James Pustejovsky

The syntax of event structure

In this paper we examine the role of events within a theory of lexical semantics. We propose a configurational theory of event structure and examine how it contributes to a lexical semantic theory for natural language. In particular, we argue that an event structure can provide a distinct and useful level of representation for linguistic analysis involving the aspectual properties of verbs, adverbial scope, the role of argument structure, and the mapping from the lexicon to syntax.

Robust relational parsing over biomedical literature: extracting inhibit relations.

We describe the design of a robust parser for identifying and extracting biomolecular relations from the biomedical literature. Separate automata over distinct syntactic domains were developed for extraction of nominal-based relational information versus verbal-based relations. This allowed us to optimize the grammars separately for each module, regardless of any specific relation resulting in significantly better performance. A unique feature of this system is the use of text-based anaphora resolution to enhance the results of argument binding in relational extraction. We demonstrate the performance of our system on inhibition-relations, and present our initial results measured against an annotated text used as a gold standard for evaluation purposes. The results represent a significant improvement over previously published results on extracting such relations from Medline: Precision was 90%, Recall 57%, and Partial Recall 22%. These results demonstrate the effectiveness of a corpus-based linguistic approach to information extraction over Medline.

Machine Learning of Temporal Relations

This paper investigates a machine learning approach for temporally ordering and anchoring events in natural language texts. To address data sparseness, we used temporal reasoning as an over-sampling method to dramatically expand the amount of training data, resulting in predictive accuracy on link labeling as high as 93% using a Maximum Entropy classifier on human annotated data. This method compared favorably against a series of increasingly sophisticated baselines involving expansion of rules derived from human intuitions.

SemEval-2007 Task 15: TempEval Temporal Relation Identification

The TempEval task proposes a simple way to evaluate automatic extraction of temporal relations. It avoids the pitfalls of evaluating a graph of inter-related labels by defining three sub tasks that allow pairwise evaluation of temporal relations. The task not only allows straightforward evaluation, it also avoids the complexities of full temporal parsing.

FactBank: a corpus annotated with event factuality

Recent work in computational linguistics points out the need for systems to be sensitive to the veracity or factuality of events as mentioned in text; that is, to recognize whether events are presented as corresponding to actual situations in the world, situations that have not happened, or situations of uncertain interpretation. Event factuality is an important aspect of the representation of events in discourse, but the annotation of such information poses a representational challenge, largely because factuality is expressed through the interaction of numerous linguistic markers and constructions. Many of these markers are already encoded in existing corpora, albeit in a somewhat fragmented way. In this article, we present FactBank, a corpus annotated with information concerning the factuality of events. Its annotation has been carried out from a descriptive framework of factuality grounded on both theoretical findings and data analysis. FactBank is built on top of TimeBank, adding to it an additional level of semantic information.

Automating Temporal Annotation with TARSQI

We present an overview of TARSQI, a modular system for automatic temporal annotation that adds time expressions, events and temporal relations to news texts.

Evita: A Robust Event Recognizer For QA Systems

We present Evita, an application for recognizing events in natural language texts. Although developed as part of a suite of tools aimed at providing question answering systems with information about both temporal and intensional relations among events, it can be used independently as an event extraction tool. It is unique in that it is not limited to any pre-established list of relation types (events), nor is it restricted to a specific domain. Evita performs the identification and tagging of event expressions based on fairly simple strategies, informed by both linguistic-and statistically-based data. It achieves a performance ratio of 80.12% F-measure.

Temporal and Event Information In Natural Language Text

In this paper, we discuss the role that temporal information plays in natural language text, specifically in the context of question answering systems. We define a descriptive framework with which we can examine the temporally sensitive aspects of natural language queries. We then investigate broadly what properties a general specification language would need, in order to mark up temporal and event information in text. We present a language, TimeML, which attempts to capture the richness of temporal and event related information in language, while demonstrating how it can play an important part in the development of more robust question answering systems.

Type Coercion and Lexical Selection

In this paper I will discuss how type-shifting is licensed in a language and what effect it has on the mapping from the lexicon to syntax. In particular, I will look at the phenomenon of type coercion, and how this behavior can be accounted for by the grammar in a systematic way. I suggest that the ambiguity exhibited by adjectives, aspectual verbs, experiencer verbs, and many causatives is the result of type coercion operations. That is, every lexical item exhibits some degree of ambiguity, what I call logical polysemy. This behavior is captured by enriching the lexical semantic representation for lexical items while also allowing a word’s semantic type to shift or be coerced in particular contexts. By allowing both verbs and nouns to shift in type, we can “spread the semantic load” in the lexicon more evenly, while still capturing the ways in which words can extend their meanings, i.e. the creative use of words.

The TempEval challenge: identifying temporal relations in text

TempEval is a framework for evaluating systems that automatically annotate texts with temporal relations. It was created in the context of the SemEval 2007 workshop and uses the TimeML annotation language. The evaluation consists of three subtasks of temporal annotation: anchoring an event to a time expression in the same sentence, anchoring an event to the document creation time, and ordering main events in consecutive sentences. In this paper we describe the TempEval task and the systems that participated in the evaluation. In addition, we describe how further task decomposition can bring even more structure to the evaluation of temporal relations.