We present a general framework for semantic role labeling. The framework combines a machine learning technique with an integer linear programming based inference procedure, which incorporates linguistic and structural constraints into a global decision process. Within this framework, we study the role of syntactic parsing information in semantic role labeling. We show that full syntactic parsing information is, by far, most relevant in identifying the argument, especially, in the very first stage—the pruning stage. Surprisingly, the quality of the pruning stage cannot be solely determined based on its recall and precision. Instead, it depends on the characteristics of the output candidates that determine the difficulty of the downstream problems. Motivated by this observation, we propose an effective and simple approach of combining different semantic role labeling systems through joint inference, which significantly improves its performance. Our system has been evaluated in the CoNLL-2005 shared task on semantic role labeling, and achieves the highest F1 score among 19 participants.

This paper focuses on semantic role labeling using automatically-generated syntactic information. A simple and robust strategy for system combination is presented, which allows to partially recover from input parsing errors and to significantly boost results of individual systems. This combination scheme is also very flexible since the individual systems are not required to provide any information other than their solution. Extensive experimental evaluation in the CoNLL-2005 shared task framework supports our previous claims. The proposed architecture outperforms the best results reported in that evaluation exercise.

Abstract not found

We show how punctuation can be used to improve unsupervised dependency parsing. Our linguistic analysis confirms the strong connection between English punctuation and phrase boundaries in the Penn Treebank. However, approaches that naively include punctuation marks in the grammar (as if they were words) do not perform well with Klein and Manning’s Dependency Model with Valence (DMV). Instead, we split a sentence at punctuation and impose parsing restrictions over its fragments. Our grammar inducer is trained on the Wall Street Journal (WSJ) and achieves 59.5 % accuracy out-of-domain (Brown sentences with 100 or fewer words), more than 6 % higher than the previous best results. Further evaluation, using the 2006/7 CoNLL sets, reveals that punctuation aids grammar induction in 17 of 18 languages, for an overall average net gain of 1.3%. Some of this improvement is from training, but more than half is from parsing with induced constraints, in inference. Punctuation-aware decoding works with existing (even already-trained) parsing models and always increased accuracy in our experiments. 1

Many plain text information hiding techniques demand deep semantic processing, and so suffer in reliability. In contrast, syntactic processing is a more mature and reliable technology. Assuming a perfect parser, this paper evaluates a set of automated and reversible syntactic transforms that can hide information in plain text without changing the meaning or style of a document. A large representative collection of newspaper text is fed through a prototype system. In contrast to previous work, the output is subjected to human testing to verify that the text has not been significantly compromised by the information hiding procedure, yielding a success rate of 96 % and bandwidth of 0.3 bits per sentence.

Most supervised language processing systems show a significant drop-off in performance when they are tested on text that comes from a domain significantly different from the domain of the training data. Semantic role labeling techniques are typically trained on newswire text, and in tests their performance on fiction is as much as 19 % worse than their performance on newswire text. We investigate techniques for building open-domain semantic role labeling systems that approach the ideal of a train-once, use-anywhere system. We leverage recently-developed techniques for learning representations of text using latent-variable language models, and extend these techniques to ones that provide the kinds of features that are useful for semantic role labeling. In experiments, our novel system reduces error by 16 % relative to the previous state of the art on out-of-domain text. 1

We integrate PropBank semantic role labels to an existing statistical parsing model producing richer output. We show conclusive results on joint learning and inference of syntactic and semantic representations. 1

We propose a unified neural network architecture and learning algorithm that can be applied to various natural language processing tasks including part-of-speech tagging, chunking, named entity recognition, and semantic role labeling. This versatility is achieved by trying to avoid task-specific engineering and therefore disregarding a lot of prior knowledge. Instead of exploiting man-made input features carefully optimized for each task, our system learns internal representations on the basis of vast amounts of mostly unlabeled training data. This work is then used as a basis for building a freely available tagging system with good performance and minimal computational requirements.

Martha Palmer, whose guidance and support, and the personal time she has invested throughout my time as a graduate student, are much appreciated. Dan Gildea has been instrumental in helping me develop and focus my dissertation research topic. I would also like to thank Mitch Marcus, Fernando Pereira, and Ben Taskar, for accepting my invitation to participate in my thesis dissertation as members of the thesis committee. Finally, I would like to thank my wife, my parents, and my two brothers for their unwavering love, affection and support. ii

Semantic role labeling (SRL) is an important module of spoken language understanding systems. This work extends the standard evaluation metrics for joint dependency parsing and SRL of text in order to be able to handle speech recognition output with word errors and sentence segmentation errors. We propose metrics based on word alignments and bags of relations, and compare their results on the output of several SRL systems on broadcast news and conversations of the OntoNotes corpus. We evaluate and analyze the relation between the performance of the subtasks that lead to SRL, including ASR, part-of-speech tagging or sentence segmentation. The tools are made available to the community.