Related papers: DialAug: Mixing up Dialogue Contexts in Contrastiv…
Deep neural networks have shown recent promise in many language-related tasks such as the modeling of conversations. We extend RNN-based sequence to sequence models to capture the long range discourse across many turns of conversation. We…
Visual storytelling systems generate multi-sentence stories from image sequences. In this task, capturing contextual information and bridging visual variation bring additional challenges. We propose a simple yet effective framework that…
Retrieval-augmented Neural Machine Translation models have been successful in many translation scenarios. Different from previous works that make use of mutually similar but redundant translation memories~(TMs), we propose a new…
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…
Visual Dialog aims to answer multi-round, interactive questions based on the dialog history and image content. Existing methods either consider answer ranking and generating individually or only weakly capture the relation across the two…
Topic-controlled summarisation enables users to generate summaries focused on specific aspects of source documents. This paper investigates a data augmentation strategy for training small language models (sLMs) to perform topic-controlled…
Large language models (LLMs) encode vast world knowledge in their parameters, yet they remain fundamentally limited by static knowledge, finite context windows, and weakly structured causal reasoning. This survey provides a unified account…
Selecting an appropriate response from many candidates given the utterances in a multi-turn dialogue is the key problem for a retrieval-based dialogue system. Existing work formalizes the task as matching between the utterances and a…
Recent advances in deep neural networks, language modeling and language generation have introduced new ideas to the field of conversational agents. As a result, deep neural models such as sequence-to-sequence, Memory Networks, and the…
In this work, we propose contextual language models that incorporate dialog level discourse information into language modeling. Previous works on contextual language model treat preceding utterances as a sequence of inputs, without…
The training of task-oriented dialogue systems is often confronted with the lack of annotated data. In contrast to previous work which augments training data through expensive crowd-sourcing efforts, we propose four different automatic…
Large Language Models (LLMs) often experience performance degradation during long-running interactions due to increasing context length, memory saturation, and computational overhead. This paper presents an adaptive context compression…
Aiming at answering questions based on the content of remotely sensed images, visual question answering for remote sensing data (RSVQA) has attracted much attention nowadays. However, previous works in RSVQA have focused little on the…
Incorporating external knowledge is crucial for knowledge-intensive tasks, such as question answering and fact checking. However, language models (LMs) may ignore relevant information that contradicts outdated parametric memory or be…
We investigate the task of modeling open-domain, multi-turn, unstructured, multi-participant, conversational dialogue. We specifically study the effect of incorporating different elements of the conversation. Unlike previous efforts, which…
Automatic data augmentation (AutoAugment) (Cubuk et al., 2019) searches for optimal perturbation policies via a controller trained using performance rewards of a sampled policy on the target task, hence reducing data-level model bias. While…
Recent advances in open-domain dialogue systems rely on the success of neural models that are trained on large-scale data. However, collecting large-scale dialogue data is usually time-consuming and labor-intensive. To address this data…
Multimodal emotion recognition in conversation (MERC) seeks to identify the speakers' emotions expressed in each utterance, offering significant potential across diverse fields. The challenge of MERC lies in balancing speaker modeling and…
Sequential recommendation addresses the issue of preference drift by predicting the next item based on the user's previous behaviors. Recently, a promising approach using contrastive learning has emerged, demonstrating its effectiveness in…
Recent studies in dialogue state tracking (DST) leverage historical information to determine states which are generally represented as slot-value pairs. However, most of them have limitations to efficiently exploit relevant context due to…