195
click to vote
ACL
2012
13 years 8 months ago
2012
We investigate the consistency of human assessors involved in summarization evaluation to understand its effect on system ranking and automatic evaluation techniques. Using Text A...
178
click to vote
ACL
2012
13 years 8 months ago
2012
We propose a latent variable model to enhance historical analysis of large corpora. This work extends prior work in topic modelling by incorporating metadata, and the interactions...
206
click to vote
ACL
2012
13 years 8 months ago
2012
The dominant practice of statistical machine translation (SMT) uses the same Chinese word segmentation specification in both alignment and translation rule induction steps in buil...
157
Voted
ACL
2012
13 years 8 months ago
2012
We present a system for cross-lingual parse disambiguation, exploiting the assumption that the meaning of a sentence remains unchanged during translation and the fact that differe...
176
click to vote
ACL
2012
13 years 8 months ago
2012
In relation extraction, distant supervision seeks to extract relations between entities from text by using a knowledge base, such as Freebase, as a source of supervision. When a s...