skip to main content

Attention:

The NSF Public Access Repository (PAR) system and access will be unavailable from 11:00 PM ET on Thursday, February 13 until 2:00 AM ET on Friday, February 14 due to maintenance. We apologize for the inconvenience.


Search for: All records

Creators/Authors contains: "Walker, Marilyn"

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. null (Ed.)
    Neural natural language generation (NNLG) from structured meaning representations has become increasingly popular in recent years. While we have seen progress with generating syntactically correct utterances that preserve semantics, various shortcomings of NNLG systems are clear: new tasks require new training data which is not available or straightforward to acquire, and model outputs are simple and may be dull and repetitive. This paper addresses these two critical challenges in NNLG by: (1) scalably (and at no cost) creating training datasets of parallel meaning representations and reference texts with rich style markup by using data from freely available and naturally descriptive user reviews, and (2) systematically exploring how the style markup enables joint control of semantic and stylistic aspects of neural model output. We present YelpNLG, a corpus of 300,000 rich, parallel meaning representations and highly stylistically varied reference texts spanning different restaurant attributes, and describe a novel methodology that can be scalably reused to generate NLG datasets for other domains. The experiments show that the models control important aspects, including lexical choice of adjectives, output length, and sentiment, allowing the models to successfully hit multiple style targets without sacrificing semantics. 
    more » « less
  2. Effective storytelling relies on engagement and interaction. This work develops an automated software platform for telling stories to children and investigates the impact of two design choices on children’s engagement and willingness to interact with the system: story distribution and the use of complex gesture. A storyteller condition compares stories told in a third person, narrator voice with those distributed between a narrator and first-person story characters. Basic gestures are used in all our storytellings, but, in a second factor, some are augmented with gestures that indicate conversational turn changes, references to other characters and prompt children to ask questions. An analysis of eye gaze indicates that children attend more to the story when a distributed storytelling model is used. Gesture prompts appear to encourage children to ask questions, something that children did, but at a relatively low rate. Interestingly, the children most frequently asked “why” questions. Gaze switching happened more quickly when the story characters began to speak than for narrator turns. These results have implications for future agent-based storytelling system research. 
    more » « less
  3. Question Generation is the task of automatically creating questions from textual input. In this work we present a new Attentional Encoder–Decoder Recurrent Neural Network model for automatic question generation. Our model incorporates linguistic features and an additional sentence embedding to capture meaning at both sentence and word levels. The linguistic features are designed to capture information related to named entity recognition, word case, and entity coreference resolution. In addition our model uses a copying mechanism and a special answer signal that enables generation of numerous diverse questions on a given sentence. Our model achieves state of the art results of 19.98 Bleu 4 on a benchmark Question Generation dataset, outperforming all previously published results by a significant margin. A human evaluation also shows that the added features improve the quality of the generated questions. 
    more » « less
  4. Conversational systems typically focus on functional tasks such as scheduling appointments or creating todo lists. Instead we design and evaluate SlugBot (SB), one of 8 semifinalists in the 2018 AlexaPrize, whose goal is to support casual open-domain social inter-action. This novel application requires both broad topic coverage and engaging interactive skills. We developed a new technical approach to meet this demanding situation by crowd-sourcing novel content and introducing playful conversational strategies based on storytelling and games. We collected over 10,000 conversations during August 2018 as part of the Alexa Prize competition. We also conducted an in-lab follow-up qualitative evaluation. Over-all users found SB moderately engaging; conversations averaged 3.6 minutes and involved 26 user turns. However, users reacted very differently to different conversation subtypes. Storytelling and games were evaluated positively; these were seen as entertaining with predictable interactive structure. They also led users to impute personality and intelligence to SB. In contrast, search and general Chit-Chat induced coverage problems; here users found it hard to infer what topics SB could understand, with these conversations seen as being too system-driven. Theoretical and design implications suggest a move away from conversational systems that simply provide factual information. Future systems should be designed to have their own opinions with personal stories to share, and SB provides an example of how we might achieve this. 
    more » « less
  5. Responses in task-oriented dialogue systems often realize multiple propositions whose ultimate form depends on the use of sentence planning and discourse structuring operations. For example a recommendation may consist of an explicitly evaluative utterance e.g. Chanpen Thai is the best option, along with content related by the justification discourse relation, e.g. It has great food and service, that combines multiple propositions into a single phrase. While neural generation methods integrate sentence planning and surface realization in one endto-end learning framework, previous work has not shown that neural generators can: (1) perform common sentence planning and discourse structuring operations; (2) make decisions as to whether to realize content in a single sentence or over multiple sentences; (3) generalize sentence planning and discourse relation operations beyond what was seen in training. We systematically create large training corpora that exhibit particular sentence planning operations and then test neural models to see what they learn. We compare models without explicit latent variables for sentence planning with ones that provide explicit supervision during training. We show that only the models with additional supervision can reproduce sentence planning and discourse operations and generalize to situations unseen in training. 
    more » « less
  6. Natural language generators for task-oriented dialog should be able to vary the style of the output utterance while still effectively realizing the system dialog actions and their associated semantics. While the use of neural generation for training the response generation component of conversational agents promises to simplify the process of producing high quality responses in new domains, to our knowledge, there has been very little investigation of neural generators for task-oriented dialog that can vary their response style and we know of no experiments on models that can generate responses that are different in style from those seen during training, while still maintaining semantic fidelity to the input meaning representation. Here, we show that a model that is trained to achieve a single stylistic personality target can produce outputs that combine stylistic targets. We carefully evaluate the multivoice outputs for both semantic fidelity and for similarities to and differences from the linguistic features that characterize the original training style. We show that contrary to our predictions, the learned models do not always simply interpolate model parameters, but rather produce styles that are distinct and novel from the personalities they were trained on. 
    more » « less
  7. Natural language generators for taskoriented dialogue must effectively realize system dialogue actions and their associated semantics. In many applications, it is also desirable for generators to control the style of an utterance. To date, work on task-oriented neural generation has primarily focused on semantic fidelity rather than achieving stylistic goals, while work on style has been done in contexts where it is difficult to measure content preservation. Here we present three different sequence-to-sequence models and carefully test how well they disentangle content and style. We use a statistical generator, PERSONAGE, to synthesize a new corpus of over 88,000 restaurant domain utterances whose style varies according to models of personality, giving us total control over both the semantic content and the stylistic variation in the training data. We then vary the amount of explicit stylistic supervision given to the three models. We show that our most explicit model can simultaneously achieve high fidelity to both semantic and stylistic goals: this model adds a context vector of 36 stylistic parameters as input to the hidden state of the encoder at each time step, showing the benefits of explicit stylistic supervision, even when the amount of training data is large. 
    more » « less
  8. null (Ed.)
    Abstract Rapid climate warming is altering Arctic and alpine tundra ecosystem structure and function, including shifts in plant phenology. While the advancement of green up and flowering are well-documented, it remains unclear whether all phenophases, particularly those later in the season, will shift in unison or respond divergently to warming. Here, we present the largest synthesis to our knowledge of experimental warming effects on tundra plant phenology from the International Tundra Experiment. We examine the effect of warming on a suite of season-wide plant phenophases. Results challenge the expectation that all phenophases will advance in unison to warming. Instead, we find that experimental warming caused: (1) larger phenological shifts in reproductive versus vegetative phenophases and (2) advanced reproductive phenophases and green up but delayed leaf senescence which translated to a lengthening of the growing season by approximately 3%. Patterns were consistent across sites, plant species and over time. The advancement of reproductive seasons and lengthening of growing seasons may have significant consequences for trophic interactions and ecosystem function across the tundra. 
    more » « less
  9. Abstract

    Arctic regions are experiencing the greatest rates of climate warming on the planet and marked changes have already been observed in terrestrial arctic ecosystems. While most studies have focused on the effects of warming on arctic vegetation and nutrient cycling, little is known about how belowground communities, such as fungi root‐associated, respond to warming. Here, we investigate how long‐term summer warming affects ectomycorrhizal (ECM) fungal communities. We used Ion Torrent sequencing of therDNAinternal transcribed spacer 2 (ITS2) region to compare ECM fungal communities in plots with and without long‐term experimental warming in both dry and moist tussock tundra.Cortinariuswas the most OTU‐rich genus in the moist tundra, while the most diverse genus in the dry tundra wasTomentella. On the diversity level, in the moist tundra we found significant differences in community composition, and a sharp decrease in the richness of ECM fungi due to warming. On the functional level, our results indicate that warming induces shifts in the extramatrical properties of the communities, where the species with medium‐distance exploration type seem to be favored with potential implications for the mobilization of different nutrient pools in the soil. In the dry tundra, neither community richness nor community composition was significantly altered by warming, similar to what had been observed in ECM host plants. There was, however, a marginally significant increase in OTUs identified as ECM fungi with the medium‐distance exploration type in the warmed plots. Linking our findings of decreasing richness with previous results of increasing ECM fungal biomass suggests that certain ECM species are favored by warming and may become more abundant, while many other species may go locally extinct due to direct or indirect effects of warming. Such compositional shifts in the community might affect nutrient cycling and soil organic C storage.

     
    more » « less