Related papers: Solving Hard Coreference Problems
All state-of-the-art coreference resolution (CR) models involve finetuning a pretrained language model. Whether the superior performance of one CR model over another is due to the choice of language model or other factors, such as the…
Singleton mentions, i.e.~entities mentioned only once in a text, are important to how humans understand discourse from a theoretical perspective. However previous attempts to incorporate their detection in end-to-end neural coreference…
Syntax has been shown to benefit Coreference Resolution from incorporating long-range dependencies and structured information captured by syntax trees, either in traditional statistical machine learning based systems or recently proposed…
Entity coreference resolution is an important research problem with many applications, including information extraction and question answering. Coreference resolution for English has been studied extensively. However, there is relatively…
Retrieval-Augmented Generation (RAG) has emerged as a crucial framework in natural language processing (NLP), improving factual consistency and reducing hallucinations by integrating external document retrieval with large language models…
Pronouns are frequently omitted in pro-drop languages, such as Chinese, generally leading to significant challenges with respect to the production of complete translations. Recently, Wang et al. (2018) proposed a novel reconstruction-based…
We propose a new method for learning word representations using hierarchical regularization in sparse coding inspired by the linguistic study of word meanings. We show an efficient learning algorithm based on stochastic proximal methods…
In spite of great advancements of machine reading comprehension (RC), existing RC models are still vulnerable and not robust to different types of adversarial examples. Neural models over-confidently predict wrong answers to semantic…
Existing approaches for Chinese zero pronoun resolution overlook semantic information. This is because zero pronouns have no descriptive information, which results in difficulty in explicitly capturing their semantic similarities with…
One major deficiency of most semantic representation techniques is that they usually model a word type as a single point in the semantic space, hence conflating all the meanings that the word can have. Addressing this issue by learning…
Language representation models such as BERT could effectively capture contextual semantic information from plain text, and have been proved to achieve promising results in lots of downstream NLP tasks with appropriate fine-tuning. However,…
Although information extraction and coreference resolution appear together in many applications, most current systems perform them as ndependent steps. This paper describes an approach to integrated inference for extraction and coreference…
Exactly solving first-order constraints (i.e., first-order formulas over a certain predefined structure) can be a very hard, or even undecidable problem. In continuous structures like the real numbers it is promising to compute approximate…
Solving NP-hard/complete combinatorial problems with neural networks is a challenging research area that aims to surpass classical approximate algorithms. The long-term objective is to outperform hand-designed heuristics for…
Large language models have been widely adopted in natural language processing, yet they face the challenge of generating unreliable content. Recent works aim to reduce misinformation and hallucinations by resorting to attribution as a means…
Coreference evaluation metrics are hard to optimize directly as they are non-differentiable functions, not easily decomposable into elementary decisions. Consequently, most approaches optimize objectives only indirectly related to the end…
Coreference resolution has been mostly investigated within a single document scope, showing impressive progress in recent years based on end-to-end models. However, the more challenging task of cross-document (CD) coreference resolution…
Document retrieval has been an important research problem over many years in the information retrieval community. State-of-the-art techniques utilize various methods in matching documents to a given document including keywords, phrases, and…
Toponym Resolution, the task of assigning a location mention in a document to a geographic referent (i.e., latitude/longitude), plays a pivotal role in analyzing location-aware content. However, the ambiguities of natural language and a…
Large language models internalize enormous parametric knowledge during pre-training. Concurrently, realistic applications necessitate external contextual knowledge to aid models on the underlying tasks. This raises a crucial dilemma known…