Hand-coded scripts were used in the 1970-80s as knowledge backbones that enabled inference and other NLP tasks requiring deep semantic knowledge. We propose unsupervised induction of similar schemata called narrative event chains from raw newswire text. A narrative event chain is a partially ordered set of events related by a common protagonist. We describe a three step process to learning narrative event chains. The first uses unsupervised distributional methods to learn narrative relations between events sharing coreferring arguments. The second applies a temporal classifier to partially order the connected events. Finally, the third prunes and clusters self-contained chains from the space of events. We introduce two evaluations: the narrative cloze to evaluate event relatedness, and an order coherence task to evaluate narrative order. We show a 36 % improvement over baseline for narrative prediction and 25 % for temporal coherence. 1

Ordering information is a difficult but important task for applications generating natural-language text. We present a bottom-up approach to arranging sentences extracted for multi-document summarization. To capture the association and order of two textual segments (eg, sentences), we define four criteria, chronology, topical-closeness, precedence, and succession. These criteria are integrated into a criterion by a supervised learning approach. We repeatedly concatenate two textual segments into one segment based on the criterion until we obtain the overall segment with all sentences arranged. Our experimental results show a significant improvement over existing sentence ordering strategies. 1

This paper describes a fully automatic twostage machine learning architecture that learns temporal relations between pairs of events. The first stage learns the temporal attributes of single event descriptions, such as tense, grammatical aspect, and aspectual class. These imperfect guesses, combined with other linguistic features, are then used in a second stage to classify the temporal relationship between two events. We present both an analysis of our new features and results on the TimeBank Corpus that is 3% higher than previous work that used perfect human tagged features. 1

Many events in news articles don’t include time arguments. This paper describes two methods, one based on rules and the other based on statistical learning, to predict the unknown time argument for an event by the propagation from its related events. The results are promising – the rule based approach was able to correctly predict 74 % of the unknown event time arguments with 70 % precision. 1

The problem we tackle in this work is, given a present news event, to generate a plausible future event that can be caused by the given event. We present a new methodology for modeling and predicting such future news events using machine learning and data mining techniques. Our Pundit algorithm generalizes examples of causality pairs to infer a causality predictor. To obtain precise labeled causality examples, we mine 150 years of news articles, and apply semantic natural language modeling techniques to titles containing certain predefined causality patterns. For generalization, the model uses a vast amount of world knowledge ontologies mined from LinkedData, containing 200 datasets with approximately 20 billion relations. Empirical evaluation on real news articles shows that our Pundit algorithm reaches a human-level performance.

Polysemy is a major characteristic of natural languages. Like words, syntactic forms can have several meanings. Understanding the correct meaning of a syntactic form is of great importance to many NLP applications. In this paper we address an important type of syntactic polysemy – the multiple possible senses of tense syntactic forms. We make our discussion concrete by introducing the task of Tense Sense Disambiguation (TSD): given a concrete tense syntactic form present in a sentence, select its appropriate sense among a set of possible senses. Using English grammar textbooks, we compiled a syntactic sense dictionary comprising common tense syntactic forms and semantic senses for each. We annotated thousands of BNC sentences using the defined senses. We describe a supervised TSD algorithm trained on these annotations, which outperforms a strong baseline for the task. 1

Abstract When searching for information about historical events, queries are naturally formulated using temporal constraints. However, the structured temporal information needed to support such constraints is usually not available to information retrieval systems. Furthermore, the temporal boundaries of most historical events are inherently ill–defined, calling for suitable extensions of classical temporal reasoning frameworks. In this paper, we propose a framework based on a fuzzification of Allen’s Interval Algebra to cope with these issues. By using simple heuristic techniques to extract temporal information from web documents, we initially focus more on recall than on precision, relying on the subsequent application of a fuzzy temporal reasoner to improve the reliability of the extracted information, and to deal with conflicts that arise because of the vagueness of events. Experimental results indicate that a consistent and reliable knowledge base of fuzzy temporal relations can thus be obtained, which effectively allows us to target temporally constrained retrieval tasks. Keywords Temporal Reasoning · Fuzzy Set Theory · Event-based Retrieval 1

We describe a method for assigning English tense and aspect in a system that realizes surface text for symbolically encoded narratives. Our testbed is an encoding interface in which propositions that are attached to a timeline must be realized from several temporal viewpoints. This involves a mapping from a semantic encoding of time to a set of tense/aspect permutations. The encoding tool realizes each permutation to give a readable, precise description of the narrative so that users can check whether they have correctly encoded actions and statives in the formal representation. Our method selects tenses and aspects for individual event intervals as well as subintervals (with multiple reference points), quoted and unquoted speech (which reassign the temporal focus), and modal events such as conditionals. 1

We present CAVaT, a tool that performs Corpus Analysis and Validation for TimeML. CAVaT is an open source, modular checking utility for statistical analysis of features specific to temporally-annotated natural language corpora. It provides reporting, highlights salient links between a variety of general and time-specific linguistic features, and also validates a temporal annotation to ensure that it is logically consistent and sufficiently annotated. Uniquely, CAVaT provides analysis specific to TimeML-annotated temporal information. TimeML is a standard for annotating temporal information in natural language text. In this paper, we present the reporting part of CAVaT, and then its error-checking ability, including the workings of several novel TimeML document verification methods. This is followed by the execution of some example tasks using the tool to show relations between times, events, signals and links. We also demonstrate inconsistencies in a TimeML corpus (TimeBank) that have been detected with CAVaT. 1.

This article presents our work on constructing a corpus of news articles in which events are annotated for estimated bounds on their duration, and automatically learning from this corpus. We describe the annotation guidelines, the event classes we categorized to reduce gross discrepancies in inter-annotator judgments, and our use of normal distributions to model vague and implicit temporal information and to measure inter-annotator agreement for these event duration distributions. We then show that machine learning techniques applied to this data can produce coarse-grained event duration information automatically, considerably outperforming a baseline and approaching human performance. The methods described here should be applicable to other kinds of vague but substantive information in texts. 1.