Interpretation of Natural Language Rules in Conversational Machine Reading
| Autor: | Guillaume Bouchard, Marzieh Saeidi, Patrick S. H. Lewis, Michael Sheldon, Sebastian Riedel, Tim Rocktäschel, Max Bartolo, Sameer Singh |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Computer Science - Computation and Language Computer science media_common.quotation_subject Interpretation (philosophy) Machine Learning (stat.ML) 02 engineering and technology 010501 environmental sciences 01 natural sciences Data science Task (project management) Machine Learning (cs.LG) Statistics - Machine Learning Reading (process) 0202 electrical engineering electronic engineering information engineering Question answering Literal (computer programming) 020201 artificial intelligence & image processing Computation and Language (cs.CL) Natural language 0105 earth and related environmental sciences media_common |
| Zdroj: | EMNLP |
| DOI: | 10.48550/arxiv.1809.01494 |
| Popis: | Most work in machine reading focuses on question answering problems where the answer is directly expressed in the text to read. However, many real-world question answering problems require the reading of text not because it contains the literal answer, but because it contains a recipe to derive an answer together with the reader's background knowledge. One example is the task of interpreting regulations to answer "Can I...?" or "Do I have to...?" questions such as "I am working in Canada. Do I have to carry on paying UK National Insurance?" after reading a UK government website about this topic. This task requires both the interpretation of rules and the application of background knowledge. It is further complicated due to the fact that, in practice, most questions are underspecified, and a human assistant will regularly have to ask clarification questions such as "How long have you been working abroad?" when the answer cannot be directly derived from the question and text. In this paper, we formalise this task and develop a crowd-sourcing strategy to collect 32k task instances based on real-world rules and crowd-generated questions and scenarios. We analyse the challenges of this task and assess its difficulty by evaluating the performance of rule-based and machine-learning baselines. We observe promising results when no background knowledge is necessary, and substantial room for improvement whenever background knowledge is needed. Comment: EMNLP 2018 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|