In many decision‐making scenarios, people can benefit from knowing what other people's opinions are. As more and more evaluative documents are posted on the Web, summarizing these useful resources becomes a critical task for many organizations and individuals. This paper presents a framework for summarizing a corpus of evaluative documents about a single entity by a natural language summary. We propose two summarizers: an extractive summarizer and an abstractive one. As an additional contribution, we show how our abstractive summarizer can be modified to generate summaries tailored to a model of the user preferences that is solidly grounded in decision theory and can be effectively elicited from users. We have tested our framework in three user studies. In the first one, we compared the two summarizers. They performed equally well relative to each other quantitatively, while significantly outperforming a baseline standard approach to multidocument summarization. Trends in the results as well as qualitative comments from participants suggest that the summarizers have different strengths and weaknesses. After this initial user study, we realized that the diversity of opinions expressed in the corpus (i.e., its controversiality) might play a critical role in comparing abstraction versus extraction. To clearly pinpoint the role of controversiality, we ran a second user study in which we controlled for the degree of controversiality of the corpora that were summarized for the participants. The outcome of this study indicates that for evaluative text abstraction tends to be more effective than extraction, particularly when the corpus is controversial. In the third user study we assessed the effectiveness of our user tailoring strategy. The results of this experiment confirm that user tailored summaries are more informative than untailored ones.

We explore the use of large pretrained language models as few-shot semantic parsers. The goal in semantic parsing is to generate a structured meaning representation given a natural language input. However, language models are trained to generate natural language.To bridge the gap, we use language models to paraphrase inputs into a controlled sublanguage resembling English that can be automatically mapped to a target meaning representation. Our results demonstrate that with only a small amount of data and very little code to convert into English-like representations, our blueprint for rapidly bootstrapping semantic parsers leads to surprisingly effective performance on multiple community tasks, greatly exceeding baseline methods also trained on the same limited data.

We describe an approach to task-oriented dialogue in which dialogue state is represented as a dataflow graph. A dialogue agent maps each user utterance to a program that extends this graph. Programs include metacomputation operators for reference and revision that reuse dataflow fragments from previous turns. Our graph-based state enables the expression and manipulation of complex user intents, and explicit metacomputation makes these intents easier for learned models to predict. We introduce a new dataset, SMCalFlow, featuring complex dialogues about events, weather, places, and people. Experiments show that dataflow graphs and metacomputation substantially improve representability and predictability in these natural dialogues. Additional experiments on the MultiWOZ dataset show that our dataflow representation enables an otherwise off-the-shelf sequence-to-sequence model to match the best existing task-specific state tracking model. The SMCalFlow dataset, code for replicating experiments, and a public leaderboard are available at https://www.microsoft.com/en-us/research/project/dataflow-based-dialogue-semantic-machines .

Abstract-We explore the orbital dynamics of Earth-crossing objects with the intent to understand the time scales under which an "orbital stream" of material could produce time-correlated meteorite falls. These "meteoroid streams" have been suggested to be associated with three well-known meteoritedropping fireballs (Innisfree, Peekskill, and P¯Ìbram). We have performed two different analyses of the statistical significance of the "orbital similarity," in particular calculating how often orbits of the same level of similarity would come from a random sample. Secondly, we have performed extremely detailed numerical integrations related to these three cases, and we find that if they were streams of objects in similar orbits, then they would become "decoherent" (in the sense that the day-of-fall of meteorites of these streams become almost random) on time scales of 10 4 -10 5 yr. Thus, an extremely recent breakup would be required, much more recent that the cosmic ray exposure ages of the recovered falls in each case. We conclude that orbital destruction is too efficient to allow the existence of long-lived meteoroid streams and that the statistical evidence for such streams is insufficient; random fall patterns show comparable levels of clustering.