no code implementations • ACL (IWPT) 2021 • Aditya Bhargava, Gerald Penn
In this paper, we present the first statistical parser for Lambek categorial grammar (LCG), a grammatical formalism for which the graphical proof method known as *proof nets* is applicable.
no code implementations • NAACL (TextGraphs) 2021 • Jinman Zhao, Gerald Penn, Huan Ling
In this paper, we define an abstract task called structural realization that generates words given a prefix of words and a partial representation of a parse tree.
1 code implementation • NAACL (SMM4H) 2021 • Jingcheng Niu, Erin Rees, Victoria Ng, Gerald Penn
In the midst of a global pandemic, understanding the public’s opinion of their government’s policy-level, non-pharmaceutical interventions (NPIs) is a crucial component of the health-policy-making process.
1 code implementation • COLING 2022 • Jingcheng Niu, Wenjie Lu, Gerald Penn
Does BERT store surface knowledge in its bottom layers, syntactic knowledge in its middle layers, and semantic knowledge in its upper layers?
no code implementations • EMNLP (Eval4NLP) 2020 • Jingcheng Niu, Gerald Penn
Prior to the introduction of the GLUE leaderboard, the vast majority of this assessment was essentially anecdotal, and we find the use of the MCC in this regard to be problematic.
no code implementations • EACL 2021 • Eric Corlett, Gerald Penn
These frameworks can have more power than we typically use, and so complexity measures such as worst-case running time can drastically overestimate the cost of running our algorithms.
no code implementations • EACL 2021 • Patricia Thaine, Gerald Penn
The growing availability of powerful mobile devices and other edge devices, together with increasing regulatory and security concerns about the exchange of personal information across networks of these devices has challenged the Computational Linguistics community to develop methods that are at once fast, space-efficient, accurate and amenable to secure encoding schemes such as homomorphic encryption.
no code implementations • WS 2020 • Aditya Bhargava, Gerald Penn
In this paper, we make use of the primitives and operators that constitute the lexical categories of categorial grammars.
no code implementations • LREC 2020 • Jingcheng Niu, Victoria Ng, Gerald Penn, Erin E. Rees
We present a new temporal annotation standard, THEE-TimeML, and a corpus TheeBank enabling precise temporal information extraction (TIE) for event-based surveillance (EBS) systems in the public health domain.
no code implementations • LREC 2020 • Sean Robertson, Cosmin Munteanu, Gerald Penn
The corpus is split into three partitions: one from an experiment with minimal feedback; another with explicit, word-level feedback; and a third with supplementary read-and-record data.
no code implementations • ACL 2019 • Jingcheng Niu, Gerald Penn
This paper presents a detailed account of these shortcomings, our proposed repairs, our rule-based grammar and the neural slot-filling architectures associated with ATIS.
1 code implementation • 1 Jan 2019 • Sean Robertson, Gerald Penn, Yingxue Wang
Triangular, overlapping Mel-scaled filters ("f-banks") are the current standard input for acoustic models that exploit their input's time-frequency geometry, because they provide a psycho-acoustically motivated time-frequency geometry for a speech signal.
no code implementations • WS 2017 • Patricia Thaine, Gerald Penn
We consider two related problems in this paper.