Related papers: Enhanced Knowledge Selection for Grounded Dialogue…
Commonsense question answering aims to answer questions which require background knowledge that is not explicitly expressed in the question. The key challenge is how to obtain evidence from external knowledge and make predictions based on…
In order to facilitate natural language understanding, the key is to engage commonsense or background knowledge. However, how to engage commonsense effectively in question answering systems is still under exploration in both research…
The use of knowledge graphs for grounding agents in real-world Q&A applications has become increasingly common. Answering complex queries often requires multi-hop reasoning and the ability to navigate vast relational structures. Standard…
Multi-document summarization is a process of automatic generation of a compressed version of the given collection of documents. Recently, the graph-based models and ranking algorithms have been actively investigated by the extractive…
With the emerging branch of incorporating factual knowledge into pre-trained language models such as BERT, most existing models consider shallow, static, and separately pre-trained entity embeddings, which limits the performance gains of…
The task of completing knowledge triplets has broad downstream applications. Both structural and semantic information plays an important role in knowledge graph completion. Unlike previous approaches that rely on either the structures or…
Given unstructured text, Large Language Models (LLMs) are adept at answering simple (single-hop) questions. However, as the complexity of the questions increase, the performance of LLMs degrade. We believe this is due to the overhead…
Most generative document models act on bag-of-words input in an attempt to focus on the semantic content and thereby partially forego syntactic information. We argue that it is preferable to keep the original word order intact and…
Labeled property graphs often contain rich textual attributes that can enhance analytical tasks when properly leveraged. This work explores the use of pretrained text embedding models to enable efficient semantic analysis in such graphs. By…
Recent advancements in text-attributed graphs (TAGs) have significantly improved the quality of node features by using the textual modeling capabilities of language models. Despite this success, utilizing text attributes to enhance the…
The extraction of information from semi-structured text, such as resumes, has long been a challenge due to the diverse formatting styles and subjective content organization. Conventional solutions rely on specialized logic tailored for…
Relation extraction task is a crucial and challenging aspect of Natural Language Processing. Several methods have surfaced as of late, exhibiting notable performance in addressing the task; however, most of these approaches rely on vast…
In recent years, the size of big linked data has grown rapidly and this number is still rising. Big linked data and knowledge bases come from different domains such as life sciences, publications, media, social web, and so on. However, with…
LLMs are frequently used tools for conversational generation. Without additional information LLMs can generate lower quality responses due to lacking relevant content and hallucinations, as well as the perception of poor emotional…
Static knowledge graph has been incorporated extensively into sequence-to-sequence framework for text generation. While effectively representing structured context, static knowledge graph failed to represent knowledge evolution, which is…
We study knowledge-grounded dialogue generation with pre-trained language models. To leverage the redundant external knowledge under capacity constraint, we propose equipping response generation defined by a pre-trained language model with…
While neural networks have been used extensively to make substantial progress in the machine translation task, they are known for being heavily dependent on the availability of large amounts of training data. Recent efforts have tried to…
Semantic Textual Relatedness (STR) captures nuanced relationships between texts that extend beyond superficial lexical similarity. In this study, we investigate STR in the context of job title matching - a key challenge in resume…
Advances in Visually Rich Document Understanding (VrDU) have enabled information extraction and question answering over documents with complex layouts. Two tropes of architectures have emerged -- transformer-based models inspired by LLMs,…
Language Models (LMs) continue to advance, improving response quality and coherence. Given Internet-scale training datasets, LMs have likely encountered much of what users may ask them to generate in some form during their training. A…