Related papers: Response-Anticipated Memory for On-Demand Knowledg…

Human conversations contain many types of information, e.g., knowledge, common sense, and language habits. In this paper, we propose a conversational word embedding method named PR-Embedding, which utilizes the conversation pairs $…

Prior approaches to realizing mixed-initiative human--computer referential communication have adopted information-state or collaborative problem-solving approaches. In this paper, we argue for a new approach, inspired by coherence-based…

Time is an important aspect of documents and is used in a range of NLP and IR tasks. In this work, we investigate methods for incorporating temporal information during pre-training to further improve the performance on time-related tasks.…

Encoder-decoder based neural architectures serve as the basis of state-of-the-art approaches in end-to-end open domain dialog systems. Since most of such systems are trained with a maximum likelihood~(MLE) objective they suffer from issues…

Recently several datasets have been proposed to encourage research in Question Answering domains where commonsense knowledge is expected to play an important role. Recent language models such as ROBERTA, BERT and GPT that have been…

Pre-trained contextualized embedding models such as BERT are a standard building block in many natural language processing systems. We demonstrate that the sentence-level representations produced by some off-the-shelf contextualized…

In this paper, we focus on learning structure-aware document representations from data without recourse to a discourse parser or additional annotations. Drawing inspiration from recent efforts to empower neural networks with a structural…

Training recurrent neural networks to model long term dependencies is difficult. Hence, we propose to use external linguistic knowledge as an explicit signal to inform the model which memories it should utilize. Specifically, external…

Response generation for task-oriented dialogues implicitly optimizes two objectives at the same time: task completion and language quality. Conditioned response generation serves as an effective approach to separately and better optimize…

There has recently been growing interest in conversational agents with long-term memory which has led to the rapid development of language models that use retrieval-augmented generation (RAG). Until recently, most work on RAG has focused on…

Context modeling plays a critical role in building multi-turn dialogue systems. Conversational Query Rewriting (CQR) aims to simplify the multi-turn dialogue modeling into a single-turn problem by explicitly rewriting the conversational…

Generative language models often struggle with specialized or less-discussed knowledge. A potential solution is found in Retrieval-Augmented Generation (RAG) models which act like retrieving information before generating responses. In this…

We propose a two-stage neural model to tackle question generation from documents. First, our model estimates the probability that word sequences in a document are ones that a human would pick when selecting candidate answers by training a…

Multi-agent reinforcement learning (MARL) extends (single-agent) reinforcement learning (RL) by introducing additional agents and (potentially) partial observability of the environment. Consequently, algorithms for solving MARL problems…

A frequent pattern in customer care conversations is the agents responding with appropriate webpage URLs that address users' needs. We study the task of predicting the documents that customer care agents can use to facilitate users' needs.…

This paper summarizes our work on the first track of the ninth Dialog System Technology Challenge (DSTC 9), "Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access". The goal of the task is to generate…

In dialogue systems, utterances with similar semantics may have distinctive emotions under different contexts. Therefore, modeling long-range contextual emotional relationships with speaker dependency plays a crucial part in dialogue…

Recent advances in conversational systems have changed the search paradigm. Traditionally, a user poses a query to a search engine that returns an answer based on its index, possibly leveraging external knowledge bases and conditioning the…

Longitudinal Dialogues (LD) are the most challenging type of conversation for human-machine dialogue systems. LDs include the recollections of events, personal thoughts, and emotions specific to each individual in a sparse sequence of…

Existing open-domain dialogue generation models are usually trained to mimic the gold response in the training set using cross-entropy loss on the vocabulary. However, a good response does not need to resemble the gold response, since there…