Statutory reasoning is the task of reasoning with facts and statutes, which are rules written in natural language by a legislature. It is a basic legal skill. In this paper we explore the capabilities of the most capable GPT-3 model, text-davinci-003, on an established statutory-reasoning dataset called SARA. We consider a variety of approaches, including dynamic few-shot prompting, chain-of-thought prompting, and zero-shot prompting. While we achieve results with GPT-3 that are better than the previous best published results, we also identify several types of clear errors it makes. We investigate why these errors happen. We discover that GPT-3 has imperfect prior knowledge of the actual U.S. statutes on which SARA is based. More importantly, we create simple synthetic statutes, which GPT-3 is guaranteed not to have seen during training. We find GPT-3 performs poorly at answering straightforward questions about these simple synthetic statutes.

We present a novel iterative extraction model, IterX, for extracting complex relations, or templates (i.e., N-tuples representing a mapping from named slots to spans of text) within a document. Documents may feature zero or more instances of a template of any given type, and the task of template extraction entails identifying the templates in a document and extracting each template's slot values. Our imitation learning approach casts the problem as a Markov decision process (MDP), and relieves the need to use predefined template orders to train an extractor. It leads to state-of-the-art results on two established benchmarks -- 4-ary relation extraction on SciREX and template extraction on MUC-4 -- as well as a strong baseline on the new BETTER Granular task.

Transformer models cannot easily scale to long sequences due to their O(N^2) time and space complexity. This has led to Transformer variants seeking to lower computational complexity, such as Longformer and Performer. While such models have theoretically greater efficiency, their effectiveness on real NLP tasks has not been well studied. We benchmark 7 variants of Transformer models on 5 difficult NLP tasks and 7 datasets. We design experiments to isolate the effect of pretraining and hyperparameter settings, to focus on their capacity for long-range attention. Moreover, we present various methods to investigate attention behaviors to illuminate model details beyond metric scores. We find that the modified attention in long-range transformers has advantages on content selection and query-guided decoding, but they come with previously unrecognized drawbacks such as insufficient attention to distant tokens and accumulated approximation error.

Answering complex questions often requires multi-step reasoning in order to obtain the final answer. Most research into decompositions of complex questions involves open-domain systems, which have shown success in using these decompositions for improved retrieval. In the machine reading setting, however, work to understand when decompositions are helpful is understudied. We conduct experiments on decompositions in machine reading to unify recent work in this space, using a range of models and datasets. We find that decompositions can be helpful in the few-shot case, giving several points of improvement in exact match scores. However, we also show that when models are given access to datasets with around a few hundred or more examples, decompositions are not helpful (and can actually be detrimental). Thus, our analysis implies that models can learn decompositions implicitly even with limited data.

Despite the superior performance brought by vision-and-language pretraining, it remains unclear whether learning with multi-modal data can help understand each individual modality. In this work, we investigate how language can help with visual representation learning from a probing perspective. Specifically, we compare vision-and-language and vision-only models by probing their visual representations on a broad range of tasks, in order to assess the quality of the learned representations in a fine-grained manner. Interestingly, our probing results suggest that vision-and-language models are better at label prediction tasks like object and attribute prediction, while vision-only models are stronger at dense prediction tasks that require more localized information. With further analysis using detailed metrics, our study suggests that language helps vision models learn better semantics, but not localization. Code is released at https://github.com/Lizw14/visual_probing.

Event schemas are structured knowledge sources defining typical real-world scenarios (e.g., going to an airport). We present a framework for efficient human-in-the-loop construction of a schema library, based on a novel mechanism for schema induction and a wellcrafted interface that allows non-experts to "program" complex event structures. Associated with this work we release a machine readable resource (schema library) of 232 detailed event schemas, each of which describe a distinct typical scenario in terms of its relevant sub-event structure (what happens in the scenario), participants (who plays a role in the scenario), fine-grained typing of each participant, and the implied relational constraints Figure 1: An example schema from our schema library, between them. Our custom annotation interface, induced from a skeleton mined by Causal ARM (Section SchemaBlocks, and the event schemas 3) and fully fleshed out by an annotator using our are available online.

Link prediction in large knowledge graphs has received a lot of attention recently because of its importance for inferring missing relations and for completing and improving noisily extracted knowledge graphs. Over the years a number of machine learning researchers have presented various models for predicting the presence of missing relations in a knowledge base. Although all the previous methods are presented with empirical results that show high performance on select datasets, there is almost no previous work on understanding the connection between properties of a knowledge base and the performance of a model. In this paper we analyze the RESCAL method and prove that it can not encode asymmetric transitive relations in knowledge bases.

The output scores of a neural network classifier are converted to probabilities via normalizing over the scores of all competing categories. Computing this partition function, $Z$, is then linear in the number of categories, which is problematic as real-world problem sets continue to grow in categorical types, such as in visual object recognition or discriminative language modeling. We propose three approaches for sublinear estimation of the partition function, based on approximate nearest neighbor search and kernel feature maps and compare the performance of the proposed approaches empirically.

We explore training an automatic modality tagger. Modality is the attitude that a speaker might have toward an event or state. One of the main hurdles for training a linguistic tagger is gathering training data. This is particularly problematic for training a tagger for modality because modality triggers are sparse for the overwhelming majority of sentences. We investigate an approach to automatically training a modality tagger where we first gathered sentences based on a high-recall simple rule-based modality tagger and then provided these sentences to Mechanical Turk annotators for further annotation. We used the resulting set of training data to train a precise modality tagger using a multi-class SVM that delivers good performance.