Large language models are rapidly replacing help forums like StackOverflow, and are especially helpful to non-professional programmers and end users. These users are often interested in data-centric tasks, like spreadsheet manipulation and data wrangling, which are hard to solve if the intent is only communicated using a natural-language description, without including data. But how do we decide how much data and which data to include in the prompt?This paper makes two contributions towards answering this question. First, we create a dataset of real-world NL-to-code tasks manipulating tabular data, mined from StackOverflow posts. Second, we introduce a novel cluster-then-select prompting technique, which adds the most representative rows from the input data to the LLM prompt. Our experiments show that LLM performance is indeed sensitive to the amount of data passed in the prompt, and that for tasks with a lot of syntactic variation in the input table,our cluster-then-select technique outperforms a random selection baseline.
Early proposals for the deep understanding of natural language text advocated an approach of “interpretation as abduction,” where the meaning of a text was derived as an explanation that logically entailed the input words, given a knowledge base of lexical and commonsense axioms. While most subsequent NLP research has instead pursued statistical and data-driven methods, the approach of interpretation as abduction has seen steady advancements in both theory and software implementations. In this paper, we summarize advances in deriving the logical form of the text, encoding commonsense knowledge, and technologies for scalable abductive reasoning. We then explore the application of these advancements to the deep understanding of a paragraph of news text, where the subtle meaning of words and phrases are resolved by backward chaining on a knowledge base of 80 hand-authored axioms.
We examine an emerging NLP application that supports creative writing by automatically suggesting continuing sentences in a story. The application tracks users’ modifications to generated sentences, which can be used to quantify their “helpfulness” in advancing the story. We explore the task of predicting helpfulness based on automatically detected linguistic features of the suggestions. We illustrate this analysis on a set of user interactions with the application using an initial selection of features relevant to story generation.
We address the task of predicting causally related events in stories according to a standard evaluation framework, the Choice of Plausible Alternatives (COPA). We present a neural encoder-decoder model that learns to predict relations between adjacent sequences in stories as a means of modeling causality. We explore this approach using different methods for extracting and representing sequence pairs as well as different model architectures. We also compare the impact of different training datasets on our model. In particular, we demonstrate the usefulness of a corpus not previously applied to COPA, the ROCStories corpus. While not state-of-the-art, our results establish a new reference point for systems evaluated on COPA, and one that is particularly informative for future neural-based approaches.
The Story Cloze Test consists of choosing a sentence that best completes a story given two choices. In this paper we present a system that performs this task using a supervised binary classifier on top of a recurrent neural network to predict the probability that a given story ending is correct. The classifier is trained to distinguish correct story endings given in the training data from incorrect ones that we artificially generate. Our experiments evaluate different methods for generating these negative examples, as well as different embedding-based representations of the stories. Our best result obtains 67.2% accuracy on the test set, outperforming the existing top baseline of 58.5%.
Obsessive-compulsive disorder (OCD) is an anxiety-based disorder that affects around 2.5% of the population. A common treatment for OCD is exposure therapy, where the patient repeatedly confronts a feared experience, which has the long-term effect of decreasing their anxiety. Some exposures consist of reading and writing stories about an imagined anxiety-provoking scenario. In this paper, we present a technology that enables patients to interactively contribute to exposure stories by supplying natural language input (typed or spoken) that advances a scenario. This interactivity could potentially increase the patient’s sense of immersion in an exposure and contribute to its success. We introduce the NLP task behind processing inputs to predict new events in the scenario, and describe our initial approach. We then illustrate the future possibility of this work with an example of an exposure scenario authored with our application.