Search for: All records

Answering complex questions that require making latent decisions is a challenging task, especially when limited supervision is available. Recent works leverage the capabilities of large language models (LMs) to perform complex question answering in a few-shot setting by demonstrating how to output intermediate rationalizations while solving the complex question in a single pass. We introduce “Successive Prompting” where, we iteratively break down a complex task into a simple task, solve it, and then repeat the process until we get the final solution. Successive prompting decouples the supervision for decomposing complex questions from the supervision for answering simple questions, allowing us to (1) have multiple opportunities to query in-context examples at each reasoning step (2) learn question decomposition separately from question answering, including using synthetic data, and (3) use bespoke (fine-tuned) components for reasoning steps where a large LM does not perform well. The intermediate supervision is typically manually written, which can be expensive to collect. We introduce a way to generate synthetic dataset which can be used to bootstrap model’s ability to decompose and answer intermediate questions. Our best model (with successive prompting) achieves an improvement in F1 of ~5% when compared with a state-of-the-art model with synthetic augmentations and few-shot version of the DROP dataset. 

A growing body of research has demonstrated the inability of NLP models to generalize compositionally and has tried to alleviate it through specialized architectures, training schemes, and data augmentation, among other approaches. In this work, we study a different approach: training on instances with diverse structures. We propose a model-agnostic algorithm for subsampling such sets of instances from a labeled instance pool with structured outputs. Evaluating on both compositional template splits and traditional IID splits of 5 semantic parsing datasets of varying complexity, we show that structurally diverse training using our algorithm leads to comparable or better generalization than prior algorithms in 9 out of 10 dataset-split type pairs. In general, we find structural diversity to consistently improve sample efficiency compared to random train sets. Moreover, we show that structurally diverse sampling yields comprehensive test sets that are a lot more challenging than IID test sets. Finally, we provide two explanations for improved generalization from diverse train sets: 1) improved coverage of output substructures, and 2) a reduction in spurious correlations between these substructures. 

Training a referring expression comprehension (ReC) model for a new visual domain requires collecting referring expressions, and potentially corresponding bounding boxes, for images in the domain. While large-scale pre-trained models are useful for image classification across domains, it remains unclear if they can be applied in a zero-shot manner to more complex tasks like ReC. We present ReCLIP, a simple but strong zero-shot baseline that repurposes CLIP, a state-of-the-art large-scale model, for ReC. Motivated by the close connection between ReC and CLIP’s contrastive pre-training objective, the first component of ReCLIP is a region-scoring method that isolates object proposals via cropping and blurring, and passes them to CLIP. However, through controlled experiments on a synthetic dataset, we find that CLIP is largely incapable of performing spatial reasoning off-the-shelf. We reduce the gap between zero-shot baselines from prior work and supervised models by as much as 29% on RefCOCOg, and on RefGTA (video game imagery), ReCLIP’s relative improvement over supervised ReC models trained on real images is 8%. 

Streaming cross document entity coreference (CDC) systems disambiguate mentions of named entities in a scalable manner via incremental clustering. Unlike other approaches for named entity disambiguation (e.g., entity linking), streaming CDC allows for the disambiguation of entities that are unknown at inference time. Thus, it is well-suited for processing streams of data where new entities are frequently introduced. Despite these benefits, this task is currently difficult to study, as existing approaches are either evaluated on datasets that are no longer available, or omit other crucial details needed to ensure fair comparison. In this work, we address this issue by compiling a large benchmark adapted from existing free datasets, and performing a comprehensive evaluation of a number of novel and existing baseline models. We investigate: how to best encode mentions, which clustering algorithms are most effective for grouping mentions, how models transfer to different domains, and how bounding the number of mentions tracked during inference impacts performance. Our results show that the relative performance of neural and feature-based mention encoders varies across different domains, and in most cases the best performance is achieved using a combination of both approaches. We also find that performance is minimally impacted by limiting the number of tracked mentions. 

The predominant challenge in weakly supervised semantic parsing is that of spurious programs that evaluate to correct answers for the wrong reasons. Prior work uses elaborate search strategies to mitigate the prevalence of spurious programs; however, they typically consider only one input at a time. In this work we explore the use of consistency between the output programs for related inputs to reduce the impact of spurious programs. We bias the program search (and thus the model’s training signal) towards programs that map the same phrase in related inputs to the same sub-parts in their respective programs. Additionally, we study the importance of designing logical formalisms that facilitate this kind of consistency-based training. We find that a more consistent formalism leads to improved model performance even without consistency-based training. When combined together, these two insights lead to a 10% absolute improvement over the best prior result on the Natural Language Visual Reasoning dataset. 

Knowledge-dependent tasks typically use two sources of knowledge: parametric, learned at training time, and contextual, given as a passage at inference time. To understand how models use these sources together, we formalize the problem of knowledge conflicts, where the contextual information contradicts the learned information. Analyzing the behaviour of popular models, we measure their over-reliance on memorized information (the cause of hallucinations), and uncover important factors that exacerbate this behaviour. Lastly, we propose a simple method to mitigate over-reliance on parametric knowledge, which minimizes hallucination, and improves out-of-distribution generalization by 4% - 7%. Our findings demonstrate the importance for practitioners to evaluate model tendency to hallucinate rather than read, and show that our mitigation strategy encourages generalization to evolving information (i.e. time-dependent queries). To encourage these practices, we have released our framework for generating knowledge conflicts. 

The ongoing pandemic has heightened the need for developing tools to flag COVID-19-related misinformation on the internet, specifically on social media such as Twitter. However, due to novel language and the rapid change of information, existing misinformation detection datasets are not effective for evaluating systems designed to detect misinformation on this topic. Misinformation detection can be divided into two sub-tasks: (i) retrieval of misconceptions relevant to posts being checked for veracity, and (ii) stance detection to identify whether the posts Agree, Disagree, or express No Stance towards the retrieved misconceptions. To facilitate research on this task, we release COVIDLies (https://ucinlp.github.io/covid19 ), a dataset of 6761 expert-annotated tweets to evaluate the performance of misinformation detection systems on 86 different pieces of COVID-19 related misinformation. We evaluate existing NLP systems on this dataset, providing initial benchmarks and identifying key challenges for future models to improve upon. 

To identify what entities are being talked about in tweets, we need to automatically link named entities that appear in tweets to structured KBs like WikiData. Existing approaches often struggle with such short, noisy texts, or their complex design and reliance on supervision make them brittle, difficult to use and maintain, and lose significance over time. Further, there is a lack of a large, linked corpus of tweets to aid researchers, along with lack of gold dataset to evaluate the accuracy of entity linking. In this paper, we introduce (1) Tweeki, an unsupervised, modular entity linking system for Twitter, (2) TweekiData, a large, automatically-annotated corpus of Tweets linked to entities in WikiData, and (3) TweekiGold, a gold dataset for entity linking evaluation. Through comprehensive analysis, we show that Tweeki is comparable to the performance of recent state-of-the-art entity linkers models, the dataset is of high quality, and a use case of how the dataset can be used to improve downstream tasks in social media analysis (geolocation prediction). 

Representing knowledge graphs (KGs) by learning embeddings for entities and relations has led to accurate models for existing KG completion benchmarks. However, due to the open-world assumption of existing KGs, evaluation of KG completion uses ranking metrics and triple classification with negative samples, and is thus unable to directly assess models on the goals of the task: completion. In this paper, we first study the shortcomings of these evaluation metrics. Specifically, we demonstrate that these metrics (1) are unreliable for estimating how calibrated the models are, (2) make strong assumptions that are often violated, and 3) do not sufficiently, and consistently, differentiate embedding methods from each other, or from simpler approaches. To address these issues, we gather a semi-complete KG referred as YAGO3-TC, using a random subgraph from the test and validation data of YAGO3-10, which enables us to compute accurate triple classification accuracy on this data. Conducting thorough experiments on existing models, we provide new insights and directions for the KG completion research. Along with the dataset and the open source implementation of the models, we also provide a leaderboard for knowledge graph completion that consists of a hidden, and growing, test set, available at https://pouyapez.github.io/yago3-tc/.