Sensitive Languages). The representations learned by our algorithm are truly emergent from the (unannotated) corpus data, whereas those found in published works on cognitive and construction grammars and on TAGs are hand-tailored. Thus, our results complement and extend both the computational and the more linguistically oriented research into language acquisition. We conclude by suggesting how empirical and formal study of language can be best integrated.

Activating basic category exemplars in sentence contexts: A dynamical account

Journal of …, 2008

This paper examines the influence of context on the processing of category names embedded in sentences. The investigation focuses on the nature of information available immediately after such a word is heard as well as on the dynamics of adaptation to context. An on-line method (Cross Modal Lexical Priming) was used to trace how this process unfolds in time. We found that the information available immediately after a category word is presented is not altered by the sentence context in which the word is immersed. Rather, the structure of availability of particular exemplars of the category resembles the typicality structure of a conceptual representation. The adaptation to context occurs later (between 300 and 450 ms after the category word) and takes the form of a rapid reorganization of the structure rather than a gradual activation of a contextually relevant exemplar. We claim that such data is best accounted for in a dynamical framework, where a coherent global structure emerges through locally guided self-organization.

Realization of discourse relations by other means: alternative lexicalizations

Proceedings of the 23rd …, 2010

Studies of discourse relations have not, in the past, attempted to characterize what serves as evidence for them, beyond lists of frozen expressions, or markers, drawn from a few well-defined syntactic classes. In this paper, we describe how the lexicalized discourse relation annotations of the Penn Discourse Treebank (PDTB) led to the discovery of a wide range of additional expressions, annotated as AltLex (alternative lexicalizations) in the PDTB 2.0. Further analysis of AltLex annotation suggests that the set of markers is openended, and drawn from a wider variety of syntactic types than currently assumed. As a first attempt towards automatically identifying discourse relation markers, we propose the use of syntactic paraphrase methods.

Dynamical Systems Implementation of Intrinsic Sentence Meaning

Minds and Machines, 2022

This paper proposes a model for implementation of intrinsic natural language sentence meaning in a physical language understanding system, where 'intrinsic' is understood as 'independent of meaning ascription by system-external observers'. The proposal is that intrinsic meaning can be implemented as a point attractor in the state space of a nonlinear dynamical system with feedback which is generated by temporally sequenced inputs. It is motivated by John Searle's well known (1980) critique of the then-standard and currently still influential Computational Theory of Mind (CTM), the essence of which was that CTM representations lack intrinsic meaning because that meaning is dependent on ascription by an observer. The proposed dynamical model comprises a collection of interacting artificial neural networks, and constitutes a radical simplification of the principle of compositional phrase structure which is at the heart of the current standard view of sentence semantics because it is computationally interpretable as a finite state machine.