Китайский древовидный банк

Over the years, many proposals have been made to incorporate assorted types of feature in language models. However, discrepancies between training sets, evaluation criteria, algorithms, and hardware environments make it …...

The paper presents a maximum entropy Chinese character-based parser trained on the Chinese Treebank (“CTB” hence- forth). Word-based parse trees CTB are first converted into character-in based trees, where word-level …...

The Proposition Bank (PropBank) project is aimed at creating a corpus of text an- notated with information about seman- tic propositions. The second phase of the project, PropBank II adds …...

We present an improved approach for learning dependency parsers from tree- bank data. Our technique is based on two ideas for improving large margin train- ing in the context of …...

We show that jointly parsing a bitext can sub- stantially improve parse quality on both sides. In a maximum entropy bitext parsing model, we define a distribution over source trees, …...

Jointly parsing two languages has been shown to improve accuracies on either or both sides. However, its search space is much bigger than the monolingual case, forcing existing approaches to …...

. Alternating Structure Optimization (ASO) is a recently proposed linear Multi- task Learning algorithm. Although its effective has been verified in both semi-supervised as well as supervised methods, yet they …...

We show that the standard beam-search al- gorithm can be used as an efficient decoder for the global linear model of Zhang and Clark (2008) for joint word segmentation and …...

This paper explores joint syntactic and seman- tic parsing of Chinese to further improve the performance of both syntactic and semantic parsing, in particular the performance of se- mantic parsing …...

Employing higher-order subtree structures in graph-based dependency parsing has shown substantial improvement over the accuracy, however suffers from the inefficiency increasing with the order of subtrees. We present a new …...

We describe a novel approach to detecting empty categories (EC) as represented in de- pendency trees as well as a new metric for measuring EC detection accuracy. The new metric …...

This paper introduces a graph-based semi- supervised joint model of Chinese word segmentation and part-of-speech tagging. The proposed approach is based on a graph-based label propagation technique. One constructs a …...

Recent work on Chinese analysis has led to large-scale annotations of the internal structures of words, enabling character- level analysis of Chinese syntactic struc- tures. In this paper, we investigate …...

We propose three improvements to ad- dress the drawbacks of state-of-the-art transition-based constituent parsers. First, to resolve the error propagation problem of the traditional pipeline approach, we incorporate POS tagging …...

We present a multi-view annotation framework for Chinese treebanking, which uses dependen- cy structures as the base view and supports conversion into phrase structures with minimal loss of information. A …...

This paper presents a novel technique for empty category (EC) detection using dis- tributed word representations. A joint model is learned from the labeled data to map both the distributed …...

AbstractWe report our work on building linguistic resources and data-driven parsers in the grammatical relation (GR) analysis for Mandarin Chinese. Chinese, as an analytic language, encodes grammatical information in a …...

AbstractIt is commonly believed that knowledge of syntactic structure should improve language modeling. However, effectively and computationally efficiently incorporating syntactic structure into neural language models has been a challenging topic. …...

AbstractAttention mechanisms have improved the performance of NLP tasks while allowing models to remain explainable. Self-attention is currently widely used, however interpretability is difficult due to the numerous attention distributions. …...

We propose two fast neural combinatory mod- els for constituency parsing: binary and multi- branching. Our models decompose the bottom- up parsing process into 1) classification of tags, labels, and …...