Although directly finetuning pretrained models on MSG tasks and concatenating multiple sources into a single long sequence is regarded as a simple method to transfer pretrained models to MSG tasks, we conjecture that the direct finetuning method leads to catastrophic forgetting and solely relying on pretrained self-attention layers to capture cross-source information is not sufficient.
In compositional question answering, the systems should assemble several supporting evidence from the document to generate the final answer, which is more difficult than sentence-level or phrase-level QA.
System combination is an important technique for combining the hypotheses of different machine translation systems to improve translation performance.
The release of ReCO consists of 300k questions that to our knowledge is the largest in Chinese reading comprehension.
Neural models have achieved great success on machine reading comprehension (MRC), many of which typically consist of two components: an evidence extractor and an answer predictor.
The lack of alignment in NMT models leads to three problems: it is hard to (1) interpret the translation process, (2) impose lexical constraints, and (3) impose structural constraints.
To better identify translation errors, our method learns the representations of source sentences and system outputs in an interactive way.
We verify our methods on various translation scenarios, including one-to-many, many-to-many and zero-shot.
Although neural machine translation has made significant progress recently, how to integrate multiple overlapping, arbitrary prior knowledge sources remains a challenge.
Although the Transformer translation model (Vaswani et al., 2017) has achieved state-of-the-art performance in a variety of translation tasks, how to use document-level context to deal with discourse phenomena problematic for Transformer still remains a challenge.
However, previous studies show that one-to-many translation based on this framework cannot perform on par with the individually trained models.
This paper concerns a deep learning approach to relevance ranking in information retrieval (IR).
Endowing a chatbot with personality or an identity is quite challenging but critical to deliver more realistic and natural conversations.