Will Monroe
YOU?
Author Swipe
Large Language Model Augmented Exercise Retrieval for Personalized Language Learning Open
We study the problem of zero-shot exercise retrieval in the context of online language learning, to give learners the ability to explicitly request personalized exercises via natural language. Using real-world data collected from language …
Improving Engineering Education with Enhanced Calibrated Peer Review Assessment of a Collaborative Research Project Open
Improving Engineering Education with Enhanced Calibrated Peer Review – Assessment of a Collaborative Research ProjectCalibrated Peer Review (CPRTM) is an online application that was developed to enable studentsto critically review other st…
Simultaneous Translation and Paraphrase for Language Education Open
We present the task of Simultaneous Translation and Paraphrasing for Language Education (STAPLE). Given a prompt in one language, the goal is to generate a diverse set of correct translations that language learners are likely to produce. T…
IcoRating: A Deep-Learning System for Scam ICO Identification Open
Cryptocurrencies (or digital tokens, digital currencies, e.g., BTC, ETH, XRP, NEO) have been rapidly gaining ground in use, value, and understanding among the public, bringing astonishing profits to investors. Unlike other money and bankin…
Generating Bilingual Pragmatic Color References Open
Contextual influences on language often exhibit substantial cross-lingual regularities; for example, we are more verbose in situations that require finer distinctions. However, these regularities are sometimes obscured by semantic and synt…
View article: Colors in Context: A Pragmatic Neural Model for Grounded Language Understanding
Colors in Context: A Pragmatic Neural Model for Grounded Language Understanding Open
We present a model of pragmatic referring expression interpretation in a grounded communication task (identifying colors from descriptions) that draws upon predictions from two recurrent neural network classifiers, a speaker and a listener…
Colors in Context: A Pragmatic Neural Model for Grounded Language Understanding Open
We present a model of pragmatic referring expression interpretation in a grounded communication task (identifying colors from descriptions) that draws upon predictions from two recurrent neural network classifiers, a speaker and a listener…
Data Distillation for Controlling Specificity in Dialogue Generation Open
People speak at different levels of specificity in different situations. Depending on their knowledge, interlocutors, mood, etc.} A conversational agent should have this ability and know when to be specific and when to be general. We propo…
Learning to Decode for Future Success Open
We introduce a simple, general strategy to manipulate the behavior of a neural decoder that enables it to generate outputs that have specific properties of interest (e.g., sequences of a pre-specified length). The model can be thought of a…
Adversarial Learning for Neural Dialogue Generation Open
In this paper, drawing intuition from the Turing test, we propose using adversarial training for open-domain dialogue generation: the system is trained to produce sequences that are indistinguishable from human-generated dialogue utterance…
Adversarial Learning for Neural Dialogue Generation Open
We apply adversarial training to open-domain dialogue generation, training a system to produce sequences that are indistinguishable from human-generated dialogue utterances. We cast the task as a reinforcement learning problem where we joi…
Understanding Neural Networks through Representation Erasure Open
While neural networks have been successfully applied to many natural language processing tasks, they come at the cost of interpretability. In this paper, we propose a general methodology to analyze and interpret decisions from a neural mod…
A Simple, Fast Diverse Decoding Algorithm for Neural Generation Open
In this paper, we propose a simple, fast decoding algorithm that fosters diversity in neural generation. The algorithm modifies the standard beam search algorithm by adding an inter-sibling ranking penalty, favoring choosing hypotheses fro…
Fitting In or Standing Out? The Tradeoffs of Structural and Cultural Embeddedness Open
A recurring theme in sociological research is the tradeoff between fitting in and standing out. Prior work examining this tension tends to take either a structural or a cultural perspective. We fuse these two traditions to develop a theory…
Deep Reinforcement Learning for Dialogue Generation Open
Recent neural models of dialogue generation offer great promise for generating responses for conversational agents, but tend to be shortsighted, predicting utterances one at a time while ignoring their influence on future outcomes. Modelin…
Learning to Generate Compositional Color Descriptions Open
The production of color language is essential for grounded language generation. Color descriptions have many challenging properties: they can be vague, compositionally complex, and denotationally rich. We present an effective approach to g…
Deep Reinforcement Learning for Dialogue Generation Open
Recent neural models of dialogue generation offer great promise for generating responses for conversational agents, but tend to be shortsighted, predicting utterances one at a time while ignoring their influence on future outcomes.Modeling…