Project description
Computers learn about human’s natural language
Computers are pretty smart but they have their limitations, particularly when it comes to natural language processing (NLP). Language processing involves high-level and abstract rules to convey information, making it difficult for computers to decipher and understand human languages. The EU-funded iEXTRACT project will review the rule-based information extraction methods in view of advances in NLP and machine learning. Information extraction is a collaborative human-computer effort, in which the user provides domain-specific knowledge, and the system solves various domain-independent linguistic complexities, ultimately allowing the user to query unstructured texts. The main goal is to assist domain experts such as lawyers and scientists by empowering them to process large volumes of data and advance their profession.
Objective
Staggering amounts of information are stored in natural language documents, rendering them unavailable to data-science techniques. Information Extraction (IE), a subfield of Natural Language Processing (NLP), aims to automate the extraction of structured information from text, yielding datasets that can be queried, analyzed and combined to provide new insights and drive research forward.
Despite tremendous progress in NLP, IE systems remain mostly inaccessible to non-NLP-experts who can greatly benefit from them. This stems from the current methods for creating IE systems: the dominant machine-learning (ML) approach requires technical expertise and large amounts of annotated data, and does not provide the user control over the extraction process. The previously dominant rule-based approach unrealistically requires the user to anticipate and deal with the nuances of natural language.
I aim to remedy this situation by revisiting rule-based IE in light of advances in NLP and ML. The key idea is to cast IE as a collaborative human-computer effort, in which the user provides domain-specific knowledge, and the system is in charge of solving various domain-independent linguistic complexities, ultimately allowing the user to query
unstructured texts via easily structured forms.
More specifically, I aim develop:
(a) a novel structured representation that abstracts much of the complexity of natural language;
(b) algorithms that derive these representations from texts;
(c) an accessible rule language to query this representation;
(d) AI components that infer the user extraction intents, and based on them promote relevant examples and highlight extraction cases that require special attention.
The ultimate goal of this project is to democratize NLP and bring advanced IE capabilities directly to the hands of
domain-experts: doctors, lawyers, researchers and scientists, empowering them to process large volumes of data and
advance their profession.
Fields of science
Programme(s)
Topic(s)
Funding Scheme
ERC-STG - Starting GrantHost institution
52900 Ramat Gan
Israel