THESIS
2020
ix, 42 pages : illustrations ; 30 cm
Abstract
Pragmatics studies what a language expression really conveys in our natural languages.
Unlike semantics, pragmatics studies how the transmission of meaning depends not only
on structural and linguistic knowledge of the speaker and listener but also on the context
of the utterance, any pre-existing knowledge about those involved, the inferred intent of
the speaker, and other factors. In this thesis, we use a dialogue description generation
task to study whether machines can learn and infer pragmatics information in dialogue.
We use the aligned image captioning datasets and visual dialogue datasets to learn how
to generate a dialogue description based on textual dialogue turns. We also remove some
dialogue turns to test the robustness of both learning and inference of a neural dia...[
Read more ]
Pragmatics studies what a language expression really conveys in our natural languages.
Unlike semantics, pragmatics studies how the transmission of meaning depends not only
on structural and linguistic knowledge of the speaker and listener but also on the context
of the utterance, any pre-existing knowledge about those involved, the inferred intent of
the speaker, and other factors. In this thesis, we use a dialogue description generation
task to study whether machines can learn and infer pragmatics information in dialogue.
We use the aligned image captioning datasets and visual dialogue datasets to learn how
to generate a dialogue description based on textual dialogue turns. We also remove some
dialogue turns to test the robustness of both learning and inference of a neural dialogue
description model. To evaluate results, we use both traditional natural language generation
related automatic metrics and our developed metric based on out-of-context concepts
to compare typical neural network based models and a dialogue interaction-based model.
We show that learning models can incorporate the context and some background or world
knowledge learned from the existing large training corpus into the dialogue description.
Post a Comment