Different from other sequential data, sentences in natural language are structured by linguistic grammars. Previous generative conversational models with chain-structured decoder ignore this structure in human language and might generate plausible responses with less satisfactory relevance and fluency. In this study, we aim to incorporate the results from linguistic analysis into the process of...

Tree-structured neural networks exploit valuable syntactic parse information as they interpret the meanings of sentences. However, they suffer from two key technical problems that make them slow and unwieldy for large-scale NLP tasks: they usually operate on parsed sentences and they do not directly support batched computation. We address these issues by introducing the Stack-augmented Parser-I...

Tree-structured data formats, such as JSON and Protocol Buffers, are capable of expressing sophisticated data types, including nested, repeated, and missing values. While such expressing power contributes to their popularity in real-world applications, it presents a significant challenge for systems supporting tree-structured data. Existing systems have focused on general-purpose solutions eith...

Designers of statistical machine translation (SMT) systems have begun to employ treestructured translation models. Systems involving tree-structured translation models tend to be complex. This article aims to reduce the conceptual complexity of such systems, in order to make them easier to design, implement, debug, use, study, understand, explain, modify, and improve. In service of this goal, t...

In front of the large increase of the available amount of structured data (such as XML documents), many algorithms have emerged for dealing with tree-structured data. In this article, we present a probabilistic approach which aims at a priori pruning noisy or irrelevant subtrees in a set of trees. The originality of this approach, in comparison with classic data reduction techniques, comes from...

Structured documents, such as program source texts, technical documentation, or XML data, comprise an important class of data in many applications. Structured documents are distinguished from flat text by their tree structure. In a program source text, this structure is the abstract syntax tree of the program. In a technical document, this structure is the division in chapters, sections, paragr...

Convolution kernels for trees provide simple means for learning with tree-structured data. The computation time of tree kernels is quadratic in the size of the trees, since all pairs of nodes need to be compared. Thus, large parse trees, obtained from HTML documents or structured network data, render convolution kernels inapplicable. In this article, we propose an effective approximation techni...

Traditional database management systems use tree-structured query evaluation plans. While easy to implement, a tree-structured query evaluation plan is not expressive enough for some optimizations like factoring common algebraic subexpressions or magic sets. These require directed acyclic graphs (DAGs), i.e. shared subplans. This work covers the different aspects of DAG-structured query graphs....

In practical applications, decoding speed is very important. Modern structured learning technique adopts template based method to extract millions of features. Complicated templates bring about abundant features which lead to higher accuracy but more feature extraction time. We propose Two Dimensional Trie (2D Trie), a novel efficient feature indexing structure which takes advantage of relation...

XML is rapidly becoming a standard for data exchange on the Internet. While XML’s document management roots have led many to focus on querying and processing of large documents, we believe much XML data will be in the form of streams. One can envision streams of XML data flowing throughout the Internet: a stream of stock quotes or minute-by-minute updates on positions of a fleet of vehicles one...