Marilyn Walker

Vrindavan Harrison, Rishi Rajasekaran, Marilyn Walker

Many open-domain dialogue systems rely on multiple response generators, any of which can contribute a response to the dialogue in a particular context. Thus the ability to compare potential responses and then select the best plays an important role in ensuring a dialogue system is coherent and engaging. Dialogue coherence goes beyond simply remaining on topic -- some trivia may be on topic and engaging when mentioned out of the blue, but may not be coherent and grounded in the context of the conversation. We carry out experiments on response selection in the Athena system, an Alexa Prize SocialBot that has dedicated content and multiple topic-specific response generators for a large number of topics. First, we collect a corpus of Athena conversations with live human traffic, where potential responses from all enabled response generators are logged and subsequently annotated for response quality. We compare several off-the-shelf response ranking methods for open-domain dialogue to Athena-Heuristic, a heuristic response ranker that was field-tested in Athena during the third Alexa Prize competition. We also compare these to a transformer-based response ranker we call Athena-RR, that we train on our Athena conversations. Athena-RR uses both the conversational context and the dialogue state to rank the potential responses. We find that Athena-RR with a Recall@1 of 70.79\% outperforms Athena-Heuristic and all of the off-the-shelf rankers by a large margin. We then conduct a live A/B study comparing Athena-Heuristic to Athena-RR in a 6,358 conversations with Alexa users. We show that Athena-RR leads to significantly longer conversations that receive significantly higher user ratings than the heuristic rule-based ranker.

Juraj Juraska, Kevin K. Bowden, Lena Reed et al.

Athena 2.0 is an Alexa Prize SocialBot that has been a finalist in the last two Alexa Prize Grand Challenges. One reason for Athena's success is its novel dialogue management strategy, which allows it to dynamically construct dialogues and responses from component modules, leading to novel conversations with every interaction. Here we describe Athena's system design and performance in the Alexa Prize during the 20/21 competition. A live demo of Athena as well as video recordings will provoke discussion on the state of the art in conversational AI.

Vrindavan Harrison, Juraj Juraska, Wen Cui et al.

This report describes Athena, a dialogue system for spoken conversation on popular topics and current events. We develop a flexible topic-agnostic approach to dialogue management that dynamically configures dialogue based on general principles of entity and topic coherence. Athena's dialogue manager uses a contract-based method where discourse constraints are dispatched to clusters of response generators. This allows Athena to procure responses from dynamic sources, such as knowledge graph traversals and feature-based on-the-fly response retrieval methods. After describing the dialogue system architecture, we perform an analysis of conversations that Athena participated in during the 2019 Alexa Prize Competition. We conclude with a report on several user studies we carried out to better understand how individual user characteristics affect system ratings.

Vrindavan Harrison, Lena Reed, Shereen Oraby et al.

Neural generation methods for task-oriented dialogue typically generate from a meaning representation that is populated using a database of domain information, such as a table of data describing a restaurant. While earlier work focused solely on the semantic fidelity of outputs, recent work has started to explore methods for controlling the style of the generated text while simultaneously achieving semantic accuracy. Here we experiment with two stylistic benchmark tasks, generating language that exhibits variation in personality, and generating discourse contrast. We report a huge performance improvement in both stylistic control and semantic accuracy over the state of the art on both of these benchmarks. We test several different models and show that putting stylistic conditioning in the decoder and eliminating the semantic re-ranker used in earlier models results in more than 15 points higher BLEU for Personality, with a reduction of semantic error to near zero. We also report an improvement from .75 to .81 in controlling contrast and a reduction in semantic error from 16% to 2%.

Jiaqi Wu, Ryan Compton, Geetanjali Rakshit et al.

We present our system, CruzAffect, for the CL-Aff Shared Task 2019. CruzAffect consists of several types of robust and efficient models for affective classification tasks. We utilize both traditional classifiers, such as XGBoosted Forest, as well as a deep learning Convolutional Neural Networks (CNN) classifier. We explore rich feature sets such as syntactic features, emotional features, and profile features, and utilize several sentiment lexicons, to discover essential indicators of social involvement and control that a subject might exercise in their happy moments, as described in textual snippets from the HappyDB database. The data comes with a labeled set (10K), and a larger unlabeled set (70K). We therefore use supervised methods on the 10K dataset, and a bootstrapped semi-supervised approach for the 70K. We evaluate these models for binary classification of agency and social labels (Task 1), as well as multi-class prediction for concepts labels (Task 2). We obtain promising results on the held-out data, suggesting that the proposed feature sets effectively represent the data for affective classification tasks. We also build concepts models that discover general themes recurring in happy moments. Our results indicate that generic characteristics are shared between the classes of agency, social and concepts, suggesting it should be possible to build general models for affective classification tasks.

Lena Reed, Shereen Oraby, Marilyn Walker

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 end-to-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 planing and discourse operations and generalize to situations unseen in training.

Kevin K. Bowden, Jiaqi Wu, Shereen Oraby et al.

In dialogue systems, the tasks of named entity recognition (NER) and named entity linking (NEL) are vital preprocessing steps for understanding user intent, especially in open domain interaction where we cannot rely on domain-specific inference. UCSC's effort as one of the funded teams in the 2017 Amazon Alexa Prize Contest has yielded Slugbot, an open domain social bot, aimed at casual conversation. We discovered several challenges specifically associated with both NER and NEL when building Slugbot, such as that the NE labels are too coarse-grained or the entity types are not linked to a useful ontology. Moreover, we have discovered that traditional approaches do not perform well in our context: even systems designed to operate on tweets or other social media data do not work well in dialogue systems. In this paper, we introduce Slugbot's Named Entity Recognition for dialogue Systems (SlugNERDS), a NER and NEL tool which is optimized to address these issues. We describe two new resources that we are building as part of this work: SlugEntityDB and SchemaActuator. We believe these resources will be useful for the research community.

Marilyn A. Walker, Albry Smither, Shereen Oraby et al.

Dialogue systems for hotel and tourist information have typically simplified the richness of the domain, focusing system utterances on only a few selected attributes such as price, location and type of rooms. However, much more content is typically available for hotels, often as many as 50 distinct instantiated attributes for an individual entity. New methods are needed to use this content to generate natural dialogues for hotel information, and in general for any domain with such rich complex content. We describe three experiments aimed at collecting data that can inform an NLG for hotels dialogues, and show, not surprisingly, that the sentences in the original written hotel descriptions provided on webpages for each hotel are stylistically not a very good match for conversational interaction. We quantify the stylistic features that characterize the differences between the original textual data and the collected dialogic data. We plan to use these in stylistic models for generation, and for scoring retrieved utterances for use in hotel dialogues

Amita Misra, Shereen Oraby, Shubhangi Tandon et al.

Online argumentative dialog is a rich source of information on popular beliefs and opinions that could be useful to companies as well as governmental or public policy agencies. Compact, easy to read, summaries of these dialogues would thus be highly valuable. A priori, it is not even clear what form such a summary should take. Previous work on summarization has primarily focused on summarizing written texts, where the notion of an abstract of the text is well defined. We collect gold standard training data consisting of five human summaries for each of 161 dialogues on the topics of Gay Marriage, Gun Control and Abortion. We present several different computational models aimed at identifying segments of the dialogues whose content should be used for the summary, using linguistic features and Word2vec features with both SVMs and Bidirectional LSTMs. We show that we can identify the most important arguments by using the dialog context with a best F-measure of 0.74 for gun control, 0.71 for gay marriage, and 0.67 for abortion.

Shereen Oraby, Vrindavan Harrison, Lena Reed et al.

The use of irony and sarcasm in social media allows us to study them at scale for the first time. However, their diversity has made it difficult to construct a high-quality corpus of sarcasm in dialogue. Here, we describe the process of creating a large- scale, highly-diverse corpus of online debate forums dialogue, and our novel methods for operationalizing classes of sarcasm in the form of rhetorical questions and hyperbole. We show that we can use lexico-syntactic cues to reliably retrieve sarcastic utterances with high accuracy. To demonstrate the properties and quality of our corpus, we conduct supervised learning experiments with simple features, and show that we achieve both higher precision and F than previous work on sarcasm in debate forums dialogue. We apply a weakly-supervised linguistic pattern learner and qualitatively analyze the linguistic differences in each class.

Shereen Oraby, Lena Reed, Ryan Compton et al.

We investigate the characteristics of factual and emotional argumentation styles observed in online debates. Using an annotated set of "factual" and "feeling" debate forum posts, we extract patterns that are highly correlated with factual and emotional arguments, and then apply a bootstrapping methodology to find new patterns in a larger pool of unannotated forum posts. This process automatically produces a large set of patterns representing linguistic expressions that are highly correlated with factual and emotional language. Finally, we analyze the most discriminating patterns to better understand the defining characteristics of factual and emotional arguments.

Amita Misra, Marilyn Walker

Research on the structure of dialogue has been hampered for years because large dialogue corpora have not been available. This has impacted the dialogue research community's ability to develop better theories, as well as good off the shelf tools for dialogue processing. Happily, an increasing amount of information and opinion exchange occur in natural dialogue in online forums, where people share their opinions about a vast range of topics. In particular we are interested in rejection in dialogue, also called disagreement and denial, where the size of available dialogue corpora, for the first time, offers an opportunity to empirically test theoretical accounts of the expression and inference of rejection in dialogue. In this paper, we test whether topic-independent features motivated by theoretical predictions can be used to recognize rejection in online forums in a topic independent way. Our results show that our theoretically motivated features achieve 66% accuracy, an improvement over a unigram baseline of an absolute 6%.

Lena Reed, Jiaqi Wu, Shereen Oraby et al.

Informal first-person narratives are a unique resource for computational models of everyday events and people's affective reactions to them. People blogging about their day tend not to explicitly say I am happy. Instead they describe situations from which other humans can readily infer their affective reactions. However current sentiment dictionaries are missing much of the information needed to make similar inferences. We build on recent work that models affect in terms of lexical predicate functions and affect on the predicate's arguments. We present a method to learn proxies for these functions from first-person narratives. We construct a novel fine-grained test set, and show that the patterns we learn improve our ability to predict first-person affective reactions to everyday events, from a Stanford sentiment baseline of .67F to .75F.

Zhichao Hu, Marilyn A. Walker

To understand narrative, humans draw inferences about the underlying relations between narrative events. Cognitive theories of narrative understanding define these inferences as four different types of causality, that include pairs of events A, B where A physically causes B (X drop, X break), to pairs of events where A causes emotional state B (Y saw X, Y felt fear). Previous work on learning narrative relations from text has either focused on "strict" physical causality, or has been vague about what relation is being learned. This paper learns pairs of causal events from a corpus of film scene descriptions which are action rich and tend to be told in chronological order. We show that event pairs induced using our methods are of high quality and are judged to have a stronger causal relation than event pairs from Rel-grams.

Elahe Rahimtoroghi, Ernesto Hernandez, Marilyn A Walker

Much of the user-generated content on social media is provided by ordinary people telling stories about their daily lives. We develop and test a novel method for learning fine-grained common-sense knowledge from these stories about contingent (causal and conditional) relationships between everyday events. This type of knowledge is useful for text and story understanding, information extraction, question answering, and text summarization. We test and compare different methods for learning contingency relation, and compare what is learned from topic-sorted story collections vs. general-domain stories. Our experiments show that using topic-specific datasets enables learning finer-grained knowledge about events and results in significant improvement over the baselines. An evaluation on Amazon Mechanical Turk shows 82% of the relations between events that we learn from topic-sorted stories are judged as contingent.

Stephanie M. Lukin, Kevin Bowden, Casey Barackman et al.

We present a new corpus, PersonaBank, consisting of 108 personal stories from weblogs that have been annotated with their Story Intention Graphs, a deep representation of the fabula of a story. We describe the topics of the stories and the basis of the Story Intention Graph representation, as well as the process of annotating the stories to produce the Story Intention Graphs and the challenges of adapting the tool to this new personal narrative domain We also discuss how the corpus can be used in applications that retell the story using different styles of tellings, co-tellings, or as a content planner.

Stephanie M. Lukin, Luke Eisenberg, Thomas Corcoran et al.

More and more of the information on the web is dialogic, from Facebook newsfeeds, to forum conversations, to comment threads on news articles. In contrast to traditional, monologic resources such as news, highly social dialogue is very frequent in social media. We aim to automatically identify sarcastic and nasty utterances in unannotated online dialogue, extending a bootstrapping method previously applied to the classification of monologic subjective sentences in Riloff and Weibe 2003. We have adapted the method to fit the sarcastic and nasty dialogic domain. Our method is as follows: 1) Explore methods for identifying sarcastic and nasty cue words and phrases in dialogues; 2) Use the learned cues to train a sarcastic (nasty) Cue-Based Classifier; 3) Learn general syntactic extraction patterns from the sarcastic (nasty) utterances and define fine-tuned sarcastic patterns to create a Pattern-Based Classifier; 4) Combine both Cue-Based and fine-tuned Pattern-Based Classifiers to maximize precision at the expense of recall and test on unannotated utterances.