On-the-fly Definition Augmentation of LLMs for Biomedical NER

Despite their general capabilities, LLMs still struggle on biomedical NER tasks, which are difficult due to the presence of specialized terminology and lack of training data. In this work we set out to improve LLM performance on biomedical NER in limited data settings via a new knowledge augmentation approach which incorporates definitions of relevant concepts on-the-fly. During this process, to provide a test bed for knowledge augmentation, we perform a comprehensive exploration of prompting strategies. Our experiments show that definition augmentation is useful for both open source and closed LLMs. For example, it leads to a relative improvement of 15\% (on average) in GPT-4 performance (F1) across all (six) of our test datasets. We conduct extensive ablations and analyses to demonstrate that our performance improvements stem from adding relevant definitional knowledge. We find that careful prompting strategies also improve LLM performance, allowing them to outperform fine-tuned language models in few-shot settings. To facilitate future research in this direction, we release our code at https://github.com/allenai/beacon.

RCT Rejection Sampling for Causal Estimation Evaluation

Confounding is a significant obstacle to unbiased estimation of causal effects from observational data. For settings with high-dimensional covariates -- such as text data, genomics, or the behavioral social sciences -- researchers have proposed methods to adjust for confounding by adapting machine learning methods to the goal of causal estimation. However, empirical evaluation of these adjustment methods has been challenging and limited. In this work, we build on a promising empirical evaluation strategy that simplifies evaluation design and uses real data: subsampling randomized controlled trials (RCTs) to create confounded observational datasets while using the average causal effects from the RCTs as ground-truth. We contribute a new sampling algorithm, which we call RCT rejection sampling, and provide theoretical guarantees that causal identification holds in the observational data to allow for valid comparisons to the ground-truth RCT. Using synthetic data, we show our algorithm indeed results in low bias when oracle estimators are evaluated on the confounded samples, which is not always the case for a previously proposed algorithm. In addition to this identification result, we highlight several finite data considerations for evaluation designers who plan to use RCT rejection sampling on their own datasets. As a proof of concept, we implement an example evaluation pipeline and walk through these finite data considerations with a novel, real-world RCT -- which we release publicly -- consisting of approximately 70k observations and text data as high-dimensional covariates. Together, these contributions build towards a broader agenda of improved empirical evaluation for causal estimation.

S2abEL: A Dataset for Entity Linking from Scientific Tables

Entity linking (EL) is the task of linking a textual mention to its corresponding entry in a knowledge base, and is critical for many knowledge-intensive NLP applications. When applied to tables in scientific papers, EL is a step toward large-scale scientific knowledge bases that could enable advanced scientific question answering and analytics. We present the first dataset for EL in scientific tables. EL for scientific tables is especially challenging because scientific knowledge bases can be very incomplete, and disambiguating table mentions typically requires understanding the papers's tet in addition to the table. Our dataset, S2abEL, focuses on EL in machine learning results tables and includes hand-labeled cell types, attributed sources, and entity links from the PaperswithCode taxonomy for 8,429 cells from 732 tables. We introduce a neural baseline method designed for EL on scientific tables containing many out-of-knowledge-base mentions, and show that it significantly outperforms a state-of-the-art generic table EL method. The best baselines fall below human performance, and our analysis highlights avenues for improvement.

The Semantic Scholar Open Data Platform

The volume of scientific output is creating an urgent need for automated tools to help scientists keep up with developments in their field. Semantic Scholar (S2) is an open data platform and website aimed at accelerating science by helping scholars discover and understand scientific literature. We combine public and proprietary data sources using state-of-the-art techniques for scholarly PDF content extraction and automatic knowledge graph construction to build the Semantic Scholar Academic Graph, the largest open scientific literature graph to-date, with 200M+ papers, 80M+ authors, 550M+ paper-authorship edges, and 2.4B+ citation edges. The graph includes advanced semantic features such as structurally parsed text, natural language summaries, and vector embeddings. In this paper, we describe the components of the S2 data processing pipeline and the associated APIs offered by the platform. We will update this living document to reflect changes as we add new data offerings and improve existing services.

SciRepEval: A Multi-Format Benchmark for Scientific Document Representations

Learned representations of scientific documents can serve as valuable input features for downstream tasks, without the need for further fine-tuning. However, existing benchmarks for evaluating these representations fail to capture the diversity of relevant tasks. In response, we introduce SciRepEval, the first comprehensive benchmark for training and evaluating scientific document representations. It includes 25 challenging and realistic tasks, 11 of which are new, across four formats: classification, regression, ranking and search. We then use the benchmark to study and improve the generalization ability of scientific document representation models. We show how state-of-the-art models struggle to generalize across task formats, and that simple multi-task training fails to improve them. However, a new approach that learns multiple embeddings per document, each tailored to a different format, can improve performance. We experiment with task-format-specific control codes and adapters in a multi-task setting and find that they outperform the existing single-embedding state-of-the-art by up to 1.5 points absolute.

Literature-Augmented Clinical Outcome Prediction

Predictive models for medical outcomes hold great promise for enhancing clinical decision-making. These models are trained on rich patient data such as clinical notes, aggregating many patient signals into an outcome prediction. However, AI-based clinical models have typically been developed in isolation from the prominent paradigm of Evidence Based Medicine (EBM), in which medical decisions are based on explicit evidence from existing literature. In this work, we introduce techniques to help bridge this gap between EBM and AI-based clinical models, and show that these methods can improve predictive accuracy. We propose a novel system that automatically retrieves patient-specific literature based on intensive care (ICU) patient information, aggregates relevant papers and fuses them with internal admission notes to form outcome predictions. Our model is able to substantially boost predictive accuracy on three challenging tasks in comparison to strong recent baselines; for in-hospital mortality, we are able to boost top-10% precision by a large margin of over 25%.

Overview of the TREC 2020 Fair Ranking Track

This paper provides an overview of the NIST TREC 2020 Fair Ranking track. For 2020, we again adopted an academic search task, where we have a corpus of academic article abstracts and queries submitted to a production academic search engine. The central goal of the Fair Ranking track is to provide fair exposure to different groups of authors (a group fairness framing). We recognize that there may be multiple group definitions (e.g. based on demographics, stature, topic) and hoped for the systems to be robust to these. We expected participants to develop systems that optimize for fairness and relevance for arbitrary group definitions, and did not reveal the exact group definitions until after the evaluation runs were submitted.The track contains two tasks,reranking and retrieval, with a shared evaluation.

Simplified Data Wrangling with ir_datasets

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.

ABNIRML: Analyzing the Behavior of Neural IR Models

Numerous studies have demonstrated the effectiveness of pretrained contextualized language models such as BERT and T5 for ad-hoc search. However, it is not well-understood why these methods are so effective, what makes some variants more effective than others, and what pitfalls they may have. We present a new comprehensive framework for Analyzing the Behavior of Neural IR ModeLs (ABNIRML), which includes new types of diagnostic tests that allow us to probe several characteristics---such as sensitivity to word order---that are not addressed by previous techniques. To demonstrate the value of the framework, we conduct an extensive empirical study that yields insights into the factors that contribute to the neural model's gains, and identify potential unintended biases the models exhibit. We find evidence that recent neural ranking models have fundamentally different characteristics from prior ranking models. For instance, these models can be highly influenced by altered document word order, sentence order and inflectional endings. They can also exhibit unexpected behaviors when additional content is added to documents, or when documents are expressed with different levels of fluency or formality. We find that these differences can depend on the architecture and not just the underlying language model.

SPECTER: Document-level Representation Learning using Citation-informed Transformers

Representation learning is a critical ingredient for natural language processing systems. Recent Transformer language models like BERT learn powerful textual representations, but these models are targeted towards token- and sentence-level training objectives and do not leverage information on inter-document relatedness, which limits their document-level representation power. For applications on scientific documents, such as classification and recommendation, the embeddings power strong performance on end tasks. We propose SPECTER, a new method to generate document-level embedding of scientific documents based on pretraining a Transformer language model on a powerful signal of document-level relatedness: the citation graph. Unlike existing pretrained language models, SPECTER can be easily applied to downstream applications without task-specific fine-tuning. Additionally, to encourage further research on document-level models, we introduce SciDocs, a new evaluation benchmark consisting of seven document-level tasks ranging from citation prediction, to document classification and recommendation. We show that SPECTER outperforms a variety of competitive baselines on the benchmark.