Purver, M;
Sadrzadeh, M;
Kempson, R;
Wijnholds, G;
Hough, J;
(2021)
Incremental Composition in Distributional Semantics.
Journal of Logic, Language and Information
10.1007/s10849-021-09337-8.
(In press).
Preview |
Text
Purver2021_Article_IncrementalCompositionInDistri.pdf - Published Version Download (1MB) | Preview |
Abstract
Despite the incremental nature of Dynamic Syntax (DS), the semantic grounding of it remains that of predicate logic, itself grounded in set theory, so is poorly suited to expressing the rampantly context-relative nature of word meaning, and related phenomena such as incremental judgements of similarity needed for the modelling of disambiguation. Here, we show how DS can be assigned a compositional distributional semantics which enables such judgements and makes it possible to incrementally disambiguate language constructs using vector space semantics. Building on a proposal in our previous work, we implement and evaluate our model on real data, showing that it outperforms a commonly used additive baseline. In conclusion, we argue that these results set the ground for an account of the non-determinism of lexical content, in which the nature of word meaning is its dependence on surrounding context for its construal.
| Type: | Article |
|---|---|
| Title: | Incremental Composition in Distributional Semantics |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1007/s10849-021-09337-8 |
| Publisher version: | http://dx.doi.org/10.1007/s10849-021-09337-8 |
| Language: | English |
| Additional information: | Despite the incremental nature of Dynamic Syntax (DS), the semantic grounding of it remains that of predicate logic, itself grounded in set theory, so is poorly suited to expressing the rampantly context-relative nature of word meaning, and related phenomena such as incremental judgements of similarity needed for the modelling of disambiguation. Here, we show how DS can be assigned a compositional distributional semantics which enables such judgements and makes it possible to incrementally disambiguate language constructs using vector space semantics. Building on a proposal in our previous work, we implement and evaluate our model on real data, showing that it outperforms a commonly used additive baseline. In conclusion, we argue that these results set the ground for an account of the non-determinism of lexical content, in which the nature of word meaning is its dependence on surrounding context for its construal. |
| Keywords: | Incrementality, Semantics, Vector space semantics, Incremental disambiguation |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10132042 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
