Search for: All records

Stereotypical character roles-also known as archetypes or dramatis personae-play an important function in narratives: they facilitate efficient communication with bundles of default characteristics and associations and ease understanding of those characters’ roles in the overall narrative. We present a fully unsupervised k-means clustering approach for learning stereotypical roles given only structural plot information. We demonstrate the technique on Vladimir Propp’s structural theory of Russian folktales (captured in the extended ProppLearner corpus, with 46 tales), showing that our approach can induce six out of seven of Propp’s dramatis personae with F1 measures of up to 0.70 (0.58 average), with an additional category for minor characters. We have explored various feature sets and variations of a cluster evaluation method. The best-performing feature set comprises plot functions, unigrams, tf-idf weights, and embeddings over coreference chain heads. Roles that are mentioned more often (Hero, Villain), or have clearly distinct plot patterns (Princess) are more strongly differentiated than less frequent or distinct roles (Dispatcher, Helper, Donor). Detailed error analysis suggests that the quality of the coreference chain and plot functions annotations are critical for this task. We provide all our data and code for reproducibility. 

Animacy is the characteristic of a referent beingable to independently carry out actions in a storyworld (e.g., movement, communication). It is anecessary property of characters in stories, and sodetecting animacy is an important step in automaticstory understanding; it is also potentially useful formany other natural language processing tasks suchas word sense disambiguation, coreference resolu-tion, character identification, and semantic role la-beling. Recent work by Jahanet al.[2018]demon-strated a new approach to detecting animacy whereanimacy is considered a direct property of corefer-ence chains (and referring expressions) rather thanwords. In Jahanet al., they combined hand-builtrules and machine learning (ML) to identify the an-imacy of referring expressions and used majorityvoting to assign the animacy of coreference chains,and reported high performance of up to 0.90F1. Inthis short report we verify that the approach gener-alizes to two different corpora (OntoNotes and theCorpus of English Novels) and we confirmed thatthe hybrid model performs best, with the rule-basedmodel in second place. Our tests apply the animacyclassifier to almost twice as much data as Jahanetal.’s initial study. Our results also strongly suggest,as would be expected, the dependence of the mod-els on coreference chain quality. We release ourdata and code to enable reproducibility. 

We introduce the task ofstory fragment stitching,which is the process of automatically aligning andmerging event sequences of partial tellings of astory (i.e.,story fragments). We assume that eachfragment contains at least one event from the storyof interest, and that every fragment shares at leastone event with another fragment. We propose agraph-based unsupervised approach to solving thisproblem in which events mentions are representedas nodes in the graph, and the graph is compressedusing a variant of model merging to combine nodes.The goal is for each node in the final graph to con-tain only coreferent event mentions. To find coref-erent events, we use BERT contextualized embed-ding in conjunction with atf-idfvector representa-tion. Constraints on the merge compression pre-serve the overall timeline of the story, and the finalgraph represents the full story timeline. We evalu-ate our approach using a new annotated corpus ofthe partial tellings of the story of Moses found inthe Quran, which we release for public use. Ourapproach achieves a performance of 0.63F1score 

Determining whether an event in a news article is a foreground or background event would be useful in many natural language processing tasks, for example, temporal relation extraction, summarization, or storyline generation. We introduce the task of distinguishing between foreground and background events in news articles as well as identifying the general temporal position of background events relative to the foreground period (past, present, future, and their combinations). We achieve good performance (0.73 F1 for background vs. foreground and temporal position, and 0.79 F1 for background vs. foreground only) on a dataset of news articles by leveraging discourse information in a featurized model. We release our implementation and annotated data for other researchers 

One of the most fundamental elements of narrative is character: if we are to understand a narrative, we must be able to identify the characters of that narrative. Therefore, character identification is a critical task in narrative natural language understanding. Most prior work has lacked a narratologically grounded definition of character, instead relying on simplified or implicit definitions that do not capture essential distinctions between characters and other referents in narratives. In prior work we proposed a preliminary definition of character that was based in clear narratological principles: a character is an animate entity that is important to the plot. Here we flesh out this concept, demonstrate that it can be reliably annotated (0.78 Cohen’s κ), and provide annotations of 170 narrative texts, drawn from 3 different corpora, containing 1,347 character co-reference chains and 21,999 non-character chains that include 3,937 animate chains. Furthermore, we have shown that a supervised classifier using a simple set of easily computable features can effectively identify these characters (overall F1 of 0.90). A detailed error analysis shows that character identification is first and foremost affected by co-reference quality, and further, that the shorter a chain is the harder it is to effectively identify as a character. We release our code and data for the benefit of other researchers 

Identifying the discourse structure of documents is an important task in understanding written text. Building on prior work, we demonstrate an improved approach to automatically identifying the discourse function of paragraphs in news articles. We start with the hierarchical theory of news discourse developed by van Dijk (1988) which proposes how paragraphs function within news articles. This discourse information is a level intermediate between phrase- or sentence-sized discourse segments and document genre, characterizing how individual paragraphs convey information about the events in the storyline of the article. Specifically, the theory categorizes the relationships between narrated events and (1) the overall storyline (such as Main Events, Background, or Consequences) as well as (2) commentary (such as Verbal Reactions and Evaluations). We trained and tested a linear chain conditional random field (CRF) with new features to model van Dijk’s labels and compared it against several machine learning models presented in previous work. Our model significantly outperformed all baselines and prior approaches, achieving an average of 0.71 F1 score which represents a 31.5% improvement over the previously best-performing support vector machine model. 

Recognizing the internal structure of events is a challenging language processing task of great importance for text understanding. We present a supervised model for automatically identifying when one event is a subevent of another. Building on prior work, we introduce several novel features, in particular discourse and narrative features, that significantly improve upon prior state-of-the-art performance. Error analysis further demonstrates the utility of these features. We evaluate our model on the only two annotated corpora with event hierarchies: HiEve and the Intelligence Community corpus. No prior system has been evaluated on both corpora. Our model outperforms previous systems on both corpora, achieving 0.74 BLANC F1 on the Intelligence Community corpus and 0.70 F1 on the HiEve corpus, respectively a 15 and 5 percentage point improvement over previous models. 

Characters are a key element of narrative and so character identification plays an important role in automatic narrative understanding. Unfortunately, most prior work that incorporates character identification is not built upon a clear, theoretically grounded concept of character. They either take character identification for granted (e.g., using simple heuristics on referring expressions), or rely on simplified definitions that do not capture important distinctions between characters and other referents in the story. Prior approaches have also been rather complicated, relying, for example, on predefined case bases or ontologies. In this paper we propose a narratologically grounded definition of character for discussion at the workshop, and also demonstrate a preliminary yet straightforward supervised machine learning model with a small set of features that performs well on two corpora. The most important of the two corpora is a set of 46 Russian folktales, on which the model achieves an F1 of 0.81. Error analysis suggests that features relevant to the plot will be necessary for further improvements in performance. 

Animacy is a necessary property for a referent to be an agent, and thus animacy detection is useful for a variety of natural language processing tasks, including word sense disambiguation, co-reference resolution, semantic role labeling, and others. Prior work treated animacy as a word-level property, and has developed statistical classifiers to classify words as either animate or inanimate. We discuss why this approach to the problem is ill-posed, and present a new approach based on classifying the animacy of co-reference chains. We show that simple voting approaches to inferring the animacy of a chain from its constituent words perform relatively poorly, and then present a hybrid system merging supervised machine learning (ML) and a small number of hand-built rules to compute the animacy of referring expressions and co-reference chains. This method achieves state of the art performance. The supervised ML component leverages features such as word embeddings over referring expressions, parts of speech, and grammatical and semantic roles. The rules take into consideration parts of speech and the hypernymy structure encoded in WordNet. The system achieves an F1 of 0.88 for classifying the animacy of referring expressions, which is comparable to state of the art results for classifying the animacy of words, and achieves an F1 of 0.75 for classifying the animacy of coreference chains themselves. We release our training and test dataset, which includes 142 texts (all narratives) comprising 156,154 words, 34,698 referring expressions, and 10,941 co-reference chains. We test the method on a subset of the OntoNotes dataset, showing using manual sampling that animacy classification is 90% +/- 2% accurate for coreference chains, and 92% +/- 1% for referring expressions. The data also contains 46 folktales, which present an interesting challenge because they often involve characters who are members of traditionally inanimate classes (e.g., stoves that walk, trees that talk). We show that our system is able to detect the animacy of these unusual referents with an F1 of 0.95.