Paragraph-level Commonsense Transformers with Recurrent Memory

• URL: http://arxiv.org/abs/2010.01486v2
• Date: Tue, 2 Feb 2021 05:17:31 GMT
• Title: Paragraph-level Commonsense Transformers with Recurrent Memory
• Authors: Saadia Gabriel, Chandra Bhagavatula, Vered Shwartz, Ronan Le Bras, Maxwell Forbes, Yejin Choi
• Abstract summary: We train a discourse-aware model that incorporates paragraph-level information to generate coherent commonsense inferences from narratives. Our results show that PARA-COMET outperforms the sentence-level baselines, particularly in generating inferences that are both coherent and novel.
• Score: 77.4133779538797
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Human understanding of narrative texts requires making commonsense inferences beyond what is stated explicitly in the text. A recent model, COMET, can generate such implicit commonsense inferences along several dimensions such as pre- and post-conditions, motivations, and mental states of the participants. However, COMET was trained on commonsense inferences of short phrases, and is therefore discourse-agnostic. When presented with each sentence of a multi-sentence narrative, it might generate inferences that are inconsistent with the rest of the narrative. We present the task of discourse-aware commonsense inference. Given a sentence within a narrative, the goal is to generate commonsense inferences along predefined dimensions, while maintaining coherence with the rest of the narrative. Such large-scale paragraph-level annotation is hard to get and costly, so we use available sentence-level annotations to efficiently and automatically construct a distantly supervised corpus. Using this corpus, we train PARA-COMET, a discourse-aware model that incorporates paragraph-level information to generate coherent commonsense inferences from narratives. PARA-COMET captures both semantic knowledge pertaining to prior world knowledge, and episodic knowledge involving how current events relate to prior and future events in a narrative. Our results show that PARA-COMET outperforms the sentence-level baselines, particularly in generating inferences that are both coherent and novel.

Related papers

• Can Language Models Take A Hint? Prompting for Controllable Contextualized Commonsense Inference [12.941933077524919]
  We introduce "hinting," a data augmentation technique that enhances contextualized commonsense inference. "Hinting" employs a prefix prompting strategy using both hard and soft prompts to guide the inference process. Our results show that "hinting" does not compromise the performance of contextual commonsense inference while offering improved controllability.
  arXiv  Detail & Related papers  (2024-10-03T04:32:46Z)
• Are Large Language Models Capable of Generating Human-Level Narratives? [114.34140090869175]
  This paper investigates the capability of LLMs in storytelling, focusing on narrative development and plot progression. We introduce a novel computational framework to analyze narratives through three discourse-level aspects. We show that explicit integration of discourse features can enhance storytelling, as is demonstrated by over 40% improvement in neural storytelling.
  arXiv  Detail & Related papers  (2024-07-18T08:02:49Z)
• Self-Consistent Narrative Prompts on Abductive Natural Language Inference [42.201304482932706]
  Abduction has long been seen as crucial for narrative comprehension and reasoning about everyday situations. We propose a prompt tuning model $alpha$-PACE, which takes self-consistency and inter-sentential coherence into consideration.
  arXiv  Detail & Related papers  (2023-09-15T10:48:10Z)
• Adversarial Transformer Language Models for Contextual Commonsense Inference [14.12019824666882]
  Contextualized or discourse aware commonsense inference is the task of generating coherent commonsense assertions. Some problems with the task are: lack of controllability for topics of the inferred facts; lack of commonsense knowledge during training. We develop techniques to address the aforementioned problems in the task.
  arXiv  Detail & Related papers  (2023-02-10T18:21:13Z)
• Computational Lens on Cognition: Study Of Autobiographical Versus Imagined Stories With Large-Scale Language Models [95.88620740809004]
  We study differences in the narrative flow of events in autobiographical versus imagined stories using GPT-3. We found that imagined stories have higher sequentiality than autobiographical stories. In comparison to imagined stories, autobiographical stories contain more concrete words and words related to the first person.
  arXiv  Detail & Related papers  (2022-01-07T20:10:47Z)
• Narrative Incoherence Detection [76.43894977558811]
  We propose the task of narrative incoherence detection as a new arena for inter-sentential semantic understanding. Given a multi-sentence narrative, decide whether there exist any semantic discrepancies in the narrative flow.
  arXiv  Detail & Related papers  (2020-12-21T07:18:08Z)
• Understanding Points of Correspondence between Sentences for Abstractive Summarization [39.7404761923196]
  We present an investigation into fusing sentences drawn from a document by introducing the notion of points of correspondence. We create a dataset containing the documents, source and fusion sentences, and human annotations of points of correspondence between sentences.
  arXiv  Detail & Related papers  (2020-06-10T02:42:38Z)
• Screenplay Summarization Using Latent Narrative Structure [78.45316339164133]
  We propose to explicitly incorporate the underlying structure of narratives into general unsupervised and supervised extractive summarization models. We formalize narrative structure in terms of key narrative events (turning points) and treat it as latent in order to summarize screenplays. Experimental results on the CSI corpus of TV screenplays, which we augment with scene-level summarization labels, show that latent turning points correlate with important aspects of a CSI episode.
  arXiv  Detail & Related papers  (2020-04-27T11:54:19Z)
• The Shmoop Corpus: A Dataset of Stories with Loosely Aligned Summaries [72.48439126769627]
  We introduce the Shmoop Corpus: a dataset of 231 stories paired with detailed multi-paragraph summaries for each individual chapter. From the corpus, we construct a set of common NLP tasks, including Cloze-form question answering and a simplified form of abstractive summarization. We believe that the unique structure of this corpus provides an important foothold towards making machine story comprehension more approachable.
  arXiv  Detail & Related papers  (2019-12-30T21:03:59Z)

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.