Amita Misra

Pratyay Banerjee, Masud Moshtaghi, Shivashankar Subramanian et al.

Large language models still struggle with reliable long-term conversational memory: simply enlarging context windows or applying naive retrieval often introduces noise and destabilizes responses. We present APEX-MEM, a conversational memory system that combines three key innovations: (1) a property graph which uses domain-agnostic ontology to structure conversations as temporally grounded events in an entity-centric framework, (2) append-only storage that preserves the full temporal evolution of information, and (3) a multi-tool retrieval agent that understands and resolves conflicting or evolving information at query time, producing a compact and contextually relevant memory summary. This retrieval-time resolution preserves the full interaction history while suppressing irrelevant details. APEX-MEM achieves 88.88% accuracy on LOCOMO's Question Answering task and 86.2% on LongMemEval, outperforming state-of-the-art session-aware approaches and demonstrating that structured property graphs enable more temporally coherent long-term conversational reasoning.

Bryan Zhang, Amita Misra

Previous work suggests that performance of cross-lingual information retrieval correlates highly with the quality of Machine Translation. However, there may be a threshold beyond which improving query translation quality yields little or no benefit to further improve the retrieval performance. This threshold may depend upon multiple factors including the source and target languages, the existing MT system quality and the search pipeline. In order to identify the benefit of improving an MT system for a given search pipeline, we investigate the sensitivity of retrieval quality to the presence of different levels of MT quality using experimental datasets collected from actual traffic. We systematically improve the performance of our MT systems quality on language pairs as measured by MT evaluation metrics including Bleu and Chrf to determine their impact on search precision metrics and extract signals that help to guide the improvement strategies. Using this information we develop techniques to compare query translations for multiple language pairs and identify the most promising language pairs to invest and improve.

Vaibhav Kumar, Hana Koorehdavoudi, Masud Moshtaghi et al.

We propose CHRT (Control Hidden Representation Transformation) - a controlled language generation framework that steers large language models to generate text pertaining to certain attributes (such as toxicity). CHRT gains attribute control by modifying the hidden representation of the base model through learned transformations. We employ a contrastive-learning framework to learn these transformations that can be combined to gain multi-attribute control. The effectiveness of CHRT is experimentally shown by comparing it with seven baselines over three attributes. CHRT outperforms all the baselines in the task of detoxification, positive sentiment steering, and text simplification while minimizing the loss in linguistic qualities. Further, our approach has the lowest inference latency of only 0.01 seconds more than the base model, making it the most suitable for high-performance production environments. We open-source our code and release two novel datasets to further propel controlled language generation research.

Amita Misra, Zhe Liu, Jalal Mahmud

Customers of machine learning systems demand accountability from the companies employing these algorithms for various prediction tasks. Accountability requires understanding of system limit and condition of erroneous predictions, as customers are often interested in understanding the incorrect predictions, and model developers are absorbed in finding methods that can be used to get incremental improvements to an existing system. Therefore, we propose an accountable error characterization method, AEC, to understand when and where errors occur within the existing black-box models. AEC, as constructed with human-understandable linguistic features, allows the model developers to automatically identify the main sources of errors for a given classification system. It can also be used to sample for the set of most informative input points for a next round of training. We perform error detection for a sentiment analysis task using AEC as a case study. Our results on the sample sentiment task show that AEC is able to characterize erroneous predictions into human understandable categories and also achieves promising results on selecting erroneous samples when compared with the uncertainty-based sampling.

Yash Bhalgat, Zhe Liu, Pritam Gundecha et al.

Given that labeled data is expensive to obtain in real-world scenarios, many semi-supervised algorithms have explored the task of exploitation of unlabeled data. Traditional tri-training algorithm and tri-training with disagreement have shown promise in tasks where labeled data is limited. In this work, we introduce a new paradigm for tri-training, mimicking the real world teacher-student learning process. We show that the adaptive teacher-student thresholds used in the proposed method provide more control over the learning process with higher label quality. We perform evaluation on SemEval sentiment analysis task and provide comprehensive comparisons over experimental settings containing varied labeled versus unlabeled data rates. Experimental results show that our method outperforms other strong semi-supervised baselines, while requiring less number of labeled training samples.

Amita Misra, Mansurul Bhuiyan, Jalal Mahmud et al.

Twitter customer service interactions have recently emerged as an effective platform to respond and engage with customers. In this work, we explore the role of negation in customer service interactions, particularly applied to sentiment analysis. We define rules to identify true negation cues and scope more suited to conversational data than existing general review data. Using semantic knowledge and syntactic structure from constituency parse trees, we propose an algorithm for scope detection that performs comparable to state of the art BiLSTM. We further investigate the results of negation scope detection for the sentiment prediction task on customer service conversation data using both a traditional SVM and a Neural Network. We propose an antonym dictionary based method for negation applied to a CNN-LSTM combination model for sentiment analysis. Experimental results show that the antonym-based method outperforms the previous lexicon-based and neural network methods.

Mansurul Bhuiyan, Amita Misra, Saurabh Tripathy et al.

In the last several years, Twitter is being adopted by the companies as an alternative platform to interact with the customers to address their concerns. With the abundance of such unconventional conversation resources, push for developing effective virtual agents is more than ever. To address this challenge, a better understanding of such customer service conversations is required. Lately, there have been several works proposing a novel taxonomy for fine-grained dialogue acts as well as develop algorithms for automatic detection of these acts. The outcomes of these works are providing stepping stones for the ultimate goal of building efficient and effective virtual agents. But none of these works consider handling the notion of negation into the proposed algorithms. In this work, we developed an SVM-based dialogue acts prediction algorithm for Twitter customer service conversations where negation handling is an integral part of the end-to-end solution. For negation handling, we propose several efficient heuristics as well as adopt recent state-of- art third party machine learning based solutions. Empirically we show model's performance gain while handling negation compared to when we don't. Our experiments show that for the informal text such as tweets, the heuristic-based approach is more effective.

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.

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

In this paper we introduce a novel, open domain socialbot for the Amazon Alexa Prize competition, aimed at carrying on friendly conversations with users on a variety of topics. We present our modular system, highlighting our different data sources and how we use the human mind as a model for data management. Additionally we build and employ natural language understanding and information retrieval tools and APIs to expand our knowledge bases. We describe our semistructured, scalable framework for crafting topic-specific dialogue flows, and give details on our dialogue management schemes and scoring mechanisms. Finally we briefly evaluate the performance of our system and observe the challenges that an open domain socialbot faces.

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.

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

The greatest challenges in building sophisticated open-domain conversational agents arise directly from the potential for ongoing mixed-initiative multi-turn dialogues, which do not follow a particular plan or pursue a particular fixed information need. In order to make coherent conversational contributions in this context, a conversational agent must be able to track the types and attributes of the entities under discussion in the conversation and know how they are related. In some cases, the agent can rely on structured information sources to help identify the relevant semantic relations and produce a turn, but in other cases, the only content available comes from search, and it may be unclear which semantic relations hold between the search results and the discourse context. A further constraint is that the system must produce its contribution to the ongoing conversation in real-time. This paper describes our experience building SlugBot for the 2017 Alexa Prize, and discusses how we leveraged search and structured data from different sources to help SlugBot produce dialogic turns and carry on conversations whose length over the semi-finals user evaluation period averaged 8:17 minutes.

Shereen Oraby, Vrindavan Harrison, Amita Misra et al.

Effective models of social dialog must understand a broad range of rhetorical and figurative devices. Rhetorical questions (RQs) are a type of figurative language whose aim is to achieve a pragmatic goal, such as structuring an argument, being persuasive, emphasizing a point, or being ironic. While there are computational models for other forms of figurative language, rhetorical questions have received little attention to date. We expand a small dataset from previous work, presenting a corpus of 10,270 RQs from debate forums and Twitter that represent different discourse functions. We show that we can clearly distinguish between RQs and sincere questions (0.76 F1). We then show that RQs can be used both sarcastically and non-sarcastically, observing that non-sarcastic (other) uses of RQs are frequently argumentative in forums, and persuasive in tweets. We present experiments to distinguish between these uses of RQs using SVM and LSTM models that represent linguistic features and post-level context, achieving results as high as 0.76 F1 for "sarcastic" and 0.77 F1 for "other" in forums, and 0.83 F1 for both "sarcastic" and "other" in tweets. We supplement our quantitative experiments with an in-depth characterization of the linguistic variation in RQs.

Kevin K. Bowden, Shereen Oraby, Amita Misra et al.

In order to build dialogue systems to tackle the ambitious task of holding social conversations, we argue that we need a data driven approach that includes insight into human conversational chit chat, and which incorporates different natural language processing modules. Our strategy is to analyze and index large corpora of social media data, including Twitter conversations, online debates, dialogues between friends, and blog posts, and then to couple this data retrieval with modules that perform tasks such as sentiment and style analysis, topic modeling, and summarization. We aim for personal assistants that can learn more nuanced human language, and to grow from task-oriented agents to more personable social bots.

Geetanjali Rakshit, Kevin K. Bowden, Lena Reed et al.

Chatbots are a rapidly expanding application of dialogue systems with companies switching to bot services for customer support, and new applications for users interested in casual conversation. One style of casual conversation is argument, many people love nothing more than a good argument. Moreover, there are a number of existing corpora of argumentative dialogues, annotated for agreement and disagreement, stance, sarcasm and argument quality. This paper introduces Debbie, a novel arguing bot, that selects arguments from conversational corpora, and aims to use them appropriately in context. We present an initial working prototype of Debbie, with some preliminary evaluation and describe future work.

Amita Misra, Brian Ecker, Marilyn A. Walker

When people converse about social or political topics, similar arguments are often paraphrased by different speakers, across many different conversations. Debate websites produce curated summaries of arguments on such topics; these summaries typically consist of lists of sentences that represent frequently paraphrased propositions, or labels capturing the essence of one particular aspect of an argument, e.g. Morality or Second Amendment. We call these frequently paraphrased propositions ARGUMENT FACETS. Like these curated sites, our goal is to induce and identify argument facets across multiple conversations, and produce summaries. However, we aim to do this automatically. We frame the problem as consisting of two steps: we first extract sentences that express an argument from raw social media dialogs, and then rank the extracted arguments in terms of their similarity to one another. Sets of similar arguments are used to represent argument facets. We show here that we can predict ARGUMENT FACET SIMILARITY with a correlation averaging 0.63 compared to a human topline averaging 0.68 over three debate topics, easily beating several reasonable baselines.

Amita Misra, Brian Ecker, Theodore Handleman et al.

Stance classification aims to identify, for a particular issue under discussion, whether the speaker or author of a conversational turn has Pro (Favor) or Con (Against) stance on the issue. Detecting stance in tweets is a new task proposed for SemEval-2016 Task6, involving predicting stance for a dataset of tweets on the topics of abortion, atheism, climate change, feminism and Hillary Clinton. Given the small size of the dataset, our team created our own topic-specific training corpus by developing a set of high precision hashtags for each topic that were used to query the twitter API, with the aim of developing a large training corpus without additional human labeling of tweets for stance. The hashtags selected for each topic were predicted to be stance-bearing on their own. Experimental results demonstrate good performance for our features for opinion-target pairs based on generalizing dependency features using sentiment lexicons.

Amita Misra, Pranav Anand, Jean E Fox Tree et al.

More and more of the information available on the web is dialogic, and a significant portion of it takes place in online forum conversations about current social and political topics. We aim to develop tools to summarize what these conversations are about. What are the CENTRAL PROPOSITIONS associated with different stances on an issue, what are the abstract objects under discussion that are central to a speaker's argument? How can we recognize that two CENTRAL PROPOSITIONS realize the same FACET of the argument? We hypothesize that the CENTRAL PROPOSITIONS are exactly those arguments that people find most salient, and use human summarization as a probe for discovering them. We describe our corpus of human summaries of opinionated dialogs, then show how we can identify similar repeated arguments, and group them into FACETS across many discussions of a topic. We define a new task, ARGUMENT FACET SIMILARITY (AFS), and show that we can predict AFS with a .54 correlation score, versus an ngram system baseline of .39 and a semantic textual similarity system baseline of .45.

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%.