Related papers: MDC-R: The Minecraft Dialogue Corpus with Referenc…
Response ranking in dialogues plays a crucial role in retrieval-based conversational systems. In a multi-turn dialogue, to capture the gist of a conversation, contextual information serves as essential knowledge to achieve this goal. In…
Conversational recommender systems (CRS) that are able to interact with users in natural language often utilize recommendation dialogs which were previously collected with the help of paired humans, where one plays the role of a seeker and…
Enhancing AI systems with efficient communication skills for effective human assistance necessitates proactive initiatives from the system side to discern specific circumstances and interact aptly. This research focuses on a collective…
Recent multimodal large language models (MLLMs) have demonstrated significant potential in open-ended conversation, generating more accurate and personalized responses. However, their abilities to memorize, recall, and reason in sustained…
Chat dialogues contain considerable useful information about a speaker's interests, preferences, and experiences.Thus, knowledge from open-domain chat dialogue can be used to personalize various systems and offer recommendations for…
Conversational Machine Comprehension (CMC), a research track in conversational AI, expects the machine to understand an open-domain natural language text and thereafter engage in a multi-turn conversation to answer questions related to the…
Multiple different responses are often plausible for a given open domain dialog context. Prior work has shown the importance of having multiple valid reference responses for meaningful and robust automated evaluations. In such cases, common…
Bundle recommender systems recommend sets of items (e.g., pants, shirt, and shoes) to users, but they often suffer from two issues: significant interaction sparsity and a large output space. In this work, we extend multi-round…
Research into the area of multiparty dialog has grown considerably over recent years. We present the Molweni dataset, a machine reading comprehension (MRC) dataset with discourse structure built over multiparty dialog. Molweni's source…
Discourse-annotated corpora are an important resource for the community, but they are often annotated according to different frameworks. This makes comparison of the annotations difficult, thereby also preventing researchers from searching…
Conversational recommendation systems (CRS) leverage contextual information from conversations to generate recommendations but often struggle due to a lack of collaborative filtering (CF) signals, which capture user-item interaction…
In \citep{andreas2020task-oriented}, a dataflow (DF) based dialogue system was introduced, showing clear advantages compared to many commonly used current systems. This was accompanied by the release of SMCalFlow, a practically relevant,…
Multiparty Dialogue Machine Reading Comprehension (MRC) differs from traditional MRC as models must handle the complex dialogue discourse structure, previously unconsidered in traditional MRC. To fully exploit such discourse structure in…
Retrieval-based conversational systems learn to rank response candidates for a given dialogue context by computing the similarity between their vector representations. However, training on a single textual form of the multi-turn context…
Multiturn dialogue models aim to generate human-like responses by leveraging conversational context, consisting of utterances from previous exchanges. Existing methods often neglect the interactions between these utterances or treat all of…
We present a method for inducing new dialogue systems from very small amounts of unannotated dialogue data, showing how word-level exploration using Reinforcement Learning (RL), combined with an incremental and semantic grammar - Dynamic…
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…
In this document we describe a rationale for a research program aimed at building an open "assistant" in the game Minecraft, in order to make progress on the problems of natural language understanding and learning from dialogue.
Annotations allow users to associate additional information with existing resources. Using proprietary and closed systems on the Web, users are already able to annotate multimedia resources such as images, audio and video. So far, however,…
Automatic open-domain dialogue evaluation is a crucial component of dialogue systems. Recently, learning-based evaluation metrics have achieved state-of-the-art performance in open-domain dialogue evaluation. However, these metrics, which…