Related papers: Free the Plural: Unrestricted Split-Antecedent Ana…
Coreference resolution, the task of identifying expressions in text that refer to the same entity, is a critical component in various natural language processing applications. This paper presents a novel end-to-end neural coreference…
Recent span-based joint extraction models have demonstrated significant advantages in both entity recognition and relation extraction. These models treat text spans as candidate entities, and span pairs as candidate relationship tuples,…
Foundational models such as the Segment Anything Model (SAM) are gaining traction in medical imaging segmentation, supporting multiple downstream tasks. However, such models are supervised in nature, still relying on large annotated…
In this paper, we present an accurate and extensible approach for the coreference resolution task. We formulate the problem as a span prediction task, like in machine reading comprehension (MRC): A query is generated for each candidate…
Pre-trained models have brought significant improvements to many NLP tasks and have been extensively analyzed. But little is known about the effect of fine-tuning on specific tasks. Intuitively, people may agree that a pre-trained model…
Machine translation systems achieve near human-level performance on some languages, yet their effectiveness strongly relies on the availability of large amounts of parallel sentences, which hinders their applicability to the majority of…
Through prompting, large-scale pre-trained models have become more expressive and powerful, gaining significant attention in recent years. Though these big models have zero-shot capabilities, in general, labeled data are still required to…
The performance of automatic speech recognition systems degrades with increasing mismatch between the training and testing scenarios. Differences in speaker accents are a significant source of such mismatch. The traditional approach to deal…
Previous attempts to incorporate a mention detection step into end-to-end neural coreference resolution for English have been hampered by the lack of singleton mention span data as well as other entity information. This paper presents a…
Verbal omissions are complex syntactic phenomena in VP coordination structures. They occur when verbs and (some of) their arguments are omitted from subsequent clauses after being explicitly stated in an initial clause. Recovering these…
Recent work has shown that language models' (LMs) prompt-based learning capabilities make them well suited for automating data labeling in domains where manual annotation is expensive. The challenge is that while writing an initial prompt…
Most reward models for visual generation reduce rich human judgments to a single unexplained score, discarding the reasoning that underlies preference. We show that teaching reward models to produce explicit, multi-dimensional critiques…
We propose to constrain segmentation functionals with a dimensionless, unbiased and position-independent shape compactness prior, which we solve efficiently with an alternating direction method of multipliers (ADMM). Involving a squared sum…
Ontonotes has served as the most important benchmark for coreference resolution. However, for ease of annotation, several long documents in Ontonotes were split into smaller parts. In this work, we build a corpus of coreference-annotated…
We present the first openly available multimodal metaphor annotated corpus. The corpus consists of videos including audio and subtitles that have been annotated by experts. Furthermore, we present a method for detecting metaphors in the new…
Automatic readability assessment (ARA) is the task of evaluating the level of ease or difficulty of text documents for a target audience. For researchers, one of the many open problems in the field is to make such models trained for the…
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…
Fine-tuning BERT-based models is resource-intensive in memory, computation, and time. While many prior works aim to improve inference efficiency via compression techniques, e.g., pruning, these works do not explicitly address the…
Pre-trained contextual representations like BERT have achieved great success in natural language processing. However, the sentence embeddings from the pre-trained language models without fine-tuning have been found to poorly capture…
Metaphors are ubiquitous in human language. The metaphor detection task (MD) aims at detecting and interpreting metaphors from written language, which is crucial in natural language understanding (NLU) research. In this paper, we introduce…