Music tagging is the task of predicting multiple tags of a music excerpt, and plays an important role in modern music recommendation systems. To obtain superior performance, recent approaches of music tagging focus on developing sophisticated models or exploiting additional multi-modal information. However, none of them deal with the problem of label noise during the training process despite of its ubiquitous presence. In this paper, we propose a progressive two-stage teacher-student training framework to prevent the music tagging model from overfitting label noise. Experimental results suggest that the proposed method surpasses conventional label-noise-robust methods and exhibits scalability across different tagging models. Moreover, detailed analyses demonstrate that the two teachers in the framework gradually improve student model’s generalization performance and effectively avoid the impairment from label noise.

Adaptive policies are better than fixed policies for simultaneous translation, since they can flexibly balance the tradeoff between translation quality and latency based on the current context information.But previous methods on obtaining adaptive policies either rely on complicated training process, or underperform simple fixed policies.We design an algorithm to achieve adaptive policies via a simple heuristic composition of a set of fixed policies.Experiments on Chinese→English and German→English show that our adaptive policies can outperform fixed ones by up to 4 BLEU points for the same latency, and more surprisingly, it even surpasses the BLEU score of full-sentence translation in the greedy mode (and very close to beam mode), but with much lower latency.

Simultaneous translation has many important application scenarios and attracts much attention from both academia and industry recently.Most existing frameworks, however, have difficulties in balancing between the translation quality and latency, i.e., the decoding policy is usually either too aggressive or too conservative.We propose an opportunistic decoding technique with timely correction ability, which always (over-)generates a certain mount of extra words at each step to keep the audience on track with the latest information.At the same time, it also corrects, in a timely fashion, the mistakes in the former overgenerated words when observing more source context to ensure high translation quality.Experiments show our technique achieves substantial reduction in latency and up to +3.1 increase in BLEU, with revision rate under 8% in Chinese-to-English and English-to-Chinese translation.

Mingbo Ma, Liang Huang, Hao Xiong, Renjie Zheng, Kaibo Liu, Baigong Zheng, Chuanqiang Zhang, Zhongjun He, Hairong Liu, Xing Li, Hua Wu, Haifeng Wang. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 2019.

Simultaneous translation is widely useful but remains one of the most difficult tasks in NLP.Previous work either uses fixed-latency policies, or train a complicated two-staged model using reinforcement learning.We propose a much simpler single model that adds a "delay" token to the target vocabulary, and design a restricted dynamic oracle to greatly simplify training.Experiments on Chinese↔English simultaneous translation show that our work leads to flexible policies that achieve better BLEU scores and lower latencies compared to both fixed and RL-learned policies.

Renjie Zheng, Mingbo Ma, Baigong Zheng, Liang Huang. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Baigong Zheng, Renjie Zheng, Mingbo Ma, Liang Huang. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

We consider the problem of finding the minimum-weight subgraph that satisfies given connectivity requirements. Specifically, given a requirement $r \in \{0,1,2,3\}$ for every vertex, we seek the minimum-weight subgraph that contains, for every pair of vertices $u$ and $v$, at least $\min\{ r(v), r(u)\}$ edge-disjoint $u$-to-$v$ paths. We give a polynomial-time approximation scheme (PTAS) for this problem when the input graph is planar and the subgraph may use multiple copies of any given edge. This generalizes an earlier result for $r \in \{0,1,2\}$. In order to achieve this PTAS, we prove some properties of triconnected planar graphs that may be of independent interest.