- Open IE for handling open relations
- Relation discovery for handling open relations


Explorations in handling open relations for RE

Most relation extraction (RE) systems work within pre-specified relation sets designed by human experts. Since the real world undergoes an open-ended growth of new relations, human experts cannot manually define all emerging relation types. Therefore, RE systems must be capable of operating in open scenarios without relying on predefined relation schemas.

Columbia University

Google

- Utilizing more data
- Performing more efficient learning
- Handling more complicated context
- Orienting more open domains

Further approaches that could lead to better RE that require further efforts

Supervised NRE models have a lack of large-scale high-quality training data because manually labeling data is time-consuming and human intensive. To help with this, distant supervision (DS) assumption has been used to automatically label data by aligning existing knowledge graphs with plain text. For any entity pair in knowledge graphs, sentences mentioning both entities will be labeled with their corresponding relations in knowledge graphs. Large-scale training examples can be easily constructed using this training scheme. Although DS provides a feasible approach to use more data, it is inevitable for its automatic labeling mechanism to be accompanied with the wrong labeling problem, since not all sentences mentioning two given entities express their relations in knowledge graphs exactly. 

Utilizing more data for RE models with distant supervision

Real-world relation distributions are long-tail. This means only the common relations obtain sufficient training instances and most relations have very limited relational facts and corresponding sentences. Few-shot learning focuses on grasping tasks with only a few training examples and is a good fit for this need. The general idea of few-shot models is to train good representations of instances or learn ways of fast adaptation from existing large-scale data, and then transfer to new tasks.

Let T be some task, E be past experience related to this classes of task T, and P be performance measure of T. Few-Shot learning is a type of machine learning problem which is specified by E, T, and P, but only has limited E either quantitatively or qualitatively. E typically includes supervised information and prior knowledge.

Performing more efficient learning with few-shot learning for RE

In Relation Extraction (RE), a single document often mentions multiple entities exhibiting complex cross-sentence relationships. Most existing RE methods focus on intra-sentence extraction and are inadequate for collectively identifying relational facts expressed across long paragraphs. Extracting these facts requires models capable of handling complicated contexts, such as full documents, rather than relying solely on isolated single sentences.

Learn Before

Related

Learn After