We present a system for the semantic role labeling task. The system combines a machine learning technique with an inference procedure based on integer linear programming that supports the incorporation of linguistic and structural constraints into the decision process. The system is tested on the data provided in the CoNLL-2004 shared task on semantic role labeling and achieves very competitive results. 1

Inference in Conditional Random Fields and Hidden Markov Models is done using the Viterbi algorithm, an efficient dynamic programming algorithm. In many cases, general (non-local and non-sequential) constraints may exist over the output sequence, but cannot be incorporated and exploited in a natural way by this inference procedure. This paper proposes a novel inference procedure based on integer linear programming (ILP) and extends CRF models to naturally and efficiently support general constraint structures. For sequential constraints, this procedure reduces to simple linear programming as the inference process. Experimental evidence is supplied in the context of an important NLP problem, semantic role labeling. 1.

We provide an experimental study of the role of syntactic parsing in semantic role labeling. Our conclusions demonstrate that syntactic parse information is clearly most relevant in the very first stage – the pruning stage. In addition, the quality of the pruning stage cannot be determined solely based on its recall and precision. Instead it depends on the characteristics of the output candidates that make downstream problems easier or harder. Motivated by this observation, we suggest an effective and simple approach of combining different semantic role labeling systems through joint inference, which significantly improves the performance. 1

In this paper, we present a semantic role labeler (or chunker) that groups syntactic chunks (i.e. base phrases) into the arguments of a predicate. This is accomplished by casting the semantic labeling as the classification of syntactic chunks (e.g. NP-chunk, PP-chunk) into one of several classes such as the beginning of an argument (B-ARG), inside an argument (I-ARG) and outside an argument (O). This amounts to tagging syntactic chunks with semantic labels using the IOB representation. The chunker is realized using support vector machines as oneversus-all classifiers. We describe the representation of data and information used to accomplish the task. We participate in the “closed challenge ” of the CoNLL-2004 shared task and report results on both development and test sets. 1

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.

This paper describes our experience in preparing the data and evaluating the results for three subtasks of SemEval-2007 Task-17 – Lexical Sample, Semantic Role Labeling (SRL) and All-Words respectively. We tabulate and analyze the results of participating systems. 1

Many learning tasks have subtasks for which much training data exists. Therefore, we want to transfer learning from the old, generalpurpose subtask to a more specific new task, for which there is often less data. While work in transfer learning often considers how the old task should affect learning on the new task, in this paper we show that it helps to take into account how the new task affects the old. Specifically, we perform joint decoding of separately-trained sequence models, preserving uncertainty between the tasks and allowing information from the new task to affect predictions on the old task. On two standard text data sets, we show that joint decoding outperforms cascaded decoding.

This thesis is about estimating probabilistic models to uncover useful hidden structure in data; specifically, we address the problem of discovering syntactic structure in natural language text. We present three new parameter estimation techniques that generalize the standard approach, maximum likelihood estimation, in different ways. Contrastive estimation maximizes the conditional probability of the observed data given a “neighborhood” of implicit negative examples. Skewed deterministic annealing locally maximizes likelihood using a cautious parameter search strategy that starts with an easier optimization problem than likelihood, and iteratively moves to harder problems, culminating in likelihood. Structural annealing is similar, but starts with a heavy bias toward simple syntactic structures and gradually relaxes the bias. Our estimation methods do not make use of annotated examples. We consider their performance in both an unsupervised model selection setting, where models trained under different initialization and regularization settings are compared by evaluating the training objective on a small set of unseen, unannotated development data, and supervised model selection, where the most accurate model on the development set (now with annotations)

In this paper we introduce a semantic role labeling system constructed on top of the full syntactic analysis of text. The labeling problem is modeled using a rich set of lexical, syntactic, and semantic attributes and learned using one-versus-all AdaBoost classifiers. Our results indicate that even a simple approach that assumes that each semantic argument maps into exactly one syntactic phrase obtains encouraging performance, surpassing the best system that uses partial syntax by almost 6%. 1