Bubble Networks: A Context-Sensitive Lexicon Representation
نویسنده
چکیده
The paradigm of packing semantics into words has long been the dogma of lexical semantics. As computational semantics is maturing as a field, we are beginning to see the failure of this paradigm. Pustejovsky’s Generative Lexicon is only able to have generative powers if the semantics packed within a word can anticipate possible combinations with other words. However, even an idealized Generative Lexicon will have to grapple with the effects of implicit, non-lexical context (e.g. topics, commonsense knowledge) on meaning determination. In this paper, we propose an intrinsic, connectionist network representation of a lexicon called a bubble network. In a bubble network, meaning is a result of graph traversal, from some word-concept node toward a context (e.g. “wedding” in the context of “ritual”), or toward another lexical item (e.g. “fast car”). Possible meanings are disambiguated using a modified spreading activation function which incorporates ideas of structural message-passing and active contexts. An encapsulation mechanism allows larger lexical expressions and assertional knowledge to be incorporated into the network, and along with the notion of utility-based learning of weights, helps to give a more natural account of lexical evolution (acquisition, deletion, generalization, individuation). A preliminary implementation and evaluation of bubble networks show that lexical expressions can be interpreted with remarkable contextsensitivity, but also point to some pragmatic problems in lexicon building using a bubble network.
منابع مشابه
Unpacking Meaning from Words: A Context-Centered Approach to Computational Lexicon Design
The knowledge representation tradition in computational lexicon design represents words as static encapsulations of purely lexical knowledge. We suggest that this view poses certain limitations on the ability of the lexicon to generate nuance-laden and context-sensitive meanings, because word boundaries are obstructive, and the impact of non-lexical knowledge on meaning is unaccounted for. Hopi...
متن کاملA Powerful And General Approach To Context Exploitation In Natural Language Processing
In natural language, the meaning of a lexeme often varies due to the specific surrounding context. Computational approaches to natural language processing can benefit from a reliable, long-range-context-dependent representation of the meaning of each lexeme that appears in a given sentence. We have developed a general new technique that produces a context-dependent ‘meaning’ representation for ...
متن کاملMental Representation of Cognates/Noncognates in Persian-Speaking EFL Learners
The purpose of this study was to investigate the mental representation of cognate and noncognate translation pairs in languages with different scripts to test the prediction of dual lexicon model (Gollan, Forster, & Frost, 1997). Two groups of Persian-speaking English language learners were tested on cognate and noncognate translation pairs in Persian-English and English-Persian directions with...
متن کاملA Reliable Routing Algorithm for Delay Sensitive Data in Body Area Networks
Wireless body Area networks (WBANs) include a number of sensor nodes placed inside or on the human body to improve patient health and quality of life. Ensuring the transfer and receipt of data in sensitive data is a very important issue. Routing algorithms should support a variety of service quality such as reliability and delay in sending and receiving data. Loss of information or excessive da...
متن کاملPrediction of Bubble Point Pressure & Asphaltene Onset Pressure During CO2 Injection Using ANN & ANFIS Models
Although CO2 injection is one of the most common methods in enhanced oil recovery, it could alter fluid properties of oil and cause some problems such as asphaltene precipitation. The maximum amount of asphaltene precipitation occurs near the fluid pressure and concentration saturation. According to the description of asphaltene deposition onset, the bubble point pressure has a very special imp...
متن کامل