Related papers: Answering Complex Open-Domain Questions with Multi…

In multi-hop QA, answering complex questions entails iterative document retrieval for finding the missing entity of the question. The main steps of this process are sub-question detection, document retrieval for the sub-question, and…

Large Language Models (LLMs) have been increasingly employed for query expansion. However, their generative nature often undermines performance on complex multi-hop retrieval tasks by introducing irrelevant or noisy information. To address…

Question answering (QA) using textual sources for purposes such as reading comprehension (RC) has attracted much attention. This study focuses on the task of explainable multi-hop QA, which requires the system to return the answer with…

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…

Multi-hop Question Generation (QG) aims to generate answer-related questions by aggregating and reasoning over multiple scattered evidence from different paragraphs. It is a more challenging yet under-explored task compared to conventional…

Open-domain question answering requires retrieval systems able to cope with the diverse and varied nature of questions, providing accurate answers across a broad spectrum of query types and topics. To deal with such topic heterogeneity…

In today's fast-paced industry, professionals face the challenge of summarizing a large number of documents and extracting vital information from them on a daily basis. These metrics are frequently hidden away in tables and/or their nested…

Interpretable multi-hop reading comprehension (RC) over multiple documents is a challenging problem because it demands reasoning over multiple information sources and explaining the answer prediction by providing supporting evidences. In…

In table-text open-domain question answering, a retriever system retrieves relevant evidence from tables and text to answer questions. Previous studies in table-text open-domain question answering have two common challenges: firstly, their…

Multihop reasoning remains an elusive goal as existing multihop benchmarks are known to be largely solvable via shortcuts. Can we create a question answering (QA) dataset that, by construction, \emph{requires} proper multihop reasoning? To…

Recently, retrieval systems based on dense representations have led to important improvements in open-domain question answering, and related tasks. While very effective, this approach is also memory intensive, as the dense vectors for the…

Recent work has proposed multi-hop models and datasets for studying complex natural language reasoning. One notable task requiring multi-hop reasoning is fact checking, where a set of connected evidence pieces leads to the final verdict of…

Retrieval-augmented generation (RAG) methods encounter difficulties when addressing complex questions like multi-hop queries. While iterative retrieval methods improve performance by gathering additional information, current approaches…

Search engines based on keyword retrieval can no longer adapt to the way of information acquisition in the era of intelligent Internet of Things due to the return of keyword related Internet pages. How to quickly, accurately and effectively…

Recent studies on open-domain question answering have achieved prominent performance improvement using pre-trained language models such as BERT. State-of-the-art approaches typically follow the "retrieve and read" pipeline and employ…

Recent progress in deep learning has continuously improved the accuracy of dialogue response selection. In particular, sophisticated neural network architectures are leveraged to capture the rich interactions between dialogue context and…

Current commonsense reasoning research focuses on developing models that use commonsense knowledge to answer multiple-choice questions. However, systems designed to answer multiple-choice questions may not be useful in applications that do…

We introduce ART, a new corpus-level autoencoding approach for training dense retrieval models that does not require any labeled training data. Dense retrieval is a central challenge for open-domain tasks, such as Open QA, where…

In many real-world settings, machine learning models and interactive systems have access to both structured knowledge, e.g., knowledge graphs or tables, and unstructured content, e.g., natural language documents. Yet, most rely on either.…

Retrieval-Augmented Generation (RAG) has been used in question answering (QA) systems to improve performance when relevant information is in one (single-hop) or multiple (multi-hop) passages. However, many real life scenarios (e.g. dealing…