Long-range transformer models have achieved encouraging results on long-context question answering (QA) tasks. Such tasks often require reasoning over a long document, and they benefit from identifying a set of evidence spans (e.g., sentences) that provide supporting evidence for addressing the question. In this work, we propose a novel method for equipping long-range transformers with an additional sequence-level objective for better identification of supporting evidence spans. We achieve this by proposing an additional contrastive supervision signal in finetuning, where the model is encouraged to explicitly discriminate supporting evidence sentences from negative ones by maximizing the question-evidence similarity. The proposed additional loss exhibits consistent improvements on three different strong long-context transformer models, across two challenging question answering benchmarks - HotpotQA and QAsper.
We introduce the LongChecker system for scientific claim verification. Given a scientific claim and an evidence-containing research abstract, LongChecker predicts a veracity label and identifies supporting rationales in a multitask fashion based on a shared encoding of the claim and abstract. We perform experiments on the SciFact dataset, and find that LongChecker achieves state-of-the-art performance. We conduct analysis to understand the source of this improvement, and find that identifying the relationship between a claim and a rationale reporting a scientific finding often requires understanding the context in which the rationale appears. By making labeling decisions based on all available context, LongChecker achieves better performance on cases requiring this type of understanding. In addition, we show that LongChecker is able to leverage weakly-supervised in-domain data to facilitate few-shot domain adaptation for scientific claim verification.
We present Aspire, a new scientific document similarity model based on matching fine-grained aspects. Our model is trained using co-citation contexts that describe related paper aspects as a novel form of textual supervision. We use multi-vector document representations, recently explored in settings with short query texts but under-explored in the challenging document-document setting. We present a fast method that involves matching only single sentence pairs, and a method that makes sparse multiple matches with optimal transport. Our model improves performance on document similarity tasks across four datasets. Moreover, our fast single-match method achieves competitive results, opening up the possibility of applying fine-grained document similarity models to large-scale scientific corpora.
Recently proposed pre-trained generation models achieve strong performance on single-document summarization benchmarks. However, most of them are pre-trained with general-purpose objectives and mainly aim to process single document inputs. In this paper, we propose PRIMER, a pre-trained model for multi-document representation with focus on summarization that reduces the need for dataset-specific architectures and large amounts of fine-tuning labeled data. Specifically, we adopt the Longformer architecture with proper input transformation and global attention to fit for multi-document inputs, and we use Gap Sentence Generation objective with a new strategy to select salient sentences for the whole cluster, called Entity Pyramid, to teach the model to select and aggregate information across a cluster of related documents. With extensive experiments on 6 multi-document summarization datasets from 3 different domains on the zero-shot, few-shot, and full-supervised settings, our model, PRIMER, outperforms current state-of-the-art models on most of these settings with large margins. Code and pre-trained models are released at https://github.com/allenai/PRIMER
Citation context analysis (CCA) is an important task in natural language processing that studies how and why scholars discuss each others' work. Despite decades of study, traditional frameworks for CCA have largely relied on overly-simplistic assumptions of how authors cite, which ignore several important phenomena. For instance, scholarly papers often contain rich discussions of cited work that span multiple sentences and express multiple intents concurrently. Yet, CCA is typically approached as a single-sentence, single-label classification task, and thus existing datasets fail to capture this interesting discourse. In our work, we address this research gap by proposing a novel framework for CCA as a document-level context extraction and labeling task. We release MultiCite, a new dataset of 12,653 citation contexts from over 1,200 computational linguistics papers. Not only is it the largest collection of expert-annotated citation contexts to-date, MultiCite contains multi-sentence, multi-label citation contexts within full paper texts. Finally, we demonstrate how our dataset, while still usable for training classic CCA models, also supports the development of new types of models for CCA beyond fixed-width text classification. We release our code and dataset at https://github.com/allenai/multicite.
Few-shot NLP research is highly active, yet conducted in disjoint research threads with evaluation suites that lack challenging-yet-realistic testing setups and fail to employ careful experimental design. Consequently, the community does not know which techniques perform best or even if they outperform simple baselines. We formulate desiderata for an ideal few-shot NLP benchmark and present FLEX, the first benchmark, public leaderboard, and framework that provides unified, comprehensive measurement for few-shot NLP techniques. FLEX incorporates and introduces new best practices for few-shot evaluation, including measurement of four transfer settings, textual labels for zero-shot evaluation, and a principled approach to benchmark design that optimizes statistical accuracy while keeping evaluation costs accessible to researchers without large compute resources. In addition, we present UniFew, a simple yet strong prompt-based model for few-shot learning which unifies the pretraining and finetuning prompt formats, eschewing complex machinery of recent prompt-based approaches in adapting downstream task formats to language model pretraining objectives. We demonstrate that despite simplicity UniFew achieves results competitive with both popular meta-learning and prompt-based approaches.
Readers of academic research papers often read with the goal of answering specific questions. Question Answering systems that can answer those questions can make consumption of the content much more efficient. However, building such tools requires data that reflect the difficulty of the task arising from complex reasoning about claims made in multiple parts of a paper. In contrast, existing information-seeking question answering datasets usually contain questions about generic factoid-type information. We therefore present QASPER, a dataset of 5,049 questions over 1,585 Natural Language Processing papers. Each question is written by an NLP practitioner who read only the title and abstract of the corresponding paper, and the question seeks information present in the full text. The questions are then answered by a separate set of NLP practitioners who also provide supporting evidence to answers. We find that existing models that do well on other QA tasks do not perform well on answering these questions, underperforming humans by at least 27 F1 points when answering them from entire papers, motivating further research in document-grounded, information-seeking QA, which our dataset is designed to facilitate.
Managing the data for Information Retrieval (IR) experiments can be challenging. Dataset documentation is scattered across the Internet and once one obtains a copy of the data, there are numerous different data formats to work with. Even basic formats can have subtle dataset-specific nuances that need to be considered for proper use. To help mitigate these challenges, we introduce a new robust and lightweight tool (ir_datases) for acquiring, managing, and performing typical operations over datasets used in IR. We primarily focus on textual datasets used for ad-hoc search. This tool provides both a python and command line interface to numerous IR datasets and benchmarks. To our knowledge, this is the most extensive tool of its kind. Integrations with popular IR indexing and experimentation toolkits demonstrate the tool's utility. We also provide documentation of these datasets through the ir_datasets catalog: https://ir-datasets.com/. The catalog acts as a hub for information on datasets used in IR, providing core information about what data each benchmark provides as well as links to more detailed information. We welcome community contributions and intend to continue to maintain and grow this tool.
We introduce a new pretraining approach for language models that are geared to support multi-document NLP tasks. Our cross-document language model (CD-LM) improves masked language modeling for these tasks with two key ideas. First, we pretrain with multiple related documents in a single input, via cross-document masking, which encourages the model to learn cross-document and long-range relationships. Second, extending the recent Longformer model, we pretrain with long contexts of several thousand tokens and introduce a new attention pattern that uses sequence-level global attention to predict masked tokens, while retaining the familiar local attention elsewhere. We show that our CD-LM sets new state-of-the-art results for several multi-text tasks, including cross-document event and entity coreference resolution, paper citation recommendation, and documents plagiarism detection, while using a significantly reduced number of training parameters relative to prior works.