This paper explores joint syntactic and semantic parsing of Chinese to further improve the performance of both syntactic and semantic parsing, in particular the performance of semantic parsing (in this paper, semantic role labeling). This is done from two levels. Firstly, an integrated parsing approach is proposed to integrate semantic parsing into the syntactic parsing process. Secondly, semantic information generated by semantic parsing is incorporated into the syntactic parsing model to better capture semantic information in syntactic parsing. Evaluation on Chinese TreeBank, Chinese PropBank, and Chinese NomBank shows that our integrated parsing approach outperforms the pipeline parsing approach on n-best parse trees, a natural extension of the widely used pipeline parsing approach on the top-best parse tree. Moreover, it shows that incorporating semantic role-related information into the syntactic parsing model significantly improves the performance of both syntactic parsing and semantic parsing. To our best knowledge, this is the first research on exploring syntactic parsing and semantic role labeling for both verbal and nominal predicates in an integrated way. 1

We adapt a semantic role parser to the domain of goal-directed speech by creating an artificial treebank from an existing text treebank. We use a three-component model that includes distributional models from both target and source domains. We show that we improve the parser’s performance on utterances collected from human-machine dialogues by training on the artificially created data without loss of performance on the text treebank. 1

dMetrics Current investigations in data-driven models of parsing have shifted from purely syntactic anal-ysis to richer semantic representations, showing that the successful recovery of the meaning of text requires structured analyses of both its grammar and its semantics. In this article, we report on a joint generative history-based model to predict the most likely derivation of a dependency parser for both syntactic and semantic dependencies, in multiple languages. Because these two dependency structures are not isomorphic, we propose a weak synchronization at the level of meaningful subsequences of the two derivations. These synchronized subsequences encompass decisions about the left side of each individual word. We also propose novel derivations for semantic dependency structures, which are appropriate for the relatively unconstrained nature of these graphs. To train a joint model of these synchronized derivations, we make use of a latent variable model of parsing, the Incremental Sigmoid Belief Network (ISBN) architecture. This architecture induces latent feature representations of the derivations, which are used to discover correlations both within and between the two derivations, providing the first application of ISBNs to a multi-task learning problem. This joint model achieves competitive performance

As tweets have become a comprehensive repository of fresh information, Semantic Role Labeling (SRL) for tweets has aroused great research interests because of its central role in a wide range of tweet related studies such as fine-grained information extraction, sentiment analysis and summarization. However, the fact that a tweet is often too short and informal to provide sufficient information poses a major challenge. To tackle this challenge, we propose a new method to collectively label similar tweets. The underlying idea is to exploit similar tweets to make up for the lack of information in a tweet. Specifically, similar tweets are first grouped together by clustering. Then for each cluster a two-stage labeling is conducted: One labeler conducts SRL to get statistical information, such as the predicate/argument/role triples that occur frequently, from its highly confidently labeled results; then in the second stage, another labeler performs SRL with such statistical information to refine the results. Experimental results on a human annotated dataset show that our approach remarkably improves SRL by 3.1 % F1.

News tweets that report what is happening have become an important real-time information source. We raise the problem of Semantic Role Labeling (SRL) for news tweets, which is meaningful for fine grained information extraction and retrieval. We present a self-supervised learning approach to train a domain specific SRL system to resolve the problem. A large volume of training data is automatically labeled, by leveraging the existing SRL system on news domain and content similarity between news and news tweets. On a human annotated test set, our system achieves state-of-the-art performance, outperforming the SRL system trained on news.

We present an inexact search algorithm for the problem of predicting a two-layered dependency graph. The algorithm is based on a k-best version of the standard cubictime search algorithm for projective dependency parsing, which is used as the backbone of a beam search procedure. This allows us to handle the complex nonlocal feature dependencies occurring in bistratal parsing if we model the interdependency between the two layers. We apply the algorithm to the syntactic– semantic dependency parsing task of the CoNLL-2008 Shared Task, and we obtain a competitive result equal to the highest published for a system that jointly learns syntactic and semantic structure.

Semantic role labels are the representation of the grammatically relevant aspects of a sentence meaning. Capturing the nature and the number of semantic roles in a sentence is therefore fundamental to correctly describing the interface between grammar and meaning. In this paper, we compare two annotation schemes, Prop-Bank and VerbNet, in a task-independent, general way, analysing how well they fare in capturing the linguistic generalisations that are known to hold for semantic role labels, and consequently how well they grammaticalise aspects of meaning. We show that VerbNet is more verb-specific and better able to generalise to new semantic role instances, while PropBank better captures some of the structural constraints among roles. We conclude that these two resources should be used together, as they are complementary. 1

When natural language processing tasks overlap in their linguistic input space, they can be technically merged. Applying machine learning algorithms to the new joint task and comparing the results of joint learning with disjoint learning of the original tasks may bring to light the linguistic relatedness of the two tasks. We present a joint learning experiment with dependency parsing and semantic role labeling of Catalan and Spanish. The developed systems are based on local memory-based classifiers predicting constraints on the syntactic and semantic dependency relations in the resulting graph based on the same input features. In a second global phase, a constraint satisfaction inference procedure produces a dependency graph and semantic role label assignments for all predicates in a sentence. The comparison between joint and disjoint learning shows that dependency parsing is better learned in a disjoint setting, while semantic role labeling benefits from joint learning. We explain the results by providing an analysis of the output of the systems. 1.

We propose a novel MLN-based method that collectively conducts SRL on groups of news sentences. Our method is built upon a baseline SRL, which uses no parsers and leverages redundancy. We evaluate our method on a manually labeled news corpus and demonstrate that news redundancy significantly improves the performance of the baseline, e.g., it improves the F-score from 64.13 % to 67.66%.

We propose a solution to the challenge of the CoNLL 2008 shared task that uses a generative history-based latent variable model to predict the most likely derivation of a synchronous dependency parser for both syntactic and semantic dependencies. The submitted model yields 79.1 % macroaverage F1 performance, for the joint task, 86.9 % syntactic dependencies LAS and 71.0 % semantic dependencies F1. A larger model trained after the deadline achieves 80.5 % macro-average F1, 87.6 % syntactic dependencies LAS, and 73.1 % semantic dependencies F1. 1