MS MARCO

AbstractThis paper presents how to generate questions from given passages using neural networks, where large scale QA pairs are automatically crawled and processed from Community-QA website, and used as training …...

AbstractIn this paper, we propose a new linguistically-based approach to answering non-factoid open-domain questions from unstructured data. First, we elaborate on an architecture for textual encoding based on which we …...

AbstractBuilding curious machines that can answer as well as ask questions is an important challenge for AI. The two tasks of question answering and question generation are usually tackled separately …...

AbstractMany recent approaches towards neural information retrieval mitigate their computational costs by using a multi-stage ranking pipeline. In the first stage, a number of potentially relevant candidates are retrieved using …...

To train a question answering model based on machine reading comprehension (MRC), sig- nificant effort is required to prepare annotated training data composed of questions and their answers from contexts. …...

AbstractIn the context of neural passage retrieval, we study three promising techniques: synthetic data generation, negative sampling, and fusion. We systematically investigate how these techniques contribute to the performance of …...

Recently, dense passage retrieval has become a mainstream approach to finding relevant infor- mation in various natural language processing tasks. A number of studies have been devoted to improving the …...

AbstractIn open-domain question answering, dense passage retrieval has become a new paradigm to retrieve relevant passages for finding answers. Typically, the dual-encoder architecture is adopted to learn dense representations of …...

AbstractIn various natural language processing tasks, passage retrieval and passage re-ranking are two key procedures in finding and ranking relevant information. Since both the two procedures contribute to the final …...

AbstractThe semantic matching capabilities of neural information retrieval can ameliorate synonymy and polysemy problems of symbolic approaches. However, neural models’ dense representations are more suitable for re-ranking, due to their …...

AbstractNeural retrieval models have superseded classic bag-of-words methods such as BM25 as the retrieval framework of choice. However, neural systems lack the interpretability of bag-of-words models; it is not trivial …...

AbstractDeep prompt tuning (DPT) has gained great success in most natural language processing (NLP) tasks. However, it is not well-investigated in dense retrieval where fine-tuning (FT) still dominates. When deploying …...

AbstractDual encoders have been used for question-answering (QA) and information retrieval (IR) tasks with good results. There are two major types of dual encoders, Siamese Dual Encoders (SDE), with parameters …...

AbstractLong-form question answering (LFQA) aims to generate a paragraph-length answer for a given question. While current work on LFQA using large pre-trained model for generation are effective at producing fluent …...

AbstractDespite pre-training’s progress in many important NLP tasks, it remains to explore effective pre-training strategies for dense retrieval. In this paper, we propose RetroMAE, a new retrieval oriented pre-training paradigm …...

AbstractRecent research demonstrates the effectiveness of using fine-tuned language models (LM) for dense retrieval. However, dense retrievers are hard to train, typically requiring heavily engineered fine-tuning pipelines to realize their …...

AbstractMulti-vector retrieval methods combine the merits of sparse (e.g. BM25) and dense (e.g. DPR) retrievers and have achieved state-of-the-art performance on various retrieval tasks. These methods, however, are orders of …...

AbstractDocument ranking aims at sorting a collection of documents with their relevance to a query. Contemporary methods explore more efficient transformers or divide long documents into passages to handle the …...

AbstractTo better support information retrieval tasks such as web search and open-domain question answering, growing effort is made to develop retrieval-oriented language models, e.g., RetroMAE and many others. Most of …...

AbstractRecently, model-based retrieval has emerged as a new paradigm in text retrieval that discards the index in the traditional retrieval model and instead memorizes the candidate corpora using model parameters. …...