Building dense retrievers requires a series of standard procedures, including training and validating neural models and creating indexes for efficient search. However, these procedures are often misaligned in that training objectives do not exactly reflect the retrieval scenario at inference time. In this paper, we explore how the gap between training and inference in dense retrieval can be reduced, focusing on dense phrase retrieval (Lee et al., 2021) where billions of representations are indexed at inference. Since validating every dense retriever with a large-scale index is practically infeasible, we propose an efficient way of validating dense retrievers using a small subset of the entire corpus. This allows us to validate various training strategies including unifying contrastive loss terms and using hard negatives for phrase retrieval, which largely reduces the training-inference discrepancy. As a result, we improve top-1 phrase retrieval accuracy by 2 3 points and top-20 passage retrieval accuracy by 2 4 points for open-domain question answering. Our work urges modeling dense retrievers with careful consideration of training and inference via efficient validation while advancing phrase retrieval as a general solution for dense retrieval.
Many NLP tasks require processing long contexts beyond the length limit of pretrained models. In order to scale these models to longer text sequences, many efficient long-range attention variants have been proposed. Despite the abundance of research along this direction, it is still difficult to gauge the relative effectiveness of these models in practical use cases, e.g., if we apply these models following the pretrain-and-finetune paradigm. In this work, we aim to conduct a thorough analysis of these emerging models with large-scale and controlled experiments. For each attention variant, we pretrain large-size models using the same long-doc corpus and then finetune these models for real-world long-context tasks. Our findings reveal pitfalls of an existing widely-used long-range benchmark and show none of the tested efficient attentions can beat a simple local window attention under standard pretraining paradigms. Further analysis on local attention variants suggests that even the commonly used attention-window overlap is not necessary to achieve good downstream results — using disjoint local attentions, we are able to build a simpler and more efficient long-doc QA model that matches the performance of Longformer with half of its pretraining compute.
We propose DrBoost, a dense retrieval ensemble inspired by boosting. DrBoost is trained in stages: each component model is learned sequentially and specialized by focusing only on retrieval mistakes made by the current ensemble. The final representation is the concatenation of the output vectors of all the component models, making it a drop-in replacement for standard dense retrievers at test time. DrBoost enjoys several advantages compared to standard dense retrieval models. It produces representations which are 4x more compact, while delivering comparable retrieval results. It also performs surprisingly well under approximate search with coarse quantization, reducing latency and bandwidth needs by another 4x. In practice, this can make the difference between serving indices from disk versus from memory, paving the way for much cheaper deployments.
NLP benchmarks have largely focused on short texts, such as sentences and paragraphs, even though long texts comprise a considerable amount of natural language in the wild. We introduce SCROLLS, a suite of tasks that require reasoning over long texts. We examine existing long-text datasets, and handpick ones where the text is naturally long, while prioritizing tasks that involve synthesizing information across the input. SCROLLS contains summarization, question answering, and natural language inference tasks, covering multiple domains, including literature, science, business, and entertainment. Initial baselines, including Longformer Encoder-Decoder, indicate that there is ample room for improvement on SCROLLS. We make all datasets available in a unified text-to-text format and host a live leaderboard to facilitate research on model architecture and pretraining methods.
Obtaining training data for multi-hop question answering (QA) is time-consuming and resource-intensive. We explore the possibility to train a well-performed multi-hop QA model without referencing any human-labeled multi-hop question-answer pairs, i.e., unsupervised multi-hop QA. We propose MQA-QG, an unsupervised framework that can generate human-like multi-hop training data from both homogeneous and heterogeneous data sources. MQA-QG generates questions by first selecting/generating relevant information from each data source and then integrating the multiple information to form a multi-hop question. Using only generated training data, we can train a competent multi-hop QA which achieves 61% and 83% of the supervised learning performance for the HybridQA and the HotpotQA dataset, respectively. We also show that pretraining the QA system with the generated data would greatly reduce the demand for human-annotated training data. Our codes are publicly available at https://github.com/teacherpeterpan/Unsupervised-Multi-hop-QA.
Neural models for automated fact verification have achieved promising results thanks to the availability of large, human-annotated datasets. However, for each new domain that requires fact verification, creating a dataset by manually writing claims and linking them to their supporting evidence is expensive. We develop QACG, a framework for training a robust fact verification model by using automatically generated claims that can be supported, refuted, or unverifiable from evidence from Wikipedia. QACG generates question-answer pairs from the evidence and then converts them into different types of claims. Experiments on the FEVER dataset show that our QACG framework significantly reduces the demand for human-annotated training data. In a zero-shot scenario, QACG improves a RoBERTa model’s F1 from 50% to 77%, equivalent in performance to 2K+ manually-curated examples. Our QACG code is publicly available.
Commonly used information retrieval methods such as TF-IDF in open-domain question answering (QA) systems are insufficient to capture deep semantic matching that goes beyond lexical overlaps. Some recent studies consider the retrieval process as maximum inner product search (MIPS) using dense question and paragraph representations, achieving promising results on several information-seeking QA datasets. However, the pretraining of the dense vector representations is highly resource-demanding, e.g., requires a very large batch size and lots of training steps. In this work, we propose a sample-efficient method to pretrain the paragraph encoder. First, instead of using heuristically created pseudo question-paragraph pairs for pretraining, we use an existing pretrained sequence-to-sequence model to build a strong question generator that creates high-quality pretraining data. Second, we propose a simple progressive pretraining algorithm to ensure the existence of effective negative samples in each batch. Across three open-domain QA datasets, our method consistently outperforms a strong dense retrieval baseline that uses 6 times more computation for training. On two of the datasets, our method achieves more than 4-point absolute improvement in terms of answer exact match.
Since late 2019, COVID-19 has quickly emerged as the newest biomedical domain, resulting in a surge of new information. As with other emergent domains, the discussion surrounding the topic has been rapidly changing, leading to the spread of misinformation. This has created the need for a public space for users to ask questions and receive credible, scientific answers. To fulfill this need, we turn to the task of open-domain question-answering, which we can use to efficiently find answers to free-text questions from a large set of documents. In this work, we present such a system for the emergent domain of COVID-19. Despite the small data size available, we are able to successfully train the system to retrieve answers from a large-scale corpus of published COVID-19 scientific papers. Furthermore, we incorporate effective re-ranking and question-answering techniques, such as document diversity and multiple answer spans. Our open-domain question-answering system can further act as a model for the quick development of similar systems that can be adapted and modified for other developing emergent domains.
Existing question answering datasets focus on dealing with homogeneous information, based either only on text or KB/Table information alone. However, as human knowledge is distributed over heterogeneous forms, using homogeneous information alone might lead to severe coverage problems. To fill in the gap, we present HybridQA, a new large-scale question-answering dataset that requires reasoning on heterogeneous information. Each question is aligned with a Wikipedia table and multiple free-form corpora linked with the entities in the table. The questions are designed to aggregate both tabular information and text information, i.e., lack of either form would render the question unanswerable. We test with three different models: 1) a table-only model. 2) text-only model. 3) a hybrid model that combines heterogeneous information to find the answer. The experimental results show that the EM scores obtained by two baselines are below 20%, while the hybrid model can achieve an EM over 40%. This gap suggests the necessity to aggregate heterogeneous information in HybridQA. However, the hybrid model’s score is still far behind human performance. Hence, HybridQA can serve as a challenging benchmark to study question answering with heterogeneous information.
Many tasks in natural language processing can be viewed as multi-label classification problems. However, most of the existing models are trained with the standard cross-entropy loss function and use a fixed prediction policy (e.g., a threshold of 0.5) for all the labels, which completely ignores the complexity and dependencies among different labels. In this paper, we propose a meta-learning method to capture these complex label dependencies. More specifically, our method utilizes a meta-learner to jointly learn the training policies and prediction policies for different labels. The training policies are then used to train the classifier with the cross-entropy loss function, and the prediction policies are further implemented for prediction. Experimental results on fine-grained entity typing and text classification demonstrate that our proposed method can obtain more accurate multi-label classification results.
A key challenge of multi-hop question answering (QA) in the open-domain setting is to accurately retrieve the supporting passages from a large corpus. Existing work on open-domain QA typically relies on off-the-shelf information retrieval (IR) techniques to retrieve answer passages, i.e., the passages containing the groundtruth answers. However, IR-based approaches are insufficient for multi-hop questions, as the topic of the second or further hops is not explicitly covered by the question. To resolve this issue, we introduce a new subproblem of open-domain multi-hop QA, which aims to recognize the bridge (i.e., the anchor that links to the answer passage) from the context of a set of start passages with a reading comprehension model. This model, the bridge reasoner, is trained with a weakly supervised signal and produces the candidate answer passages for the passage reader to extract the answer. On the full-wiki HotpotQA benchmark, we significantly improve the baseline method by 14 point F1. Without using any memory inefficient contextual embeddings, our result is also competitive with the state-of-the-art that applies BERT in multiple modules.
General Question Answering (QA) systems over texts require the multi-hop reasoning capability, i.e. the ability to reason with information collected from multiple passages to derive the answer. In this paper we conduct a systematic analysis to assess such an ability of various existing models proposed for multi-hop QA tasks. Specifically, our analysis investigates that whether providing the full reasoning chain of multiple passages, instead of just one final passage where the answer appears, could improve the performance of the existing QA models. Surprisingly, when using the additional evidence passages, the improvements of all the existing multi-hop reading approaches are rather limited, with the highest error reduction of 5.8% on F1 (corresponding to 1.3% improvement) from the BERT model. To better understand whether the reasoning chains indeed could help find the correct answers, we further develop a co-matching-based method that leads to 13.1% error reduction with passage chains when applied to two of our base readers (including BERT). Our results demonstrate the existence of the potential improvement using explicit multi-hop reasoning and the necessity to develop models with better reasoning abilities.
Existing models for extractive summarization are usually trained from scratch with a cross-entropy loss, which does not explicitly capture the global context at the document level. In this paper, we aim to improve this task by introducing three auxiliary pre-training tasks that learn to capture the document-level context in a self-supervised fashion. Experiments on the widely-used CNN/DM dataset validate the effectiveness of the proposed auxiliary tasks. Furthermore, we show that after pre-training, a clean model with simple building blocks is able to outperform previous state-of-the-art that are carefully designed.
We propose a new end-to-end question answering model, which learns to aggregate answer evidence from an incomplete knowledge base (KB) and a set of retrieved text snippets.Under the assumptions that structured data is easier to query and the acquired knowledge can help the understanding of unstructured text, our model first accumulates knowledge ofKB entities from a question-related KB sub-graph; then reformulates the question in the latent space and reads the text with the accumulated entity knowledge at hand. The evidence from KB and text are finally aggregated to predict answers. On the widely-used KBQA benchmark WebQSP, our model achieves consistent improvements across settings with different extents of KB incompleteness.
With social media becoming increasingly popular on which lots of news and real-time events are reported, developing automated question answering systems is critical to the effective-ness of many applications that rely on real-time knowledge. While previous datasets have concentrated on question answering (QA) for formal text like news and Wikipedia, we present the first large-scale dataset for QA over social media data. To ensure that the tweets we collected are useful, we only gather tweets used by journalists to write news articles. We then ask human annotators to write questions and answers upon these tweets. Unlike otherQA datasets like SQuAD in which the answers are extractive, we allow the answers to be abstractive. We show that two recently proposed neural models that perform well on formal texts are limited in their performance when applied to our dataset. In addition, even the fine-tuned BERT model is still lagging behind human performance with a large margin. Our results thus point to the need of improved QA systems targeting social media text.
Existing entity typing systems usually exploit the type hierarchy provided by knowledge base (KB) schema to model label correlations and thus improve the overall performance. Such techniques, however, are not directly applicable to more open and practical scenarios where the type set is not restricted by KB schema and includes a vast number of free-form types. To model the underlying label correlations without access to manually annotated label structures, we introduce a novel label-relational inductive bias, represented by a graph propagation layer that effectively encodes both global label co-occurrence statistics and word-level similarities. On a large dataset with over 10,000 free-form types, the graph-enhanced model equipped with an attention-based matching module is able to achieve a much higher recall score while maintaining a high-level precision. Specifically, it achieves a 15.3% relative F1 improvement and also less inconsistency in the outputs. We further show that a simple modification of our proposed graph layer can also improve the performance on a conventional and widely-tested dataset that only includes KB-schema types.
Conventional approaches to relation extraction usually require a fixed set of pre-defined relations. Such requirement is hard to meet in many real applications, especially when new data and relations are emerging incessantly and it is computationally expensive to store all data and re-train the whole model every time new data and relations come in. We formulate such challenging problem as lifelong relation extraction and investigate memory-efficient incremental learning methods without catastrophically forgetting knowledge learned from previous tasks. We first investigate a modified version of the stochastic gradient methods with a replay memory, which surprisingly outperforms recent state-of-the-art lifelong learning methods. We further propose to improve this approach to alleviate the forgetting problem by anchoring the sentence embedding space. Specifically, we utilize an explicit alignment model to mitigate the sentence embedding distortion of learned model when training on new data and new relations. Experiment results on multiple benchmarks show that our proposed method significantly outperforms the state-of-the-art lifelong learning approaches.
Knowledge graphs (KG) are the key components of various natural language processing applications. To further expand KGs’ coverage, previous studies on knowledge graph completion usually require a large number of positive examples for each relation. However, we observe long-tail relations are actually more common in KGs and those newly added relations often do not have many known triples for training. In this work, we aim at predicting new facts under a challenging setting where only one training instance is available. We propose a one-shot relational learning framework, which utilizes the knowledge distilled by embedding models and learns a matching metric by considering both the learned embeddings and one-hop graph structures. Empirically, our model yields considerable performance improvements over existing embedding models, and also eliminates the need of re-training the embedding models when dealing with newly added relations.
Inferring missing links in knowledge graphs (KG) has attracted a lot of attention from the research community. In this paper, we tackle a practical query answering task involving predicting the relation of a given entity pair. We frame this prediction problem as an inference problem in a probabilistic graphical model and aim at resolving it from a variational inference perspective. In order to model the relation between the query entity pair, we assume that there exists an underlying latent variable (paths connecting two nodes) in the KG, which carries the equivalent semantics of their relations. However, due to the intractability of connections in large KGs, we propose to use variation inference to maximize the evidence lower bound. More specifically, our framework (Diva) is composed of three modules, i.e. a posterior approximator, a prior (path finder), and a likelihood (path reasoner). By using variational inference, we are able to incorporate them closely into a unified architecture and jointly optimize them to perform KG reasoning. With active interactions among these sub-modules, Diva is better at handling noise and coping with more complex reasoning scenarios. In order to evaluate our method, we conduct the experiment of the link prediction task on multiple datasets and achieve state-of-the-art performances on both datasets.
We study the problem of learning to reason in large scale knowledge graphs (KGs). More specifically, we describe a novel reinforcement learning framework for learning multi-hop relational paths: we use a policy-based agent with continuous states based on knowledge graph embeddings, which reasons in a KG vector-space by sampling the most promising relation to extend its path. In contrast to prior work, our approach includes a reward function that takes the accuracy, diversity, and efficiency into consideration. Experimentally, we show that our proposed method outperforms a path-ranking based algorithm and knowledge graph embedding methods on Freebase and Never-Ending Language Learning datasets.