Related papers: Opponent Modeling in Negotiation Dialogues by Rela…

Pre-trained vision-language models learn massive data to model unified representations of images and natural languages, which can be widely applied to downstream machine learning tasks. In addition to zero-shot inference, in order to better…

Augmentation of task-oriented dialogues has followed standard methods used for plain-text such as back-translation, word-level manipulation, and paraphrasing despite its richly annotated structure. In this work, we introduce an augmentation…

Identifying arguments is a necessary prerequisite for various tasks in automated discourse analysis, particularly within contexts such as political debates, online discussions, and scientific reasoning. In addition to theoretical advances…

Overfitting is a phenomenon that occurs when a machine learning model is trained for too long and focused too much on the exact fitness of the training samples to the provided training labels and cannot keep track of the predictive rules…

In applications such as recommendation systems and revenue management, it is important to predict preferences on items that have not been seen by a user or predict outcomes of comparisons among those that have never been compared. A popular…

Modeling dialog as a collaborative activity consists notably in specifying the content of the Conversational Common Ground and the kind of social mental state involved. In previous work (Saget, 2006), we claim that Collective Acceptance is…

With the availability of massive general-domain dialogue data, pre-trained dialogue generation appears to be super appealing to transfer knowledge from the general domain to downstream applications. In most existing work, such transferable…

Policy learning (PL) is a module of a task-oriented dialogue system that trains an agent to make actions in each dialogue turn. Imitating human action is a fundamental problem of PL. However, both supervised learning (SL) and reinforcement…

One of the fundamental skills required for an agent acting in an environment to complete tasks is the ability to understand what actions are plausible at any given point. This work explores a novel use of code representations to reason…

In this thesis, we leverage the neural copy mechanism and memory-augmented neural networks (MANNs) to address existing challenge of neural task-oriented dialogue learning. We show the effectiveness of our strategy by achieving good…

We introduce a novel approach to transformers that learns hierarchical representations in multiparty dialogue. First, three language modeling tasks are used to pre-train the transformers, token- and utterance-level language modeling and…

The recent abundance of conversational data on the Web and elsewhere calls for effective NLP systems for dialog understanding. Complete utterance-level understanding often requires context understanding, defined by nearby utterances. In…

Training the generative models with minimal corpus is one of the critical challenges for building open-domain dialogue systems. Existing methods tend to use the meta-learning framework which pre-trains the parameters on all non-target tasks…

This paper suggests a direction of coreference resolution for online decoding on actively generated input such as dialogue, where the model accepts an utterance and its past context, then finds mentions in the current utterance as well as…

Dialogue data in real scenarios tend to be sparsely available, rendering data-starved end-to-end dialogue systems trained inadequately. We discover that data utilization efficiency in low-resource scenarios can be enhanced by mining…

Implicit discourse relations are not only more challenging to classify, but also to annotate, than their explicit counterparts. We tackle situations where training data for implicit relations are lacking, and exploit domain adaptation from…

Effective interlocutors account for the uncertain goals, beliefs, and emotions of others. But even the best human conversationalist cannot perfectly anticipate the trajectory of a dialogue. How well can language models represent inherent…

An intelligent dialogue system in a multi-turn setting should not only generate the responses which are of good quality, but it should also generate the responses which can lead to long-term success of the dialogue. Although, the current…

Open-domain dialogue generation suffers from the data insufficiency problem due to the vast size of potential responses. In this paper, we propose to explore potential responses by counterfactual reasoning. Given an observed response, the…

The construction of open-domain dialogue systems requires high-quality dialogue datasets. The dialogue data admits a wide variety of responses for a given dialogue history, especially responses with different semantics. However, collecting…