Dense Event Ordering with a Multi-Pass Architecture

Abstract

The past 10 years of event ordering research has focused on learning partial orderings over document events and time expressions. The most popular corpus, the TimeBank, contains a small subset of the possible ordering graph. Many evaluations follow suit by only testing certain pairs of events (e.g., only main verbs of neighboring sentences). This has led most research to focus on specific learners for partial labelings. This paper attempts to nudge the discussion from identifying some relations to all relations. We present new experiments on strongly connected event graphs that contain ∼10 times more relations per document than the TimeBank. We also describe a shift away from the single learner to a sieve-based architecture that naturally blends multiple learners into a precision-ranked cascade of sieves. Each sieve adds labels to the event graph one at a time, and earlier sieves inform later ones through transitive closure. This paper thus describes innovations in both approach and task. We experiment on the densest event graphs to date and show a 14% gain over state-of-the-art.

The UAB Informatics Institute and 2016 CEGS N-GRID de-identification shared task challenge

“…The multi-pass sieve framework has been applied to resolving co-reference resolution(21, 22) and successfully generalized to other NLP tasks(23, 24). The framework favors breaking a complex task into independent sub-tasks (or sieves) and iteratively passing through the document.…”

Neural Ranking Models for Temporal Dependency Structure Parsing

“…Such a pair-wise clas-sification approach is often dictated by the way the data is annotated. In most of the widely used temporal data sets, temporal relations between individual pairs of events and/or time expressions are annotated independently of one another (Pustejovsky et al, 2003;Chambers et al, 2014;Styler IV et al, 2014;O'Gorman et al, 2016;Mostafazadeh et al, 2016). Our work is most closely related to that of , which also treats temporal relation modeling as temporal dependency structure parsing.…”

Temporal Information Extraction for Question Answering Using Syntactic Dependencies in an LSTM-based Architecture

“…If there is no information about the relation between two entities, it is labeled as "vague". We follow the experimental setup in (Chambers et al, 2014), which splits the corpus into training/validation/test sets of 22, 5, and 9 documents, respectively.…”

“…Sun (2014) proposed a strategy that "prefers the edges that can be inferred by other edges in the graph and remove the ones that are least so". Another strategy is to use the results from separate classifiers or "sieves" to rank TLINKs according to their confidence (Mani et al, 2007;Chambers et al, 2014). High-ranking results overwrite low-ranking ones.…”