skip to main content


Title: A New Approach to Animacy Detection
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.  more » « less
Award ID(s):
1749917
NSF-PAR ID:
10140307
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
Proceedings of the 27th International Conference on Computational Linguistics
Page Range / eLocation ID:
1 - 12
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. null (Ed.)
    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. 
    more » « less
  2. We test predictions from the language emergent perspective on verbal working memory that lexico-syntactic constraints should support both item and order memory. In natural language, long-term knowledge of lexico-syntactic patterns involving part of speech, verb biases, and noun animacy support language comprehension and production. In three experiments, participants were presented with randomly generated dative-like sentences or lists in which part of speech, verb biases, and animacy of a single word were manipulated. Participants were more likely to recall words in the correct position when presented with a verb over a noun in the verb position, a good dative verb over an intransitive verb in the verb position, and an animate noun over an inanimate noun in the subject noun position. These results demonstrate that interactions between words and their context in the form of lexico-syntactic constraints influence verbal working memory. 
    more » « less
  3. Speech and language development are early indicators of overall analytical and learning ability in children. The preschool classroom is a rich language environment for monitoring and ensuring growth in young children by measuring their vocal interactions with both teachers and classmates. Early childhood researchers recognize the importance in analyzing naturalistic vs. controlled lab recordings to measure both quality and quantity of child interactions. Recently, large language model-based speech technologies have performed well on conversational speech recognition. In this regard, we assess performance of such models on the wide dynamic scenario of early childhood classroom settings. This study investigates an alternate Deep Learning-based Teacher-Student learning solution for recognizing adult speech within preschool interactions. Our proposed adapted model achieves the best F1-score for recognizing most frequent 400 words on test sets for both classrooms. Additionally, F1-scores for alternate word groups provides a breakdown of performance across relevant language-based word-categories. The study demonstrates the prospects of addressing educational assessment needs through communication audio stream analysis, while maintaining both security and privacy of all children and adults. The resulting child communication metrics from this study can also be used for broad-based feedback for teachers. 
    more » « less
  4. Muresan, Smaranda ; Nakov, Preslav ; Villavicencio, Aline (Ed.)
    Phonemes are defined by their relationship to words: changing a phoneme changes the word. Learning a phoneme inventory with little supervision has been a longstanding challenge with important applications to under-resourced speech technology. In this paper, we bridge the gap between the linguistic and statistical definition of phonemes and propose a novel neural discrete representation learning model for self-supervised learning of phoneme inventory with raw speech and word labels. Under mild assumptions, we prove that the phoneme inventory learned by our approach converges to the true one with an exponentially low error rate. Moreover, in experiments on TIMIT and Mboshi benchmarks, our approach consistently learns a better phoneme-level representation and achieves a lower error rate in a zero-resource phoneme recognition task than previous state-of-the-art self-supervised representation learning algorithms. 
    more » « less
  5. Bilinguals occasionally produce language intrusion errors (inadvertent translations of the intended word), especially when attempting to produce function word targets, and often when reading aloud mixed-language paragraphs. We investigate whether these errors are due to a failure of attention during speech planning, or failure of monitoring speech output by classifying errors based on whether and when they were corrected, and investigating eye movement behaviour surrounding them. Prior research on this topic has primarily tested alphabetic languages (e.g., Spanish–English bilinguals) in which part of speech is confounded with word length, which is related to word skipping (i.e., decreased attention). Therefore, we tested 29 Chinese–English bilinguals whose languages differ in orthography, visually cueing language membership, and for whom part of speech (in Chinese) is less confounded with word length. Despite the strong orthographic cue, Chinese–English bilinguals produced intrusion errors with similar effects as previously reported (e.g., especially with function word targets written in the dominant language). Gaze durations did differ by whether errors were made and corrected or not, but these patterns were similar for function and content words and therefore cannot explain part of speech effects. However, bilinguals regressed to words produced as errors more often than to correctly produced words, but regressions facilitated correction of errors only for content, not for function words. These data suggest that the vulnerability of function words to language intrusion errors primarily reflects automatic retrieval and failures of speech monitoring mechanisms from stopping function versus content word errors after they are planned for production.

     
    more » « less