Answering questions by learning to rank - Learning to rank by answering questions
Answering multiple-choice questions in a setting in which no supporting documents are explicitly provided continues to stand as a core problem in natural language processing. The contribution of this article is two-fold. First, it describes a method which can be used to semantically rank documents extracted from Wikipedia or similar natural language corpora. Second, we propose a model employing the semantic ranking that holds the first place in two of the most popular leaderboards for answering multiple-choice questions: ARC Easy and Challenge. To achieve this, we introduce a self-attention based neural network that latently learns to rank documents by their importance related to a given question, whilst optimizing the objective of predicting the correct answer. These documents are considered relevant contexts for the underlying question. We have published the ranked documents so that they can be used off-the-shelf to improve downstream decision models.
Code (0)
등록된 구현이 없습니다.
Tasks
ARCLearning-To-RankMultiple-choiceSimilar Papers 제목 키워드 기반
Answering questions by learning to rank -- Learning to rank by answering questions
Answering multiple-choice questions in a setting in which no supporting documents are explicitly provided continues to stand as a core problem in natural language processing. The contribution of this article is two-fold.…
ARCLearning-To-RankMultiple-choiceAnswer Extraction for Why Arabic Questions Answering Systems: EWAQ
With the increasing amount of web information, questions answering systems becomes very important to allow users to access to direct answers for their requests. This paper presents an Arabic Questions Answering Systems b…
Natural Language InferenceAnswering Any-hop Open-domain Questions with Iterative Document Reranking
Existing approaches for open-domain question answering (QA) are typically designed for questions that require either single-hop or multi-hop reasoning, which make strong assumptions of the complexity of questions to be a…
Multi-hop Question AnsweringNatural QuestionsOpen-Domain Question AnsweringQuestion Answering+2Retrieve and Re-rank: A Simple and Effective IR Approach to Simple Question Answering over Knowledge Graphs
SimpleQuestions is a commonly used benchmark for single-factoid question answering (QA) over Knowledge Graphs (KG). Existing QA systems rely on various components to solve different sub-tasks of the problem (such as enti…
Entity LinkingInformation RetrievalKnowledge GraphsLearning-To-Rank+5Simple Question Answering with Subgraph Ranking and Joint-Scoring
Knowledge graph based simple question answering (KBSQA) is a major area of research within question answering. Although only dealing with simple questions, i.e., questions that can be answered through a single knowledge …
Fact SelectionQuestion AnsweringRelation