Spoken Language Parsing based on Incremental Disambiguation (original) (raw)
Related papers
Incremental parsing for interactive natural language interface
2001
This paper proposes an effective incremental parsing method for such interactive natural language processing systems as real-time dialogue systems, simultaneous machine interpreting systems, etc. This method produces the analysis of the input while it is being received. It can efficiently deal with not only the normal input, which is piecemeal addition to the input from left to right, but also such changes of the input as insertion and deletion. For such changes of the input, this method exploits the parts of the previous analyses. We implemented this method on the workstation and made a experiment. We have confirmed that the method can be expected to be useful for an on-line language processing system.
Incremental parsing with reference interaction
Proceedings of the Workshop on Incremental Parsing Bringing Engineering and Cognition Together - IncrementParsing '04, 2004
We present a general architecture for incremental interaction between modules in a speech-tointention continuous understanding dialogue system. This architecture is then instantiated in the form of an incremental parser which receives suitability feedback on NP constituents from a reference resolution module. Oracle results indicate that perfect NP suitability judgments can provide a labelled-bracket error reduction of as much as 42% and an efficiency improvement of 30%. Preliminary experiments in which the parser incorporates feedback judgments based on the set of referents found in the discourse context achieve a maximum error reduction of 9.3% and efficiency gain of 4.6%. The parser is also able to incrementally instantiate the semantics of underspecified pronouns based on matches from the discourse context. These results suggest that the architecture holds promise as a platform for incremental parsing supporting continuous understanding.
Ambiguity Resolution Analysis in Incremental Parsing of Natural Language
IEEE Transactions on Neural Networks, 2005
Incremental parsing gains its importance in natural language processing and psycholinguistics because of its cognitive plausibility. Modeling the associated structures is believed to help a better understanding of the human parser. In earlier work we have introduced a recursive neural network capable of performing syntactic ambiguity resolution in incremental parsing. In this paper we report a systematic analysis of the behavior of the network that allows to gain important insights about the kind of information that is exploited to resolve different forms of ambiguity.
A framework for utterance disambiguation in dialogue
2000
We discuss the data sources available for ut- terance disambiguation in a bilingual dialogue system, distinguishing global, contextual, and user-specic domains, and syntactic and seman- tic levels. We propose a framework for combin- ing the available information, and techniques for increasing a stochastic grammar's sensitivity to local context and a speaker's idiolect.
Robust Parsing of Spoken Dialogue Using Contextual Knowledge and Recognition Probabilities
Computing Research Repository - CORR, 1995
In this paper we describe the linguistic processor of a spoken dialogue system. The parser receives a word graph from the recognition module as its input. Its task is to find the best path through the graph. If no complete solution can be found, a robust mecha- nism for selecting multiple partial results is applied. We show how the information content rate of the re- sults can be improved if the selection is based on an integrated quality score combining word recognition scores and context-dependent semantic predictions. Results of parsing word graphs with and without pre- dictions are reported.
Incremental parsing models for dialog task structure
Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics on - EACL '09, 2009
In this paper, we present an integrated model of the two central tasks of dialog management: interpreting user actions and generating system actions. We model the interpretation task as a classication problem and the generation task as a prediction problem. These two tasks are interleaved in an incremental parsing-based dialog model. We compare three alternative parsing methods for this dialog model using a corpus of human-human spoken dialog from a catalog ordering domain that has been annotated for dialog acts and task/subtask information. We contrast the amount of context provided by each method and its impact on performance.
Proceedings of the 16th conference on Computational linguistics -, 1996
In many contexts, automatic analyzers cannot fully disambiguate a sentence or an utterance reliably, but can produce ambiguous results containing the correct interpretation. It is useful to study vatious properties of these ambiguities in the view of subsequent total or partial interactive disambiguation. We have proposed a technique for labelling ambiguities in texts and in dialogue transcriptions, and experimented it on multilingual data. It has been first necessary to define formally the very notion of ambiguity relative to a representation system, as well as associated concepts such as ambiguity kernel, ambiguity scope, ambiguity occurrence.
On-line Interpretation in Speech Understanding and Dialogue Systems
Recent Advances in Speech Understanding and Dialog Systems, 1988
This paper addresses syntactic, semantic and pragmatic aspects of central concern in the design of on-line language understanding systems. In the area of syntax, the paper focuses on the phenomenon of discontinuous constituents. A form of syntactic representation is defined, called discontinuous trees, which allows the constituent structure of sentences with discontinuous constituents to be represented without changing the word order in the sentence. A kind of phrase-structure gram.mar is defined which can generate such representations, and an on-line parsing algorithm is presented which parses sentences into these representations. In the area of semantics, the paper focuses on the effective resolution of ambiguity and vagueness, and on the on-line interpretation of anaphora. For dealing with ambiguous and vague expressions in an effective, on-line manner a cascaded model-theoretic approach is developed which makes use of intermediate semantic representations in a formal language that preserves some of the ambiguity and vagueness in natural language. For the interpretation of anaphora, an approach is outlined that has recently been suggested by Groenendijk and Stokhof, based on the use of dynamic logic. In the area of pragmatics, the paper focuses on the analysis of informationexchange dialogues as consisting of communicative actions. The notion function of a communicative action is defined in terms of the flow of information between speaker and addressee. It is argued that Groenendijk and Stokhof's dynamic approach to semantic interpretation can be elegantly combined with this`functional' approach to communicative action into in an integrated theory of utterance meaning. The resulting`dyna~nic interpretation theory' is outlined, which offers exciting perspectives for a full-fledged, on-line utterance interpretation process. (1) A process F is on-line if there is a function f such that for every input sequence C il, iz, .., ik~: F(G ii~iz,.-~ik~)-f(F(C ai~iz~..~tk-l1~Zk) Note that, if C il, iz, .., ik 1 is a sequence of inputs which forms part of a complete input sequence G il, izi .., i"~, according to this definition the processing of that part indeed takes place immediately, as it does not depend on later inputs.
Finite-State Parsing And Disambiguation
1990
A language-independent method of finitestate surface syntactic parsing and word-disambiguation is discussed. Input sentences are represented as finite-state networks already containing all possible roles and interpretations of its units. Also syntactic constraint rules are represented as finite-state machines where each constraint excludes certain types of ungrammatical readings. The whole grammar is an intersection of its constraint rules and excludes all ungrammatical possibilities leaving the correct interpretation(s) of the sentence. The method is being tested for Finnish, Swedish and English.