8 accepted papers
The term Language Models (LMs) as a time-specific collection of models of interest is constantly reinvented, with its referents updated much like the *Ship of Theseus* replaces its parts but remains the same ship in essence. In this paper, we investigate this *Ship of Language Models* problem, where…
This paper aims to suppress mainlobe deceptive jammers considering the multipath effect in a frequency diverse array-multiple-input multiple-output (FDA-MIMO) radar. At the problem formulation stage, the overall received signal including the true target, main-lobe deceptive jammers, and burst jammin…
Annotation quality is often framed as post-hoc cleanup of annotator-caused issues. This position paper discusses whether, how, and why this narrative limits the scope of improving annotation. We call to consider annotation as a procedural collaboration, outlining three points in this direction:(1) A…
Event temporal relation extraction (ETRE) is usually formulated as a multi-label classification task, where each type of relation is simply treated as a one-hot label. This formulation ignores the meaning of relations and wipes out their intrinsic dependency. After examining the relation definitions…
This paper deals with the problem of Doppler ambiguity in a frequency diverse array (FDA) multiple-input and multiple-output (MIMO) radar. In our modeling stage, a spread phase alignment (SPA) method is proposed by utilizing the pulse-dependent transmit spatial frequency. In this respect, the Dopple…
DocRED is a widely used dataset for document-level relation extraction. In the large-scale annotation, a recommend-revise scheme is adopted to reduce the workload. Within this scheme, annotators are provided with candidate relation instances from distant supervision, and they then manually supplemen…
Recent studies strive to incorporate various human rationales into neural networks to improve model performance, but few pay attention to the quality of the rationales. Most existing methods distribute their models’ focus to distantly-labeled rationale words entirely and equally, while ignoring the…
Document-level Relation Extraction (RE) is a more challenging task than sentence RE as it often requires reasoning over multiple sentences. Yet, human annotators usually use a small number of sentences to identify the relationship between a given entity pair. In this paper, we present an embarrassin…