Introduction | To address this limitation, as the first contribution, we propose a novel document-level discourse parser based on probabilistic discriminative parsing models , represented as Conditional Random Fields (CRFs) (Sutton et al., 2007), to infer the probability of all possible DT constituents. |
Introduction | Two separate parsing models could exploit the fact that rhetorical relations are distributed differently intra-sententially vs. multi-sententially. |
Our Discourse Parsing Framework | Both of our parsers have the same two components: a parsing model assigns a probability to every possible DT, and a parsing algorithm identifies the most probable DT among the candidate DTs in that scenario. |
Our Discourse Parsing Framework | Before describing our parsing models and the parsing algorithm, we introduce some terminology that we will use throughout the paper. |
Parsing Models and Parsing Algorithm | The job of our intra-sentential and multi-sentential parsing models is to assign a probability to each of the constituents of all possible DTs at the sentence level and at the document level, respectively. |
Parsing Models and Parsing Algorithm | Formally, given the model parameters 9, for each possible constituent R[z’, m, j] in a candidate DT at the sentence or document level, the parsing model estimates P(R[z’, m, j] |@), which specifies a joint distribution over the label R and the structure [i, m, j] of the constituent. |
Parsing Models and Parsing Algorithm | 4.1 Intra-Sentential Parsing Model |
Character-based Chinese Parsing | To produce character-level trees for Chinese NLP tasks, we develop a character-based parsing model , which can jointly perform word segmentation, POS tagging and phrase-structure parsing. |
Character-based Chinese Parsing | Our character-based Chinese parsing model is based on the work of Zhang and Clark (2009), which is a transition-based model for lexicalized constituent parsing. |
Experiments | The character-level parsing model has the advantage that deep character information can be extracted as features for parsing. |
Experiments | Zhang and Clark (2010), and the phrase-structure parsing model of Zhang and Clark (2009). |
Experiments | The phrase-structure parsing model is trained with a 64-beam. |
Introduction | We build a character-based Chinese parsing model to parse the character-level syntax trees. |
Related Work | Our character-level parsing model is inspired by the work of Zhang and Clark (2009), which is a transition-based model with a beam-search decoder for word-based constituent parsing. |
Bilingually-Guided Dependency Grammar Induction | Use the parsing model to build new treebank on target language for next iteration. |
Bilingually-Guided Dependency Grammar Induction | With this approach, we can optimize the mixed parsing model by maximizing the objective in Formula (9). |
Introduction | We evaluate the final automatically-induced dependency parsing model on 5 languages. |
Unsupervised Dependency Grammar Induction | And the framework of our unsupervised model builds a random treebank on the monolingual corpus firstly for initialization and trains a discriminative parsing model on it. |
Unsupervised Dependency Grammar Induction | Algorithm 1 outlines the unsupervised training in its entirety, where the treebank DE and unsupervised parsing model with A are updated iteratively. |
Unsupervised Dependency Grammar Induction | In line 1 we build a random treebank DE on the monolingual corpus, and then train the parsing model with it (line 2) through a training procedure train(-, which needs DE and 15F as classification instances. |
Introduction | 3 A Maximum Entropy Based Shift-Reduce Parsing Model |
Introduction | 1. relative frequencies in two directions; 2. lexical weights in two directions; 3. phrase penalty; 4. distance-based reordering model; 5. lexicaized reordering model; 6. n-gram language model model; 7. word penalty; 8. ill-formed structure penalty; 9. dependency language model; 10. maximum entropy parsing model . |
Introduction | Table 3: Contribution of maximum entropy shift-reduce parsing model . |