相关论文: Designing Statistical Language Learners: Experimen…

The ease and speed of spreading misinformation and propaganda on the Web motivate the need to develop trustworthy technology for detecting fallacies in natural language arguments. However, state-of-the-art language modeling methods exhibit…

Systematic generalization is the ability to combine known parts into novel meaning; an important aspect of efficient human learning, but a weakness of neural network learning. In this work, we investigate how two well-known modeling…

To understand how well a large language model captures certain semantic or syntactic features, researchers typically apply probing classifiers. However, the accuracy of these classifiers is critical for the correct interpretation of the…

Neural network models often generalize poorly to mismatched domains or distributions. In NLP, this issue arises in particular when models are expected to generalize compositionally, that is, to novel combinations of familiar words and…

Recent progress in deep learning and natural language processing has given rise to powerful models that are primarily trained on a cloze-like task and show some evidence of having access to substantial linguistic information, including some…

We present the surprising finding that a language model's reasoning capabilities can be improved by training on synthetic datasets of chain-of-thought (CoT) traces from more capable models, even when all of those traces lead to an incorrect…

This paper presents a novel method that allows a machine learning algorithm following the transformation-based learning paradigm \cite{brill95:tagging} to be applied to multiple classification tasks by training jointly and simultaneously on…

We present models for embedding words in the context of surrounding words. Such models, which we refer to as token embeddings, represent the characteristics of a word that are specific to a given context, such as word sense, syntactic…

Neural language models (LMs) have been shown to capture complex linguistic patterns, yet their utility in understanding human language and more broadly, human cognition, remains debated. While existing work in this area often evaluates…

To train a statistical spoken dialogue system (SDS) it is essential that an accurate method for measuring task success is available. To date training has relied on presenting a task to either simulated or paid users and inferring the…

String diagrams are an increasingly popular algebraic language for the analysis of graphical models of computations across different research fields. Whereas string diagrams have been thoroughly studied as semantic structures, much less…

Student modeling is central to many educational technologies as it enables predicting future learning outcomes and designing targeted instructional strategies. However, open-ended learning domains pose challenges for accurately modeling…

This work investigates spoken language understanding (SLU) systems in the scenario when the semantic information is extracted directly from the speech signal by means of a single end-to-end neural network model. Two SLU tasks are…

AI systems are becoming active participants in organizational and knowledge work. They increasingly interact with humans, coordinate workflows, and operate in multi-agent arrangements. Understanding their effects therefore requires more…

Accurate syntactic representations are essential for robust generalization in natural language. Recent work has found that pre-training can teach language models to rely on hierarchical syntactic features - as opposed to incorrect linear…

This paper introduces and analyzes a battery of inference models for the problem of semantic role labeling: one based on constraint satisfaction, and several strategies that model the inference as a meta-learning problem using…

Recent work has attempted to characterize the structure of semantic memory and the search algorithms which, together, best approximate human patterns of search revealed in a semantic fluency task. There are a number of models that seek to…

The natural language generation (NLG) component of a spoken dialogue system (SDS) usually needs a substantial amount of handcrafting or a well-labeled dataset to be trained on. These limitations add significantly to development costs and…

Generative models have been showing potential for producing data in mass. This study explores the enhancement of clinical natural language processing performance by utilizing synthetic data generated from advanced language models. Promising…

In this research, we advanced a spoken language recognition system, moving beyond traditional feature vector-based models. Our improvements focused on effectively capturing language characteristics over extended periods using a specialized…