We use the re-translation strategy to translate the streamed speech, resulting in caption flicker.
This paper describes our submission for the End-to-end Multi-domain Task Completion Dialog shared task at the 9th Dialog System Technology Challenge (DSTC-9).
We create a new task-oriented dialog platform (MEEP) where agents are given considerable freedom in terms of utterances and API calls, but are constrained to work within a push-button environment.
Web-crawled data provides a good source of parallel corpora for training machine translation models.
Ranked #1 on Machine Translation on WMT2019 English-Japanese
Relation Extraction suffers from dramatical performance decrease when training a model on one genre and directly applying it to a new genre, due to the distinct feature distributions.
We aim to automatically generate natural language descriptions about an input structured knowledge base (KB).
We demonstrate two annotation platforms that allow an English speaker to annotate names for any language without knowing the language.
We demonstrate ELISA-EDL, a state-of-the-art re-trainable system to extract entity mentions from low-resource languages, link them to external English knowledge bases, and visualize locations related to disaster topics on a world heatmap.
We present a paper abstract writing system based on an attentive neural sequence-to-sequence model that can take a title as input and automatically generate an abstract.
Ranked #1 on Paper generation on ACL Title and Abstract Dataset
We construct a multilingual common semantic space based on distributional semantics, where words from multiple languages are projected into a shared space to enable knowledge and resource transfer across languages.
Current supervised name tagging approaches are inadequate for most low-resource languages due to the lack of annotated data and actionable linguistic knowledge.
The ambitious goal of this work is to develop a cross-lingual name tagging and linking framework for 282 languages that exist in Wikipedia.
Instead of directly relying on word alignment results, this framework combines advantages of rule-based methods and deep learning methods by implementing two steps: First, generates a high-confidence entity annotation set on IL side with strict searching methods; Second, uses this high-confidence set to weakly supervise the model training.