Abstract
Neural networks have long been used to study linguistic phenomena spanning the domains of phonology, morphology, syntax, and semantics. Of these domains, semantics is somewhat unique in that there is little clarity concerning what a model needs to be able to do in order to provide an account of how the meanings of complex linguistic expressions, such as sentences, are understood. We argue that one thing such models need to be able to do is generate predictions about which further sentences are likely to follow from a given sentence; these define the sentence's “inferential role.” We then show that it is possible to train a tree-structured neural network model to generate very simple examples of such inferential roles using the recently released Stanford Natural Language Inference (SNLI) dataset. On an empirical front, we evaluate the performance of this model by reporting entailment prediction accuracies on a set of test sentences not present in the training data. We also report the results of a simple study that compares human plausibility ratings for both human-generated and model-generated entailments for a random selection of sentences in this test set. On a more theoretical front, we argue in favor of a revision to some common assumptions about semantics: understanding a linguistic expression is not only a matter of mapping it onto a representation that somehow constitutes its meaning; rather, understanding a linguistic expression is mainly a matter of being able to draw certain inferences. Inference should accordingly be at the core of any model of semantic cognition.
Highlights
By most accounts, linguistic comprehension is the result of cognitive processes that map between sounds and mental representations of meaning (e.g., Smolensky and Legendre, 2006; Pickering and Garrod, 2013; Christiansen and Chater, 2016)
To work toward formalizing these aspects of intentional interpretation, we introduce a neural network model that learns to generate sentences that are the inferential consequences of its inputs
We present experimentally produced plausibility ratings for a random collection of generated sentences, and from these ratings conclude that the model captures something important about the inferential relations amongst ordinary linguistic expressions
Summary
Linguistic comprehension is the result of cognitive processes that map between sounds and mental representations of meaning (e.g., Smolensky and Legendre, 2006; Pickering and Garrod, 2013; Christiansen and Chater, 2016). An obvious challenge for these accounts is to provide a good theoretical characterization of the relevant representations. Numerous proposals can be found in the literature, but there is no obvious consensus regarding their relative merits. The reason for this lack of consensus is that linguistic comprehension is itself a somewhat vague and ill-defined phenomenon. In the context of efforts to model linguistic comprehension, for instance, it is not entirely obvious what a model needs to be able to do in order to provide an account of how people understand complex linguistic expressions such as phrases and sentences
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.
