Related papers: Semantic Operator Prediction and Applications
Semantic parsing is a key NLP task that maps natural language to structured meaning representations. As in many other NLP tasks, SOTA performance in semantic parsing is now attained by fine-tuning a large pretrained language model (PLM).…
Word representation is a fundamental component in neural language understanding models. Recently, pre-trained language models (PrLMs) offer a new performant method of contextualized word representations by leveraging the sequence-level…
We introduce a top-down approach to discourse parsing that is conceptually simpler than its predecessors (Kobayashi et al., 2020; Zhang et al., 2020). By framing the task as a sequence labelling problem where the goal is to iteratively…
Semantic operators have increasingly become integrated within data systems to enable processing data using Large Language Models (LLMs). Despite significant recent effort in improving these operators, their accuracy is limited due to a…
We present the first sentence simplification model that learns explicit edit operations (ADD, DELETE, and KEEP) via a neural programmer-interpreter approach. Most current neural sentence simplification systems are variants of…
Humans can reason compositionally when presented with new tasks. Previous research shows that appropriate prompting techniques enable large language models (LLMs) to solve artificial compositional generalization tasks such as SCAN. In this…
Automatic evaluation of semantic rationality is an important yet challenging task, and current automatic techniques cannot well identify whether a sentence is semantically rational. The methods based on the language model do not measure the…
The predominant challenge in weakly supervised semantic parsing is that of spurious programs that evaluate to correct answers for the wrong reasons. Prior work uses elaborate search strategies to mitigate the prevalence of spurious…
We evaluate the character-level translation method for neural semantic parsing on a large corpus of sentences annotated with Abstract Meaning Representations (AMRs). Using a sequence-to-sequence model, and some trivial preprocessing and…
We propose a sequence labeling framework with a secondary training objective, learning to predict surrounding words for every word in the dataset. This language modeling objective incentivises the system to learn general-purpose patterns of…
We define a class of probabilistic models in terms of an operator algebra of stochastic processes, and a representation for this class in terms of stochastic parameterized grammars. A syntactic specification of a grammar is mapped to…
The effectiveness of a language model is influenced by its token representations, which must encode contextual information and handle the same word form having a plurality of meanings (polysemy). Currently, none of the common language…
Operator learning is a recent development in the simulation of Partial Differential Equations (PDEs) by means of neural networks. The idea behind this approach is to learn the behavior of an operator, such that the resulting neural network…
Koopman operators provide tractable means of learning linear approximations of non-linear dynamics. Many approaches have been proposed to find these operators, typically based upon approximations using an a-priori fixed class of models.…
A fundamental challenge in developing semantic parsers is the paucity of strong supervision in the form of language utterances annotated with logical form. In this paper, we propose to exploit structural regularities in language in…
Semantic sparsity is a common challenge in structured visual classification problems; when the output space is complex, the vast majority of the possible predictions are rarely, if ever, seen in the training set. This paper studies semantic…
Operations research (OR) is a core methodology that supports complex system decision-making, with broad applications in transportation, supply chain management, and production scheduling. However, traditional approaches that rely on…
Transition-based parsers for Abstract Meaning Representation (AMR) rely on node-to-word alignments. These alignments are learned separately from parser training and require a complex pipeline of rule-based components, pre-processing, and…
Attention-based sequence-to-sequence models have shown promising results in automatic speech recognition. Using these architectures, one-dimensional input and output sequences are related by an attention approach, thereby replacing more…
Choice constructs are an important part of the language of logic programming, yet the study of their semantics has been a challenging task. So far, only two-valued semantics have been studied, and the different proposals for such semantics…