Abstract
We develop a vector space semantics for verb phrase ellipsis with anaphora using type-driven compositional distributional semantics based on the Lambek calculus with limited contraction (LCC) of Jäger (Anaphora and type logical grammar, Springer, Berlin, 2006). Distributional semantics has a lot to say about the statistical collocation based meanings of content words, but provides little guidance on how to treat function words. Formal semantics on the other hand, has powerful mechanisms for dealing with relative pronouns, coordinators, and the like. Type-driven compositional distributional semantics brings these two models together. We review previous compositional distributional models of relative pronouns, coordination and a restricted account of ellipsis in the DisCoCat framework of Coecke et al. (Mathematical foundations for a compositional distributional model of meaning, 2010. arXiv:1003.4394, Ann Pure Appl Log 164(11):1079–1100, 2013). We show how DisCoCat cannot deal with general forms of ellipsis, which rely on copying of information, and develop a novel way of connecting typelogical grammar to distributional semantics by assigning vector interpretable lambda terms to derivations of LCC in the style of Muskens and Sadrzadeh (in: Amblard, de Groote, Pogodalla, Retoré (eds) Logical aspects of computational linguistics, Springer, Berlin, 2016). What follows is an account of (verb phrase) ellipsis in which word meanings can be copied: the meaning of a sentence is now a program with non-linear access to individual word embeddings. We present the theoretical setting, work out examples, and demonstrate our results with a state of the art distributional model on an extended verb disambiguation dataset.
Highlights
Distributional semantics is a field of research within computational linguistics that provides an implementable algorithm with an empirically verifiable output for representing word meanings and degrees of semantic similarity thereof
What was novel in previous work was that we discovered and showed how the use of Frobenius copying/dispatching of information does not work for resolving ellipsis, 1 The work of Kruszewski et al (2016) gives a distributional semantic account of conversational negation
Similar to previous work (Wijnholds and Sadrzadeh 2018), we argue for a simple revision of the DisCoCat framework (Coecke et al 2013) in order to allow us to incorporate a proper notion of reuse of resources: instead of directly interpreting derivations as linear maps, where it becomes impossible to have a map that copies word embeddings (Jacobs 2011; Abramsky 2009), we decompose the interpretation of grammar derivations into a twostep process, relying on a non-linear typed lambda calculus, in the style of (Muskens and Sadrzadeh 2016, 2019)
Summary
Distributional semantics is a field of research within computational linguistics that provides an implementable algorithm with an empirically verifiable output for representing word meanings and degrees of semantic similarity thereof. Similar to previous work (Wijnholds and Sadrzadeh 2018), we argue for a simple revision of the DisCoCat framework (Coecke et al 2013) in order to allow us to incorporate a proper notion of reuse of resources: instead of directly interpreting derivations as linear maps, where it becomes impossible to have a map that copies word embeddings (Jacobs 2011; Abramsky 2009), we decompose the interpretation of grammar derivations into a twostep process, relying on a non-linear typed lambda calculus, in the style of (Muskens and Sadrzadeh 2016, 2019).
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
