Makebelieve: using commonsense knowledge to generate stories

Story generation, namely, generating a reasonable story from a leading context, is an important but challenging task. In spite of the success in modeling fluency and local coherence, existing neural language generation models (e.g., GPT-2) still suffer from repetition, logic conflicts, and lack of long-range coherence in generated stories. We conjecture that this is because of the difficulty of associating relevant commonsense knowledge, understanding the causal relationships, and planning entities and events with proper temporal order. In this paper, we devise a knowledge-enhanced pretraining model for commonsense story generation. We propose to utilize commonsense knowledge from external knowledge bases to generate reasonable stories. To further capture the causal and temporal dependencies between the sentences in a reasonable story, we use multi-task learning, which combines a discriminative objective to distinguish true and fake stories during fine-tuning. Automatic and manual evaluation shows that our model can generate more reasonable stories than state-of-the-art baselines, particularly in terms of logic and global coherence.

Automated storytelling has long captured the attention of researchers for the ubiquity of narratives in everyday life. The best human-crafted stories exhibit coherent plot, strong characters, and adherence to genres, attributes that current states-of-the-art still struggle to produce, even using transformer architectures. In this paper, we analyze works in story generation that utilize machine learning approaches to (1) address story generation controllability, (2) incorporate commonsense knowledge, (3) infer reasonable character actions, and (4) generate creative language.

Integrating Robot Task Planner with Common-sense Knowledge Base to Improve the Efficiency of Planning

The telling of stories is a pervasive aspect within our life because it helps to shape our experience by structuring the events during our encounters with reality. Narrating means making a comment about a certain event, following an idea about the medium and form of presentation, which is grounded in one's own motivational and psychological attributes [5].

This paper introduces a method for bridging topics designed to facilitate generating stories over documents. First, we present a method for topic extraction based on narrative structure with k-means algorithm. We then model the story generation process and present a method for finding a bridge document between two documents.

The twenty-first century presents challenges for humanity in the context of massive environmental contamination. This problem can only be solved through awareness of man’s place in the world of the Absolute. This requires a high level of self-awareness. This brings about the need for a new approach to socially-oriented ecological thinking; host axiology that values ecology. This worldview without ideology and inaccuracy should be supported by a real basis of Aristotelian-Thomistic thinking. Furthermore, it must avoid gaps in knowledge, hence the community, in addition to possessing scientific, technical, legal and economic knowledge, should be knowledgeable of humanistic anthropology, axiology, theodicy, and religion, gained comprehensively through the use of common sense knowledge, wisdom, science, philosophy, and religion. Otherwise, gaps, inconsistencies, and even contradictions within the meaning of the world dominate and lead to quarrels and antagonism.

Currently we are facing an overburdening growth of the number of reliable information sources on the Internet. The quantity of information available to everyone via Internet is dramatically growing each year [15]. At the same time, temporal and cognitive resources of human users are not changing, therefore causing a phenomenon of information overload. World Wide Web is one of the main sources of information for decision makers (reference to my research). However our studies show that, at least in Poland, the decision makers see some important problems when turning to Internet as a source of decision information. One of the most common obstacles raised is distribution of relevant information among many sources, and therefore need to visit different Web sources in order to collect all important content and analyze it. A few research groups have recently turned to the problem of information extraction from the Web [13]. The most effort so far has been directed toward collecting data from dispersed databases accessible via web pages (related to as data extraction or information extraction from the Web) and towards understanding natural language texts by means of fact, entity, and association recognition (related to as information extraction). Data extraction efforts show some interesting results, however proper integration of web databases is still beyond us. Information extraction field has been recently very successful in retrieving information from natural language texts, however it is still lacking abilities to understand more complex information, requiring use of common sense knowledge, discourse analysis and disambiguation techniques.

It is by now widely accepted that a number of tasks in natural language understanding (NLU) require the storage of and reasoning with a vast amount of background (commonsense) knowledge. While several efforts have been made to build such ontologies, a consensus on a scientific methodology for ontological design is yet to emerge. In this paper we suggest an approach to building a commonsense ontology for language understanding using language itself as a design guide. The idea is rooted in Frege's conception of compositional semantics and is related to the idea of type inferences in strongly-typed, polymorphic programming languages. The method proposed seems to (i) resolve the problem of multiple inheritance; (ii) suggest an explanation for polysemy and metaphor; and (iii) provide a step towards establishing a systematic approach to ontological design.

Commonsense knowledge (CSK) about concepts and their properties is helpful for AI applications. Prior works, such as ConceptNet, have compiled large CSK collections. However, they are restricted in their expressiveness to subject-predicate-object (SPO) triples with simple concepts for S and strings for P and O. This paper presents a method called ASCENT++ to automatically build a large-scale knowledge base (KB) of CSK assertions, with refined expressiveness and both better precision and recall than prior works. ASCENT++ goes beyond SPO triples by capturing composite concepts with subgroups and aspects, and by refining assertions with semantic facets. The latter is essential to express the temporal and spatial validity of assertions and further qualifiers. Furthermore, ASCENT++ combines open information extraction (OpenIE) with judicious cleaning and ranking by typicality and saliency scores. For high coverage, our method taps into the large-scale crawl C4 with broad web contents. The evaluation with human judgments shows the superior quality of the ASCENT++ KB, and an extrinsic evaluation for QA-support tasks underlines the benefits of ASCENT++. A web interface, data, and code can be accessed at https://ascentpp.mpi-inf.mpg.de/.

Semantic processing represents the new challenge for all applications that require text understanding, as for instance Q/A. In this paper we will highlight the need to couple statistical approaches with deep linguistic processing and will focus on ldquoimplicitrdquo or lexically unexpressed linguistic elements that are nonetheless necessary for a complete semantic interpretation of a text. We will address the following types of ldquoimplicitrdquo entities and events: - grammatical ones, as suggested by a linguistic theories like LFG or similar generative theories; - semantic ones suggested in the FrameNet project, i.e. CNI, DNI, INI; - pragmatic ones: here we will present a theory and an implementation for the recovery of implicit entities and events of (non-) standard implicatures. In particular we will show how the use of commonsense knowledge may fruitfully contribute in finding relevant implied meanings. We will also briefly explore the subject of point of view which is computed by semantic informational structure and contributes the intended entity from whose point of view is expressed a given subjective statement. We also present an evaluation based on section 24 of Penn Treebank as encoded by LFG people in the PARC-700 treebank where lexically unexpressed are adequately classified and diversified.

In this paper, we present CogNet, a knowledge base (KB) dedicated to integrating three types of knowledge: (1) linguistic knowledge from FrameNet, which schematically describes situations, objects and events. (2) world knowledge from YAGO, Freebase, DBpedia and Wikidata, which provides explicit knowledge about specific instances. (3) commonsense knowledge from ConceptNet, which describes implicit general facts. To model these different types of knowledge consistently, we introduce a three-level unified frame-styled representation architecture. To integrate free-form commonsense knowledge with other structured knowledge, we propose a strategy that combines automated labeling and crowdsourced annotation. At present, CogNet integrates 1,000+ semantic frames from linguistic KBs, 20,000,000+ frame instances from world KBs, as well as 90,000+ commonsense assertions from commonsense KBs. All these data can be easily queried and explored on our online platform, and free to download in RDF format for utilization under a CC-BY-SA 4.0 license. The demo and data are available at http://cognet.top/.

Narrative generation aims at producing fluent long texts from input data, which is widely used in event prediction, story generation and other fields. Previous work mainly relied on text data, picture data, knowledge graphs, etc. Unfortunately, these static data only focused on entities and their relationships, cannot reflect the dynamic development of events in the real world. In addition, because the language model itself does not have the ability of logical reasoning, the generated results often lack logical reasoning. To address these challenges, several studies incorporate logic event graphs into the task of narrative generation. The Logic Event Graph(LEG) is essentially an event logic knowledge base, which describes the event evolution law and development modes. With the help of the LEG, the narrative generation system will acquire the human "reasoning" ability, and generate narratives that better reflect the objective evolution laws of human behaviors and events. While significant research has been conducted in these areas, gaps in the surveying literature still exist. In this survey, we—(1)analyze the context of narrative generation; (2)discuss the advantages of joining the LEG in narrative generate; (3)review common strategies in narrative generation; (4)summarize the evaluation metricse of narrative generate, and the advantages and disadvantages of each evaluation metrics are discussed; (5)present current challenges and future research directions. This survey can guide researchers and practitioners to understand the research progress in these areas.

Commonsense question answering (CQA) aims to test if models can answer questions regarding commonsense knowledge that everyone knows. Prior works that incorporate external knowledge bases have shown promising results, but knowledge bases are expensive to construct and are often limited to a fixed set of relations. In this paper, we instead focus on better utilizing the implicit knowledge stored in pre-trained language models. While researchers have found that the knowledge embedded in pre-trained language models can be extracted by having them fill in the blanks of carefully designed prompts for relation extraction and text classification, it remains unclear if we can adopt this paradigm in CQA where the inputs and outputs take much more flexible forms. To this end, we investigate four translation methods that can translate natural questions into cloze-style sentences to better solicit commonsense knowledge from language models, including a syntactic-based model, an unsupervised neural model, and two supervised neural models. In addition, to combine the different translation methods, we propose to encourage consistency among model predictions on different translated questions with unlabeled data. We demonstrate the effectiveness of our methods on three CQA datasets in zero-shot settings. We show that our methods are complementary to a knowledge base improved model, and combining them can lead to state-of-the-art zero-shot performance. Analyses also reveal distinct characteristics of the different cloze translation methods and provide insights on why combining them can lead to great improvements. Code/dataset is available at https://github.com/PlusLabNLP/zero_shot_cqa.

This paper describes Contexteller, a collaborative educational system for storytelling that supports teachers in configuring and adapting stories to match children's cultural background, by means of exploiting common sense knowledge. This game is meant to support teachers to interact with students with different social and cultural backgrounds, allowing her/him to create stories according to the students´ cultural reality, expressed in their common sense knowledge, and consequently enabling them to get interested in helping the development of the story. This cultural sensitive storytelling environment intends to promote a closer contact between teacher and students and among students themselves giving them a computer tool to help children to freely express their thoughts, desires and to support them to cooperative work with teachers what is desirable for their intellectual and cognitive development. Contextualization and the narrative are supported by the OMCS-Br common sense knowledge base, which gives to the teacher some resources to perform an activity according to the pedagogical goals

Despite the richness and vastness of the common-sense knowledge bases, we argue that common-sense knowledge has to be integrated into the target applications (Text Classification, Dialogue systems, Information Extraction systems, etc.) more effectively. In order to consider this common-sense knowledge in target applications, we propose a deep learning model of common-sense knowledge in Portuguese language, which can be easily coupled in Natural Language Understanding (NLU) systems in order to leverage their performance. More specifically, the model is composed by a neural network LSTM (Long Short Term Memory) that receives a text from the target application, for example, an user message in a dialog, a response to a user tweet, a news text; and selects and learns what is the best set of common-sense relations to return to the target application, which should be considered in the target learning model or system. We implemented the common-sense learning module in two target applications - a Stance Classification system and an End-to-End Dialogue system. In both cases, incorporating the deep learning model improved the results.