in Studies on Deep Learning, Natural Language Processing, Knowledge Graph
Commonsense knowledge graph can be useful source of explicit knowledge for generating texts that make sense. However, it is hard to use KG since it would hold huge amount of information than needed. Retrieving graphs which is relevent for the generation is the key.
in Studies on Deep Learning, Natural Language Processing, Knowledge Graph
Though knowledge graph can capture the essence of corpus, generating sentences based on the graph is difficult task. This paper tried to generate texts(paper abstracts) from KG in science(AI) domain.
in Studies on Deep Learning, Natural Language Processing, Knowledge Graph
Knowledge graph is graph representation of knowledge. Entities are represented as nodes and relations between entities are represented as edges. Commonsense knowledge graph stores commonsense knowledge in form of graphs. Two of common dataset for commonsense knowledge graph are ATOMIC and ConceptNet.
It has been long since my last post. I tried to post deep learning papers but I was so busy. I worked at Naver as an intern and wrote my master thesis for my graduation at the same time. Then, I refreshed for few months away from deep learning papers. Now I feel like I need to get back to business again.
There were some problems in previous VQA dataset. Strong language prior, non-compositional language and variablility in language were key obstacles for model to learn proper concepts and logics from VQA dataset. Synthetically generated CLEVR dataset solved these problems to some extent but lacked realisticity by remaining in relatively simple domain.
Discriminative question answering often overfit to datasets by catching any kinds of clue that leads to answer.
Visual question answering and visual question generation are complementary tasks. Learning one task may benefit the other.
Information retrieval from search engine becomes difficult when the query is incomplete or too complex. This paper suggests a query reformulation system that rewrite the query to maximize the probability of relevant documents returned.
Rejoice in what you learn and spray it!