We present NESL (the Neuro-Episodic Schema Learner), an event schema learning system that combines large language models, FrameNet parsing, a powerful logical representation of language, and a set of simple behavioral schemas meant to bootstrap the learning process. In lieu of a pre-made corpus of stories, our dataset is a continuous feed of “situation samples” from a pre-trained language model, which are then parsed into FrameNet frames, mapped into simple behavioral schemas, and combined and generalized into complex, hierarchical schemas for a variety of everyday scenarios. We show that careful sampling from the language model can help emphasize stereotypical properties of situations and de-emphasize irrelevant details, and that the resulting schemas specify situations more comprehensively than those learned by other systems.
more »
« less
Learning general event schemas with episodic logic
We present a system for learning generalized, stereotypical patterns of events—or
“schemas”—from natural language stories, and applying them to make predictions about other stories. Our schemas are represented with Episodic Logic, a logical form that closely mirrors natural language. By beginning with a “head start” set of protoschemas—schemas that a 1- or 2-year-old child would likely know—we can obtain useful, general world knowledge with very few story examples—often only one or two. Learned schemas can be combined into more complex, composite schemas, and used to make predictions in other stories where only partial information is available.
more »
« less
- Award ID(s):
- 1940981
- NSF-PAR ID:
- 10299990
- Date Published:
- Journal Name:
- Workshop at NASSLLI 2020, Brandeis University, Waltham MA, July 11-17, 2020.
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Event schemas are a form of world knowledge about the typical progression of events. Recent methods for event schema induction use information extraction systems to construct a large number of event graph instances from documents, and then learn to generalize the schema from such instances. In contrast, we propose to treat event schemas as a form of commonsense knowledge that can be derived from large language models (LLMs). This new paradigm greatly simplifies the schema induction process and allows us to handle both hierarchical relations and temporal relations between events in a straightforward way. Since event schemas have complex graph structures, we design an incremental prompting and verification method INCPROMPT to break down the construction of a complex event graph into three stages: event skeleton construction, event expansion, and event-event relation verification. Compared to directly using LLMs to generate a linearized graph, INCPROMPT can generate large and complex schemas with 7.2% F1 improvement in temporal relations and 31.0% F1 improvement in hierarchical relations. In addition, compared to the previous state-of-the-art closed-domain schema induction model, human assessors were able to cover ∼10% more events when translating the schemas into coherent stories and rated our schemas 1.3 points higher (on a 5-point scale) in terms of readability.more » « less
-
Espinosa-Anke, Luis ; Martín-Vide, Carlos ; Spasić, Irena (Ed.)Algorithmic journalism refers to automatic AI-constructed news stories. There have been successful commercial implementations for news stories in sports, weather, financial reporting and similar domains with highly structured, well defined tabular data sources. Other domains such as local reporting have not seen adoption of algorithmic journalism, and thus no automated reporting systems are available in these categories which can have important implications for the industry. In this paper, we demonstrate a novel approach for producing news stories on government legislative activity, an area that has not widely adopted algorithmic journalism. Our data source is state legislative proceedings, primarily the transcribed speeches and dialogue from floor sessions and committee hearings in US State legislatures. Specifically, we create a library of potential events called phenoms. We systematically analyze the transcripts for the presence of phenoms using a custom partial order planner. Each phenom, if present, contributes some natural language text to the generated article: either stating facts, quoting individuals or summarizing some aspect of the discussion. We evaluate two randomly chosen articles with a user study on Amazon Mechanical Turk with mostly Likert scale questions. Our results indicate a high degree of achievement for accuracy of facts and readability of final content with 13 of 22 users in the first article and 19 of 20 subjects of the second article agreeing or strongly agreeing that the articles included the most important facts of the hearings. Other results strengthen this finding in terms of accuracy, focus and writing quality.more » « less
-
The scientific literature sometimes considers music an abstract stimulus, devoid of explicit meaning, and at other times considers it a universal language. Here, individuals in three geographically distinct locations spanning two cultures performed a highly unconstrained task: they provided free-response descriptions of stories they imagined while listening to instrumental music. Tools from natural language processing revealed that listeners provide highly similar stories to the same musical excerpts when they share an underlying culture, but when they do not, the generated stories show limited overlap. These results paint a more complex picture of music’s power: music can generate remarkably similar stories in listeners’ minds, but the degree to which these imagined narratives are shared depends on the degree to which culture is shared across listeners. Thus, music is neither an abstract stimulus nor a universal language but has semantic affordances shaped by culture, requiring more sustained attention from psychology.more » « less
-
null (Ed.)Many techniques in modern computational linguistics and natural language processing (NLP) make the assumption that approaches that work well on English and other widely used European (and sometimes Asian) languages are “language agnostic” – that is that they will also work across the typologically diverse languages of the world. In high-resource languages, especially those that are analytic rather than synthetic, a common approach is to treat morphologically-distinct variants of a common root (such as dog and dogs) as completely independent word types. Doing so relies on two main assumptions: that there exist a limited number of morphological inflections for any given root, and that most or all of those variants will appear in a large enough corpus (conditioned on assumptions about domain, etc.) so that the model can adequately learn statistics about each variant. Approaches like stemming, lemmatization, morphological analysis, subword segmentation, or other normalization techniques are frequently used when either of those assumptions are likely to be violated, particularly in the case of synthetic languages like Czech and Russian that have more inflectional morphology than English. Within the NLP literature, agglutinative languages like Finnish and Turkish are commonly held up as extreme examples of morphological complexity that challenge common modelling assumptions. Yet, when considering all of the world’s languages, Finnish and Turkish are closer to the average case in terms of synthesis. When we consider polysynthetic languages (those at the extreme of morphological complexity), even approaches like stemming, lemmatization, or subword modelling may not suffice. These languages have very high numbers of hapax legomena (words appearing only once in a corpus), underscoring the need for appropriate morphological handling of words, without which there is no hope for a model to capture enough statistical information about those words. Moreover, many of these languages have only very small text corpora, substantially magnifying these challenges. To this end, we examine the current state-of-the-art in language modelling, machine translation, and predictive text completion in the context of four polysynthetic languages: Guaraní, St. Lawrence Island Yupik, Central Alaskan Yup’ik, and Inuktitut. We have a particular focus on Inuit-Yupik, a highly challenging family of endangered polysynthetic languages that ranges geographically from Greenland through northern Canada and Alaska to far eastern Russia. The languages in this family are extraordinarily challenging from a computational perspective, with pervasive use of derivational morphemes in addition to rich sets of inflectional suffixes and phonological challenges at morpheme boundaries. Finally, we propose a novel framework for language modelling that combines knowledge representations from finite-state morphological analyzers with Tensor Product Representations (Smolensky, 1990) in order to enable successful neural language models capable of handling the full linguistic variety of typologically variant languages.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
