Related papers: On Incorporating Structural Information to improve…

Existing dialog datasets contain a sequence of utterances and responses without any explicit background knowledge associated with them. This has resulted in the development of models which treat conversation as a sequence-to-sequence…

Image-text matching has received growing interest since it bridges vision and language. The key challenge lies in how to learn correspondence between image and text. Existing works learn coarse correspondence based on object co-occurrence…

Dialogue structure discovery is essential in dialogue generation. Well-structured topic flow can leverage background information and predict future topics to help generate controllable and explainable responses. However, most previous work…

Visual storytelling is a creative and challenging task, aiming to automatically generate a story-like description for a sequence of images. The descriptions generated by previous visual storytelling approaches lack coherence because they…

Pretraining deep language models has led to large performance gains in NLP. Despite this success, Schick and Sch\"utze (2020) recently showed that these models struggle to understand rare words. For static word embeddings, this problem has…

Recently, graph neural networks (GNNs) have been widely used for document classification. However, most existing methods are based on static word co-occurrence graphs without sentence-level information, which poses three challenges:(1) word…

This paper contains what the Georgetown InfoSense group has done in regard to solving the challenges presented by TREC iKAT 2023. Our submitted runs outperform the median runs by a significant margin, exhibiting superior performance in nDCG…

Recent advances in pre-trained language models have significantly improved neural response generation. However, existing methods usually view the dialogue context as a linear sequence of tokens and learn to generate the next word through…

Contextualized representations from a pre-trained language model are central to achieve a high performance on downstream NLP task. The pre-trained BERT and A Lite BERT (ALBERT) models can be fine-tuned to give state-ofthe-art results in…

Graph-based Aspect-based Sentiment Classification (ABSC) approaches have yielded state-of-the-art results, expecially when equipped with contextual word embedding from pre-training language models (PLMs). However, they ignore sequential…

It has been shown that named entity recognition (NER) could benefit from incorporating the long-distance structured information captured by dependency trees. We believe this is because both types of features - the contextual information…

It is always well believed that modeling relationships between objects would be helpful for representing and eventually describing an image. Nevertheless, there has not been evidence in support of the idea on image description generation.…

With the rapid development of information technology, online platforms (e.g., news portals and social media) generate enormous web information every moment. Therefore, it is crucial to extract structured representations of events from…

Predicting an interaction before it is fully executed is very important in applications such as human-robot interaction and video surveillance. In a two-human interaction scenario, there often contextual dependency structure between the…

We present a novel response generation system that can be trained end to end on large quantities of unstructured Twitter conversations. A neural network architecture is used to address sparsity issues that arise when integrating contextual…

Long document question answering is a challenging task due to its demands for complex reasoning over long text. Previous works usually take long documents as non-structured flat texts or only consider the local structure in long documents.…

Modern generative pre-trained language models excel at open-ended text generation, yet continue to underperform on structure-related tasks such as NER, relation extraction, and semantic role labeling, especially when compared to…

Existing neural models for dialogue response generation assume that utterances are sequentially organized. However, many real-world dialogues involve multiple interlocutors (i.e., multi-party dialogues), where the assumption does not hold…

Identifying controversial posts on social media is a fundamental task for mining public sentiment, assessing the influence of events, and alleviating the polarized views. However, existing methods fail to 1) effectively incorporate the…

Contextualized word embeddings can lead to state-of-the-art performances in natural language understanding. Recently, a pre-trained deep contextualized text encoder such as BERT has shown its potential in improving natural language tasks…