This paper describes the construction of a new large-scale English-Japanese Simultaneous Interpretation (SI) corpus and presents the results of its analysis. A portion of the corpus contains SI data from three interpreters with different amounts of e
xperience. Some of the SI data were manually aligned with the source speeches at the sentence level. Their latency, quality, and word order aspects were compared among the SI data themselves as well as against offline translations. The results showed that (1) interpreters with more experience controlled the latency and quality better, and (2) large latency hurt the SI quality.
Recent studies indicate that NLU models are prone to rely on shortcut features for prediction, without achieving true language understanding. As a result, these models fail to generalize to real-world out-of-distribution data. In this work, we show t
hat the words in the NLU training set can be modeled as a long-tailed distribution. There are two findings: 1) NLU models have strong preference for features located at the head of the long-tailed distribution, and 2) Shortcut features are picked up during very early few iterations of the model training. These two observations are further employed to formulate a measurement which can quantify the shortcut degree of each training sample. Based on this shortcut measurement, we propose a shortcut mitigation framework LGTR, to suppress the model from making overconfident predictions for samples with large shortcut degree. Experimental results on three NLU benchmarks demonstrate that our long-tailed distribution explanation accurately reflects the shortcut learning behavior of NLU models. Experimental analysis further indicates that LGTR can improve the generalization accuracy on OOD data, while preserving the accuracy on in-distribution data.
The aim of this research is to shed light on the simultaneous
interpretation of textual discourse markers from English into Arabic.
The research corpus consists of three political speeches by US
president Barack Obama. In his speeches, textual dis
course markers
are intentionally used and have certain functions, so some examples
are chosen to compare original English texts to their Arabic
interpreted counterparts and to show what happens to these markers
in the process of simultaneous interpretation.
