Related papers: HopRetriever: Retrieve Hops over Wikipedia to Answ…

Lexical and semantic matches are commonly used as relevance measurements for information retrieval. Together they estimate the semantic equivalence between the query and the candidates. However, semantic equivalence is not the only…

We consider open-domain queston answering (QA) where answers are drawn from either a corpus, a knowledge base (KB), or a combination of both of these. We focus on a setting in which a corpus is supplemented with a large but incomplete KB,…

Despite recent advances in large language models (LLMs), most QA benchmarks are still confined to single-paragraph or single-document settings, failing to capture the complexity of real-world information-seeking tasks. Practical QA often…

This paper proposes to tackle open- domain question answering using Wikipedia as the unique knowledge source: the answer to any factoid question is a text span in a Wikipedia article. This task of machine reading at scale combines the…

Nowadays, editors tend to separate different subtopics of a long Wiki-pedia article into multiple sub-articles. This separation seeks to improve human readability. However, it also has a deleterious effect on many Wikipedia-based tasks that…

Reading comprehension QA tasks have seen a recent surge in popularity, yet most works have focused on fact-finding extractive QA. We instead focus on a more challenging multi-hop generative task (NarrativeQA), which requires the model to…

Asking questions from natural language text has attracted increasing attention recently, and several schemes have been proposed with promising results by asking the right question words and copy relevant words from the input to the…

Information retrieval (IR) or knowledge retrieval, is a critical component for many down-stream tasks such as open-domain question answering (QA). It is also very challenging, as it requires succinctness, completeness, and correctness. In…

Online encyclopedia such as Wikipedia has become one of the best sources of knowledge. Much effort has been devoted to expanding and enriching the structured data by automatic information extraction from unstructured text in Wikipedia.…

Cross-document event coreference resolution is a foundational task for NLP applications involving multi-text processing. However, existing corpora for this task are scarce and relatively small, while annotating only modest-size clusters of…

Recent work on open domain question answering (QA) assumes strong supervision of the supporting evidence and/or assumes a blackbox information retrieval (IR) system to retrieve evidence candidates. We argue that both are suboptimal, since…

Multi-hop reading comprehension requires not only the ability to reason over raw text but also the ability to combine multiple evidence. We propose a novel learning approach that helps language models better understand difficult multi-hop…

Multi-relation Question Answering is a challenging task, due to the requirement of elaborated analysis on questions and reasoning over multiple fact triples in knowledge base. In this paper, we present a novel model called Interpretable…

We propose a novel, path-based reasoning approach for the multi-hop reading comprehension task where a system needs to combine facts from multiple passages to answer a question. Although inspired by multi-hop reasoning over knowledge…

Multi-hop question answering is a challenging task with distinct industrial relevance, and Retrieval-Augmented Generation (RAG) methods based on large language models (LLMs) have become a popular approach to tackle this task. Owing to the…

We develop a unified system to answer directly from text open-domain questions that may require a varying number of retrieval steps. We employ a single multi-task transformer model to perform all the necessary subtasks -- retrieving…

We study the task of generating from Wikipedia articles question-answer pairs that cover content beyond a single sentence. We propose a neural network approach that incorporates coreference knowledge via a novel gating mechanism. Compared…

This paper presents a novel framework for reconstructing multi-hop explanations in science Question Answering (QA). While existing approaches for multi-hop reasoning build explanations considering each question in isolation, we propose a…

We propose a new model, DocHopper, that iteratively attends to different parts of long, hierarchically structured documents to answer complex questions. Similar to multi-hop question-answering (QA) systems, at each step, DocHopper uses a…

Explainable multi-hop question answering (QA) not only predicts answers but also identifies rationales, i. e. subsets of input sentences used to derive the answers. This problem has been extensively studied under the supervised setting,…