Related papers: Structured Tree Alignment for Evaluation of (Speec…
Tasks like code generation and semantic parsing require mapping unstructured (or partially structured) inputs to well-formed, executable outputs. We introduce abstract syntax networks, a modeling framework for these problems. The outputs…
Information needs around a topic cannot be satisfied in a single turn; users typically ask follow-up questions referring to the same theme and a system must be capable of understanding the conversational context of a request to retrieve…
Measuring sentence similarity is a classic topic in natural language processing. Light-weighted similarities are still of particular practical significance even when deep learning models have succeeded in many other tasks. Some…
Parsing sentences into syntax trees can benefit downstream applications in NLP. Transition-based parsers build trees by executing actions in a state transition system. They are computationally efficient, and can leverage machine learning to…
We present a conceptual framework that unifies a variety of evaluation metrics for different structured prediction tasks (e.g. event and relation extraction, syntactic and semantic parsing). Our framework requires representing the outputs…
Comparison and evaluation of graph-based representations of sentence meaning is a challenge because competing representations of the same sentence may have different number of nodes, and it is not obvious which nodes should be compared to…
Large Language Models are increasingly being deployed to extract structured data from unstructured and semi-structured sources: parsing invoices, medical records, and converting PDF documents to database entries. Yet existing benchmarks for…
General treebank analyses are graph structured, but parsers are typically restricted to tree structures for efficiency and modeling reasons. We propose a new representation and algorithm for a class of graph structures that is flexible…
Rhetorical Structure Theory implies no single discourse interpretation of a text, and the limitations of RST parsers further exacerbate inconsistent parsing of similar structures. Therefore, it is important to take into account that the…
Deep neural networks for machine comprehension typically utilizes only word or character embeddings without explicitly taking advantage of structured linguistic information such as constituency trees and dependency trees. In this paper, we…
Bounding box regression is the crucial step in object detection. In existing methods, while $\ell_n$-norm loss is widely adopted for bounding box regression, it is not tailored to the evaluation metric, i.e., Intersection over Union (IoU).…
The translation of pronouns presents a special challenge to machine translation to this day, since it often requires context outside the current sentence. Recent work on models that have access to information across sentence boundaries has…
The increasing size and complexity of scientific data could dramatically enhance discovery and prediction for basic scientific applications. Realizing this potential, however, requires novel statistical analysis methods that are both…
Feedback data is widely used for fine-tuning and evaluating state-of-the-art AI models. Pairwise text preferences, where human or AI annotators select the "better" of two options, are particularly common. Such preferences are used to train…
Recent works on structured text translation remain limited to the sentence level, as they struggle to effectively handle the complex document-level XML or HTML structures. To address this, we propose \textbf{Format Reinforcement Learning…
We study the problem of integrating syntactic information from constituency trees into a neural model in Frame-semantic parsing sub-tasks, namely Target Identification (TI), FrameIdentification (FI), and Semantic Role Labeling (SRL). We use…
In this paper, we introduce a new and simple method for comparing speech utterances without relying on text transcripts. Our speech-to-speech comparison metric utilizes state-of-the-art speech2unit encoders like HuBERT to convert speech…
Current anchor-free object detectors are quite simple and effective yet lack accurate label assignment methods, which limits their potential in competing with classic anchor-based models that are supported by well-designed assignment…
We propose a novel method for translation selection in statistical machine translation, in which a convolutional neural network is employed to judge the similarity between a phrase pair in two languages. The specifically designed…
Previous works have demonstrated the effectiveness of utilising pre-trained sentence encoders based on their sentence representations for meaning comparison tasks. Though such representations are shown to capture hidden syntax structures,…