What do Large Language Models Learn about Scripts?

• URL: http://arxiv.org/abs/2112.13834v1
• Date: Mon, 27 Dec 2021 18:51:18 GMT
• Title: What do Large Language Models Learn about Scripts?
• Authors: Abhilasha Sancheti and Rachel Rudinger
• Abstract summary: We introduce the task of generating full event sequence descriptions given a scenario in the form of natural language prompts. In zero-shot probing experiments, we find that generative LMs produce poor ESDs with mostly omitted, irrelevant, repeated or misordered events. We propose a pipeline-based script induction framework (SIF) which can generate good quality ESDs for unseen scenarios.
• Score: 5.429894958215681
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Script Knowledge (Schank and Abelson, 1975) has long been recognized as crucial for language understanding as it can help in filling in unstated information in a narrative. However, such knowledge is expensive to produce manually and difficult to induce from text due to reporting bias (Gordon and Van Durme, 2013). In this work, we are interested in the scientific question of whether explicit script knowledge is present and accessible through pre-trained generative language models (LMs). To this end, we introduce the task of generating full event sequence descriptions (ESDs) given a scenario in the form of natural language prompts. In zero-shot probing experiments, we find that generative LMs produce poor ESDs with mostly omitted, irrelevant, repeated or misordered events. To address this, we propose a pipeline-based script induction framework (SIF) which can generate good quality ESDs for unseen scenarios (e.g., bake a cake). SIF is a two-staged framework that fine-tunes LM on a small set of ESD examples in the first stage. In the second stage, ESD generated for an unseen scenario is post-processed using RoBERTa-based models to filter irrelevant events, remove repetitions, and reorder the temporally misordered events. Through automatic and manual evaluations, we demonstrate that SIF yields substantial improvements ($1$-$3$ BLUE points) over a fine-tuned LM. However, manual analysis shows that there is great room for improvement, offering a new research direction for inducing script knowledge.

Related papers

• Instruction Position Matters in Sequence Generation with Large Language Models [67.87516654892343]
  Large language models (LLMs) are capable of performing conditional sequence generation tasks, such as translation or summarization. We propose enhancing the instruction-following capability of LLMs by shifting the position of task instructions after the input sentences.
  arXiv  Detail & Related papers  (2023-08-23T12:36:57Z)
• Can LMs Learn New Entities from Descriptions? Challenges in Propagating Injected Knowledge [72.63368052592004]
  We study LMs' abilities to make inferences based on injected facts (or propagate those facts) We find that existing methods for updating knowledge show little propagation of injected knowledge. Yet, prepending entity definitions in an LM's context improves performance across all settings.
  arXiv  Detail & Related papers  (2023-05-02T17:59:46Z)
• What Makes Data-to-Text Generation Hard for Pretrained Language Models? [17.07349898176898]
  Expressing natural language descriptions of structured facts or relations -- data-to-text generation (D2T) -- increases the accessibility of structured knowledge repositories. Previous work shows that pre-trained language models(PLMs) perform remarkably well on this task after fine-tuning on a significant amount of task-specific training data. We conduct an empirical study of both fine-tuned and auto-regressive PLMs on the DART multi-domain D2T dataset.
  arXiv  Detail & Related papers  (2022-05-23T17:58:39Z)
• In-Context Learning for Few-Shot Dialogue State Tracking [55.91832381893181]
  We propose an in-context (IC) learning framework for few-shot dialogue state tracking (DST) A large pre-trained language model (LM) takes a test instance and a few annotated examples as input, and directly decodes the dialogue states without any parameter updates. This makes the LM more flexible and scalable compared to prior few-shot DST work when adapting to new domains and scenarios.
  arXiv  Detail & Related papers  (2022-03-16T11:58:24Z)
• Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents [111.33545170562337]
  We investigate the possibility of grounding high-level tasks, expressed in natural language, to a chosen set of actionable steps. We find that if pre-trained LMs are large enough and prompted appropriately, they can effectively decompose high-level tasks into low-level plans. We propose a procedure that conditions on existing demonstrations and semantically translates the plans to admissible actions.
  arXiv  Detail & Related papers  (2022-01-18T18:59:45Z)
• proScript: Partially Ordered Scripts Generation via Pre-trained Language Models [49.03193243699244]
  We demonstrate for the first time that pre-trained neural language models (LMs) can be finetuned to generate high-quality scripts. We collected a large (6.4k), crowdsourced partially ordered scripts (named proScript) Our experiments show that our models perform well (e.g., F1=75.7 in task (i)), illustrating a new approach to overcoming previous barriers to script collection.
  arXiv  Detail & Related papers  (2021-04-16T17:35:10Z)
• Time-Stamped Language Model: Teaching Language Models to Understand the Flow of Events [8.655294504286635]
  We propose to formulate this task as a question answering problem. This enables us to use pre-trained language models on other QA benchmarks by adapting those to the procedural text understanding. Our model evaluated on the Propara dataset shows improvements on the published state-of-the-art results with a $3.1%$ increase in F1 score.
  arXiv  Detail & Related papers  (2021-04-15T17:50:41Z)
• Evaluating Document Coherence Modelling [37.287725949616934]
  We examine the performance of a broad range of pretrained LMs on a sentence intrusion detection task for English. Our experiments show that pretrained LMs perform impressively in in-domain evaluation, but experience a substantial drop in the cross-domain setting.
  arXiv  Detail & Related papers  (2021-03-18T10:05:06Z)
• Knowledge-Aware Procedural Text Understanding with Multi-Stage Training [110.93934567725826]
  We focus on the task of procedural text understanding, which aims to comprehend such documents and track entities' states and locations during a process. Two challenges, the difficulty of commonsense reasoning and data insufficiency, still remain unsolved. We propose a novel KnOwledge-Aware proceduraL text understAnding (KOALA) model, which effectively leverages multiple forms of external knowledge.
  arXiv  Detail & Related papers  (2020-09-28T10:28:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.