Microsoft AI Challenge India 2018: Learning to Rank Passages for Web Question Answering with Deep Attention Networks
This paper describes our system for The Microsoft AI Challenge India 2018: Ranking Passages for Web Question Answering. The system uses the biLSTM network with co-attention mechanism between query and passage representations. Additionally, we use self attention on embeddings to increase the lexical coverage by allowing the system to take union over different embeddings. We also incorporate hand-crafted features to improve the system performance. Our system achieved a Mean Reciprocal Rank (MRR) of 0.67 on eval-1 dataset.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep AttentionLearning-To-RankQuestion AnsweringMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Rider: Reader-Guided Passage Reranking for Open-Domain Question Answering
Current open-domain question answering systems often follow a Retriever-Reader architecture, where the retriever first retrieves relevant passages and the reader then reads the retrieved passages to form an answer. In th…
Natural QuestionsOpen-Domain Question AnsweringPassage RerankingQuestion Answering+3Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering
A popular recent approach to answering open-domain questions is to first search for question-related passages and then apply reading comprehension models to extract answers. Existing methods usually extract answers from …
Open-Domain Question AnsweringQuestion AnsweringReading ComprehensionReranking+2Question Decomposition for Retrieval-Augmented Generation
Grounding large language models (LLMs) in verifiable external sources is a well-established strategy for generating reliable answers. Retrieval-augmented generation (RAG) is one such approach, particularly effective for …
Question AnsweringAnswer GenerationJoint Passage Ranking for Diverse Multi-Answer Retrieval
We study multi-answer retrieval, an under-explored problem that requires retrieving passages to cover multiple distinct answers for a given question. This task requires joint modeling of retrieved passages, as models sho…
Answer GenerationDiversityPassage RankingPassage Retrieval+3GripRank: Bridging the Gap between Retrieval and Generation via the Generative Knowledge Improved Passage Ranking
Retrieval-enhanced text generation has shown remarkable progress on knowledge-intensive language tasks, such as open-domain question answering and knowledge-enhanced dialogue generation, by leveraging passages retrieved …
Answer GenerationDialogue GenerationKnowledge DistillationLanguage Modelling+6