Recent pre-trained abstractive summarization systems have started to achieve credible performance, but a major barrier to their use in practice is their propensity to output summaries that are not faithful to the input and that contain factual errors. While a number of annotated datasets and statistical models for assessing factuality have been explored, there is no clear picture of what errors are most important to target or where current techniques are succeeding and failing. We explore both synthetic and human-labeled data sources for training models to identify factual errors in summarization, and study factuality at the word-, dependency-, and sentence-level. Our observations are threefold. First, exhibited factual errors differ significantly across datasets, and commonly-used training sets of simple synthetic errors do not reflect errors made on abstractive datasets like XSum. Second, human-labeled data with fine-grained annotations provides a more effective training signal than sentence-level annotations or synthetic data. Finally, we show that our best factuality detection model enables training of more factual XSum summarization models by allowing us to identify non-factual tokens in the training data.
While numerous methods have been proposed as defenses against adversarial examples in question answering (QA), these techniques are often model specific, require retraining of the model, and give only marginal improvements in performance over vanilla models. In this work, we present a simple model-agnostic approach to this problem that can be applied directly to any QA model without any retraining. Our method employs an explicit answer candidate reranking mechanism that scores candidate answers on the basis of their content overlap with the question before making the final prediction. Combined with a strong base QAmodel, our method outperforms state-of-the-art defense techniques, calling into question how well these techniques are actually doing and strong these adversarial testbeds are.
Neural entity typing models typically represent entity types as vectors in a high-dimensional space, but such spaces are not well-suited to modeling these types' complex interdependencies. We study the ability of box embeddings, which represent entity types as d-dimensional hyperrectangles, to represent hierarchies of fine-grained entity type labels even when these relationships are not defined explicitly in the ontology. Our model represents both types and entity mentions as boxes. Each mention and its context are fed into a BERT-based model to embed that mention in our box space; essentially, this model leverages typological clues present in the surface text to hypothesize a type representation for the mention. Soft box containment can then be used to derive probabilities, both the posterior probability of a mention exhibiting a given type and the conditional probability relations between types themselves. We compare our approach with a strong vector-based typing model, and observe state-of-the-art performance on several entity typing benchmarks. In addition to competitive typing performance, our box-based model shows better performance in prediction consistency (predicting a supertype and a subtype together) and confidence (i.e., calibration), implying that the box-based model captures the latent type hierarchies better than the vector-based model does.
Models encapsulating narrative schema knowledge have proven to be useful for a range of event-related tasks, but these models typically do not engage with temporal relationships between events. We present a a BART-based conditional generation model capable of capturing event cooccurrence as well as temporality of event sequences. This single model can address both temporal ordering, sorting a given sequence of events into the order they occurred, and event infilling, predicting new events which fit into a temporally-ordered sequence of existing ones. Our model is trained as a denoising autoencoder: we take temporally-ordered event sequences, shuffle them, delete some events, and then attempting to recover the original event sequence. In this fashion, the model learns to make inferences given incomplete knowledge about the events in an underlying scenario. On the temporal ordering task, we show that our model is able to unscramble event sequences from existing datasets without access to explicitly labeled temporal training data, outperforming both a BERT-based pairwise model and a BERT-based pointer network. On event infilling, human evaluation shows that our model is able to generate events that fit better temporally into the input events when compared to GPT-2 story completion models.
A principal barrier to training temporal relation extraction models in new domains is the lack of varied, high quality examples and the challenge of collecting more. We present a method of automatically collecting distantly-supervised examples of temporal relations. We scrape and automatically label event pairs where the temporal relations are made explicit in text, then mask out those explicit cues, forcing a model trained on this data to learn other signals. We demonstrate that a pre-trained Transformer model is able to transfer from the weakly labeled examples to human-annotated benchmarks in both zero-shot and few-shot settings, and that the masking scheme is important in improving generalization.
Despite significant progress in text generation models, a serious limitation is their tendency to produce text that is factually inconsistent with information in the input. Recent work has studied whether textual entailment systems can be used to identify factual errors; however, these sentence-level entailment models are trained to solve a different problem than generation filtering and they do not localize which part of a generation is non-factual. In this paper, we propose a new formulation of entailment that decomposes it at the level of dependency arcs. Rather than focusing on aggregate decisions, we instead ask whether the semantic relationship manifested by individual dependency arcs in the generated output is supported by the input. Human judgments on this task are difficult to obtain; we therefore propose a method to automatically create data based on existing entailment or paraphrase corpora. Experiments show that our dependency arc entailment model trained on this data can identify factual inconsistencies in paraphrasing and summarization better than sentence-level methods or those based on question generation, while additionally localizing the erroneous parts of the generation.
Compressive summarization systems typically rely on a crafted set of syntactic rules to determine what spans of possible summary sentences can be deleted, then learn a model of what to actually delete by optimizing for content selection (ROUGE). In this work, we propose to relax the rigid syntactic constraints on candidate spans and instead leave compression decisions to two data-driven criteria: plausibility and salience. Deleting a span is plausible if removing it maintains the grammaticality and factuality of a sentence, and spans are salient if they contain important information from the summary. Each of these is judged by a pre-trained Transformer model, and only deletions that are both plausible and not salient can be applied. When integrated into a simple extraction-compression pipeline, our method achieves strong in-domain results on benchmark summarization datasets, and human evaluation shows that the plausibility model generally selects for grammatical and factual deletions. Furthermore, the flexibility of our approach allows it to generalize cross-domain: our system fine-tuned on only 500 samples from a new domain can match or exceed an in-domain extractive model trained on much more data.
An advantage of seq2seq abstractive summarization models is that they generate text in a free-form manner, but this flexibility makes it difficult to interpret model behavior. In this work, we analyze summarization decoders in both blackbox and whitebox ways by studying on the entropy, or uncertainty, of the model's token-level predictions. For two strong pre-trained models, PEGASUS and BART on two summarization datasets, we find a strong correlation between low prediction entropy and where the model copies tokens rather than generating novel text. The decoder's uncertainty also connects to factors like sentence position and syntactic distance between adjacent pairs of tokens, giving a sense of what factors make a context particularly selective for the model's next output token. Finally, we study the relationship of decoder uncertainty and attention behavior to understand how attention gives rise to these observed effects in the model. We show that uncertainty is a useful perspective for analyzing summarization and text generation models more broadly.
Multimodal program synthesis, which leverages different types of user input to synthesize a desired program, is an attractive way to scale program synthesis to challenging settings; however, it requires integrating noisy signals from the user (like natural language) with hard constraints on the program's behavior. This paper proposes an optimal neural synthesis approach where the goal is to find a program that satisfies user-provided constraints while also maximizing the program's score with respect to a neural model. Specifically, we focus on multimodal synthesis tasks in which the user intent is expressed using combination of natural language (NL) and input-output examples. At the core of our method is a top-down recurrent neural model that places distributions over abstract syntax trees conditioned on the NL input. This model not only allows for efficient search over the space of syntactically valid programs, but it allows us to leverage automated program analysis techniques for pruning the search space based on infeasibility of partial programs with respect to the user's constraints. The experimental results on a multimodal synthesis dataset (StructuredRegex) show that our method substantially outperforms prior state-of-the-art techniques in terms of accuracy %, finds model-optimal programs more frequently, and explores fewer states during search.