Incremental intent classification requires the assignment of intent labels to partial utterances. However, partial utterances do not necessarily contain enough information to be mapped to the intent class of their complete utterance (correctly and with a certain degree of confidence). Using the final interpretation as the ground truth to measure a classifier’s accuracy during intent classification of partial utterances is thus problematic. We release inCLINC, a dataset of partial and full utterances with human annotations of plausible intent labels for different portions of each utterance, as an upper (human) baseline for incremental intent classification. We analyse the incremental annotations and propose entropy reduction as a measure of human annotators’ convergence on an interpretation (i.e. intent label). We argue that, when the annotators do not converge to one or a few possible interpretations and yet the classifier already identifies the final intent class early on, it is a sign of overfitting that can be ascribed to artefacts in the dataset.

Reliable tagging of Temporal Expressions (TEs, e.g., Book a table at L’Osteria for Sunday evening) is a central requirement for Voice Assistants (VAs). However, there is a dearth of resources and systems for the VA domain, since publicly-available temporal taggers are trained only on substantially different domains, such as news and clinical text. Since the cost of annotating large datasets is prohibitive, we investigate the trade-off between in-domain data and performance in DA-Time, a hybrid temporal tagger for the English VA domain which combines a neural architecture for robust TE recognition, with a parser-based TE normalizer. We find that transfer learning goes a long way even with as little as 25 in-domain sentences: DA-Time performs at the state of the art on the news domain, and substantially outperforms it on the VA domain.

The recognition and automatic annotation of temporal expressions (e.g. “Add an event for tomorrow evening at eight to my calendar”) is a key module for AI voice assistants, in order to allow them to interact with apps (for example, a calendar app). However, in the NLP literature, research on temporal expressions has focused mostly on data from the news, from the clinical domain, and from social media. The voice assistant domain is very different than the typical domains that have been the focus of work on temporal expression identification, thus requiring a dedicated data collection. We present a crowdsourcing method for eliciting natural-language commands containing temporal expressions for an AI voice assistant, by using pictures and scenario descriptions. We annotated the elicited commands (480) as well as the commands in the Snips dataset following the TimeML/TIMEX3 annotation guidelines, reaching a total of 1188 annotated commands. The commands can be later used to train the NLU components of an AI voice assistant.

We present a semi-supervised clustering approach to induce script structure from crowdsourced descriptions of event sequences by grouping event descriptions into paraphrase sets (representing event types) and inducing their temporal order. Our approach exploits semantic and positional similarity and allows for flexible event order, thus overcoming the rigidity of previous approaches. We incorporate crowdsourced alignments as prior knowledge and show that exploiting a small number of alignments results in a substantial improvement in cluster quality over state-of-the-art models and provides an appropriate basis for the induction of temporal order. We also show a coverage study to demonstrate the scalability of our approach.

Scripts are standardized event sequences describing typical everyday activities, which play an important role in the computational modeling of cognitive abilities (in particular for natural language processing). We present a large-scale crowdsourced collection of explicit linguistic descriptions of script-specific event sequences (40 scenarios with 100 sequences each). The corpus is enriched with crowdsourced alignment annotation on a subset of the event descriptions, to be used in future work as seed data for automatic alignment of event descriptions (for example via clustering). The event descriptions to be aligned were chosen among those expected to have the strongest corrective effect on the clustering algorithm. The alignment annotation was evaluated against a gold standard of expert annotators. The resulting database of partially-aligned script-event descriptions provides a sound empirical basis for inducing high-quality script knowledge, as well as for any task involving alignment and paraphrase detection of events.

Logical metonymies like """"The author began the book"""" involve the interpretation of events that are not realized in the sentence (Covert events: -> """"writing the book""""). The Generative Lexicon (Pustejovsky 1995) provides a qualia-based account of covert event interpretation, claiming that the covert event is retrieved from the qualia structure of the object. Such a theory poses the question of to what extent covert events in logical metonymies can be accounted for by qualia structures. Building on previous work on English, we present a corpus study for German verbs (""""anfangen (mit)"""", """"aufhoeren (mit)"""", """"beenden"""", """"beginnen (mit)"""", """"geniessen"""", based on data obtained from the deWaC corpus. We built a corpus of logical metonymies, which were manually annotated and compared with the qualia structures of their objects, then we contrasted annotation results from two expert annotators for metonymies (""""The author began the book"""") and long forms (""""The author began reading the book"""") across verbs. Our annotation was evaluated on a sample of sentences annotated by a group of naive annotators on a crowdsourcing platform. The logical metonymy database (2661 metonymies and 1886 long forms) with two expert annotations is freely available for scientific research purposes.

Verb lexical semantic properties are only one of the factors that contribute to the determination of the event type expressed by a sentence, which is instead the result of a complex interplay between the verb meaning and its linguistic context. We report on two computational models for the automatic identification of event type in Italian. Both models use linguistically-motivated features extracted from Italian corpora. The main goal of our experiments is to evaluate the contribution of different types of linguistic indicators to identify the event type of a sentence, as well as to model various cases of context-driven event type shift. In the first model, event type identification has been modelled as a supervised classification task, performed with Maximum Entropy classifiers. In the second model, Self-Organizing Maps have been used to define and identify event types in an unsupervised way. The interaction of various contextual factors in determining the event type expressed by a sentence makes event type identification a highly challenging task. Computational models can help us to shed new light on the real structure of event type classes as well as to gain a better understanding of context-driven semantic shifts.