Related papers: The World is Not Binary: Learning to Rank with Gra…

The recent history of machine learning research has taught us that machine learning methods can be most effective when they are provided with very large, high-capacity models, and trained on very large and diverse datasets. This has spurred…

Responding with knowledge has been recognized as an important capability for an intelligent conversational agent. Yet knowledge-grounded dialogues, as training data for learning such a response generation model, are difficult to obtain.…

Nonstationarity is ubiquitous in practical classification settings, leading deployed models to perform poorly even when they generalize well to holdout sets available at training time. We address this by reframing nonstationary…

Rich, open-domain textual data available on the web resulted in great advancements for language processing. However, while that data may be suitable for language processing tasks, they are mostly non-conversational, lacking many phenomena…

Most efforts in interpreting neural relevance models have focused on local explanations, which explain the relevance of a document to a query but are not useful in predicting the model's behavior on unseen query-document pairs. We propose a…

Pre-ranking is a critical stage in industrial recommendation systems, tasked with efficiently scoring thousands of recalled items for downstream ranking. A key challenge is the train-serving discrepancy: pre-ranking models are trained only…

Speaker recognition, recognizing speaker identities based on voice alone, enables important downstream applications, such as personalization and authentication. Learning speaker representations, in the context of supervised learning,…

Conversation disentanglement aims to separate intermingled messages into detached sessions, which is a fundamental task in understanding multi-party conversations. Existing work on conversation disentanglement relies heavily upon…

Learning to rank has been intensively studied and widely applied in information retrieval. Typically, a global ranking function is learned from a set of labeled data, which can achieve good performance on average but may be suboptimal for…

In precision-oriented tasks like answer ranking, it is more important to rank many relevant answers highly than to retrieve all relevant answers. It follows that a good ranking strategy would be to learn how to identify the easiest correct…

Current neural network-based conversational models lack diversity and generate boring responses to open-ended utterances. Priors such as persona, emotion, or topic provide additional information to dialog models to aid response generation,…

Multiple choice benchmarks have long been the workhorse of language model evaluation because grading multiple choice is objective and easy to automate. However, we show multiple choice questions from popular benchmarks can often be answered…

Automatic evaluation of open-domain dialogue response generation is very challenging because there are many appropriate responses for a given context. Existing evaluation models merely compare the generated response with the ground truth…

Generating explanations for neural networks has become crucial for their applications in real-world with respect to reliability and trustworthiness. In natural language processing, existing methods usually provide important features which…

Training accurate classifiers requires many labels, but each label provides only limited information (one bit for binary classification). In this work, we propose BabbleLabble, a framework for training classifiers in which an annotator…

While neural conversation models have shown great potentials towards generating informative and engaging responses via introducing external knowledge, learning such a model often requires knowledge-grounded dialogues that are difficult to…

We investigate response selection for multi-turn conversation in retrieval-based chatbots. Existing studies pay more attention to the matching between utterances and responses by calculating the matching score based on learned features,…

In recent years, representation learning has become the research focus of the machine learning community. Large-scale neural networks are a crucial step toward achieving general intelligence, with their success largely attributed to their…

Open domain conversational agents can answer a broad range of targeted queries. However, the sequential nature of interaction with these systems makes knowledge exploration a lengthy task which burdens the user with asking a chain of well…

Binary relevance is a simple approach to solve multi-label learning problems where an independent binary classifier is built per each label. A common challenge with this in real-world applications is that the label space can be very large,…