Title | ||
---|---|---|
Combining flat and structured approaches for temporal slot filling or: how much to compress? |
Abstract | ||
---|---|---|
In this paper, we present a hybrid approach to Temporal Slot Filling (TSF) task. Our method decomposes the task into two steps: temporal classification and temporal aggregation. As in many other NLP tasks, a key challenge lies in capturing relations between text elements separated by a long context. We have observed that features derived from a structured text representation can help compressing the context and reducing ambiguity. On the other hand, surface lexical features are more robust and work better in some cases. Experiments on the KBP2011 temporal training data set show that both surface and structured approaches outperform a baseline bag-of-word based classifier and the proposed hybrid method can further improve the performance significantly. Our system achieved the top performance in KBP2011 evaluation. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1007/978-3-642-28601-8_17 | CICLing (2) |
Keywords | Field | DocType |
temporal slot,temporal classification,kbp2011 evaluation,hybrid approach,structured text representation,proposed hybrid method,kbp2011 temporal training data,nlp task,structured approach,long context,temporal aggregation | Training set,Data mining,Pattern recognition,Computer science,Structured text,Artificial intelligence,Classifier (linguistics),Ambiguity,Fold (higher-order function) | Conference |
Citations | PageRank | References |
1 | 0.38 | 17 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Qi Li | 1 | 137 | 7.83 |
Javier Artiles | 2 | 631 | 41.97 |
Taylor Cassidy | 3 | 187 | 12.48 |
Heng Ji | 4 | 1544 | 127.27 |