732 citations
- Microsoft (United States)US45 papers
- Massachusetts Institute of TechnologyUS32 papers
- University of WashingtonUS31 papers
- Carnegie Mellon UniversityUS29 papers
- University of Science and Technology of ChinaCN28 papers
- Peking UniversityCN26 papers
- Stanford UniversityUS24 papers
- University of CambridgeGB23 papers
- Tsinghua UniversityCN22 papers
- University of California, BerkeleyUS21 papers
- Georgia Institute of TechnologyUS14 papers
- Google (United States)US14 papers
149 papers · 1 filter
Language Tokens: A Frustratingly Simple Approach Improves Zero-Shot Performance of Multilingual Translation
Muhammad ElNokrashy, Amr Hendy, Mohamed Maher +2
This paper proposes a simple yet effective method to improve direct (X-to-Y) translation for both cases: zero-shot and when direct data is available. We modify the input tokens at…
ScaleVLAD: Improving Multimodal Sentiment Analysis via Multi-Scale Fusion of Locally Descriptors
Huaishao Luo, Lei Ji, Yanyong Huang +3
Fusion technique is a key research topic in multimodal sentiment analysis. The recent attention-based fusion demonstrates advances over simple operation-based fusion. However, thes…
Multilingual Machine Translation Systems from Microsoft for WMT21 Shared Task
Jian Yang, Shuming Ma, Haoyang Huang +8
This report describes Microsoft's machine translation systems for the WMT21 shared task on large-scale multilingual machine translation. We participated in all three evaluation tra…
An Empirical Investigation of Multi-bridge Multilingual NMT models
Anoop Kunchukuttan
In this paper, we present an extensive investigation of multi-bridge, many-to-many multilingual NMT models (MB-M2M) ie., models trained on non-English language pairs in addition to…
NaRLE: Natural Language Models using Reinforcement Learning with Emotion Feedback
Ruijie Zhou, Soham Deshmukh, Jeremiah Greer +1
Current research in dialogue systems is focused on conversational assistants working on short conversations in either task-oriented or open domain settings. In this paper, we focus…
Building an Efficient and Effective Retrieval-based Dialogue System via Mutual Learning
Chongyang Tao, Jiazhan Feng, Chang Liu +3
Establishing retrieval-based dialogue systems that can select appropriate responses from the pre-built index has gained increasing attention from researchers. For this task, the ad…