Nazanin Dehghani


Embedding Time Differences in Context-sensitive Neural Networks for Learning Time to Event
Nazanin Dehghani | Hassan Hajipoor | Hadi Amiri
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)

We propose an effective context-sensitive neural model for time to event (TTE) prediction task, which aims to predict the amount of time to/from the occurrence of given events in streaming content. We investigate this problem in the context of a multi-task learning framework, which we enrich with time difference embeddings. In addition, we develop a multi-genre dataset of English events about soccer competitions and academy awards ceremonies, and their relevant tweets obtained from Twitter. Our model is 1.4 and 3.3 hours more accurate than the current state-of-the-art model in estimating TTE on English and Dutch tweets respectively. We examine different aspects of our model to illustrate its source of improvement.


Event Time Extraction with a Decision Tree of Neural Classifiers
Nils Reimers | Nazanin Dehghani | Iryna Gurevych
Transactions of the Association for Computational Linguistics, Volume 6

Extracting the information from text when an event happened is challenging. Documents do not only report on current events, but also on past events as well as on future events. Often, the relevant time information for an event is scattered across the document. In this paper we present a novel method to automatically anchor events in time. To our knowledge it is the first approach that takes temporal information from the complete document into account. We created a decision tree that applies neural network based classifiers at its nodes. We use this tree to incrementally infer, in a stepwise manner, at which time frame an event happened. We evaluate the approach on the TimeBank-EventTime Corpus (Reimers et al., 2016) achieving an accuracy of 42.0% compared to an inter-annotator agreement (IAA) of 56.7%. For events that span over a single day we observe an accuracy improvement of 33.1 points compared to the state-of-the-art CAEVO system (Chambers et al., 2014). Without retraining, we apply this model to the SemEval-2015 Task 4 on automatic timeline generation and achieve an improvement of 4.01 points F1-score compared to the state-of-the-art. Our code is publically available.


Temporal Anchoring of Events for the TimeBank Corpus
Nils Reimers | Nazanin Dehghani | Iryna Gurevych
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)