arXiv subjects

Yangming Li

Publications and source records attributed to Yangming Li.

33 records · Page 2Linked to original sources

arXiv2021

Rewriter-Evaluator Architecture for Neural Machine Translation

Encoder-decoder has been widely used in neural machine translation (NMT). A few methods have been proposed to improve it with multiple passes of decoding. However, their full potential is limited by a lack of appropriate termination policies. To address this issue, we present a novel architecture, Rewriter-Evaluator. It consists of a rewriter and an evaluator. Translating a source sentence involves multiple passes. At every pass, the rewriter produces a new translation to improve the past translation and the evaluator estimates the translation quality to decide whether to terminate the rewriting process. We also propose prioritized gradient descent (PGD) that facilitates training the rewriter and the evaluator jointly. Though incurring multiple passes of decoding, Rewriter-Evaluator with the proposed PGD method can be trained with a similar time to that of training encoder-decoder models. We apply the proposed architecture to improve the general NMT models (e.g., Transformer). We conduct extensive experiments on two translation tasks, Chinese-English and English-German, and show that the proposed architecture notably improves the performances of NMT models and significantly outperforms previous baselines.

cs.CL↗

arXiv2021

Segmenting Natural Language Sentences via Lexical Unit Analysis

In this work, we present Lexical Unit Analysis (LUA), a framework for general sequence segmentation tasks. Given a natural language sentence, LUA scores all the valid segmentation candidates and utilizes dynamic programming (DP) to extract the maximum scoring one. LUA enjoys a number of appealing properties such as inherently guaranteeing the predicted segmentation to be valid and facilitating globally optimal training and inference. Besides, the practical time complexity of LUA can be reduced to linear time, which is very efficient. We have conducted extensive experiments on 5 tasks, including syntactic chunking, named entity recognition (NER), slot filling, Chinese word segmentation, and Chinese part-of-speech (POS) tagging, across 15 datasets. Our models have achieved the state-of-the-art performances on 13 of them. The results also show that the F1 score of identifying long-length segments is notably improved.

cs.CL↗

arXiv2021

Neural Sequence Segmentation as Determining the Leftmost Segments

Prior methods to text segmentation are mostly at token level. Despite the adequacy, this nature limits their full potential to capture the long-term dependencies among segments. In this work, we propose a novel framework that incrementally segments natural language sentences at segment level. For every step in segmentation, it recognizes the leftmost segment of the remaining sequence. Implementations involve LSTM-minus technique to construct the phrase representations and recurrent neural networks (RNN) to model the iterations of determining the leftmost segments. We have conducted extensive experiments on syntactic chunking and Chinese part-of-speech (POS) tagging across 3 datasets, demonstrating that our methods have significantly outperformed previous all baselines and achieved new state-of-the-art results. Moreover, qualitative analysis and the study on segmenting long-length sentences verify its effectiveness in modeling long-term dependencies.

cs.CL↗

arXiv2021

Empirical Analysis of Unlabeled Entity Problem in Named Entity Recognition

In many scenarios, named entity recognition (NER) models severely suffer from unlabeled entity problem, where the entities of a sentence may not be fully annotated. Through empirical studies performed on synthetic datasets, we find two causes of performance degradation. One is the reduction of annotated entities and the other is treating unlabeled entities as negative instances. The first cause has less impact than the second one and can be mitigated by adopting pretraining language models. The second cause seriously misguides a model in training and greatly affects its performances. Based on the above observations, we propose a general approach, which can almost eliminate the misguidance brought by unlabeled entities. The key idea is to use negative sampling that, to a large extent, avoids training NER models with unlabeled entities. Experiments on synthetic datasets and real-world datasets show that our model is robust to unlabeled entity problem and surpasses prior baselines. On well-annotated datasets, our model is competitive with the state-of-the-art method.

cs.CL↗

arXiv2021

Interpretable NLG for Task-oriented Dialogue Systems with Heterogeneous Rendering Machines

End-to-end neural networks have achieved promising performances in natural language generation (NLG). However, they are treated as black boxes and lack interpretability. To address this problem, we propose a novel framework, heterogeneous rendering machines (HRM), that interprets how neural generators render an input dialogue act (DA) into an utterance. HRM consists of a renderer set and a mode switcher. The renderer set contains multiple decoders that vary in both structure and functionality. For every generation step, the mode switcher selects an appropriate decoder from the renderer set to generate an item (a word or a phrase). To verify the effectiveness of our method, we have conducted extensive experiments on 5 benchmark datasets. In terms of automatic metrics (e.g., BLEU), our model is competitive with the current state-of-the-art method. The qualitative analysis shows that our model can interpret the rendering process of neural generators well. Human evaluation also confirms the interpretability of our proposed approach.

cs.CL↗

arXiv2020

TexSmart: A Text Understanding System for Fine-Grained NER and Enhanced Semantic Analysis

This technique report introduces TexSmart, a text understanding system that supports fine-grained named entity recognition (NER) and enhanced semantic analysis functionalities. Compared to most previous publicly available text understanding systems and tools, TexSmart holds some unique features. First, the NER function of TexSmart supports over 1,000 entity types, while most other public tools typically support several to (at most) dozens of entity types. Second, TexSmart introduces new semantic analysis functions like semantic expansion and deep semantic representation, that are absent in most previous systems. Third, a spectrum of algorithms (from very fast algorithms to those that are relatively slow but more accurate) are implemented for one function in TexSmart, to fulfill the requirements of different academic and industrial applications. The adoption of unsupervised or weakly-supervised algorithms is especially emphasized, with the goal of easily updating our models to include fresh data with less human annotation efforts. The main contents of this report include major functions of TexSmart, algorithms for achieving these functions, how to use the TexSmart toolkit and Web APIs, and evaluation results of some key algorithms.

cs.CL↗

arXiv2020

DCR-Net: A Deep Co-Interactive Relation Network for Joint Dialog Act Recognition and Sentiment Classification

In dialog system, dialog act recognition and sentiment classification are two correlative tasks to capture speakers intentions, where dialog act and sentiment can indicate the explicit and the implicit intentions separately. Most of the existing systems either treat them as separate tasks or just jointly model the two tasks by sharing parameters in an implicit way without explicitly modeling mutual interaction and relation. To address this problem, we propose a Deep Co-Interactive Relation Network (DCR-Net) to explicitly consider the cross-impact and model the interaction between the two tasks by introducing a co-interactive relation layer. In addition, the proposed relation layer can be stacked to gradually capture mutual knowledge with multiple steps of interaction. Especially, we thoroughly study different relation layers and their effects. Experimental results on two public datasets (Mastodon and Dailydialog) show that our model outperforms the state-of-the-art joint model by 4.3% and 3.4% in terms of F1 score on dialog act recognition task, 5.7% and 12.4% on sentiment classification respectively. Comprehensive analysis empirically verifies the effectiveness of explicitly modeling the relation between the two tasks and the multi-steps interaction mechanism. Finally, we employ the Bidirectional Encoder Representation from Transformer (BERT) in our framework, which can further boost our performance in both tasks.

cs.CL↗

arXiv2020

LC-GAN: Image-to-image Translation Based on Generative Adversarial Network for Endoscopic Images

Intelligent vision is appealing in computer-assisted and robotic surgeries. Vision-based analysis with deep learning usually requires large labeled datasets, but manual data labeling is expensive and time-consuming in medical problems. We investigate a novel cross-domain strategy to reduce the need for manual data labeling by proposing an image-to-image translation model live-cadaver GAN (LC-GAN) based on generative adversarial networks (GANs). We consider a situation when a labeled cadaveric surgery dataset is available while the task is instrument segmentation on an unlabeled live surgery dataset. We train LC-GAN to learn the mappings between the cadaveric and live images. For live image segmentation, we first translate the live images to fake-cadaveric images with LC-GAN and then perform segmentation on the fake-cadaveric images with models trained on the real cadaveric dataset. The proposed method fully makes use of the labeled cadaveric dataset for live image segmentation without the need to label the live dataset. LC-GAN has two generators with different architectures that leverage the deep feature representation learned from the cadaveric image based segmentation task. Moreover, we propose the structural similarity loss and segmentation consistency loss to improve the semantic consistency during translation. Our model achieves better image-to-image translation and leads to improved segmentation performance in the proposed cross-domain segmentation task.

eess.IV↗

arXiv2020

Towards Better Surgical Instrument Segmentation in Endoscopic Vision: Multi-Angle Feature Aggregation and Contour Supervision

Accurate and real-time surgical instrument segmentation is important in the endoscopic vision of robot-assisted surgery, and significant challenges are posed by frequent instrument-tissue contacts and continuous change of observation perspective. For these challenging tasks more and more deep neural networks (DNN) models are designed in recent years. We are motivated to propose a general embeddable approach to improve these current DNN segmentation models without increasing the model parameter number. Firstly, observing the limited rotation-invariance performance of DNN, we proposed the Multi-Angle Feature Aggregation (MAFA) method, leveraging active image rotation to gain richer visual cues and make the prediction more robust to instrument orientation changes. Secondly, in the end-to-end training stage, the auxiliary contour supervision is utilized to guide the model to learn the boundary awareness, so that the contour shape of segmentation mask is more precise. The proposed method is validated with ablation experiments on the novel Sinus-Surgery datasets collected from surgeons' operations, and is compared to the existing methods on a public dataset collected with a da Vinci Xi Robot.

cs.CV↗

arXiv2020

Finite Groups with Some s-semipermutable subgroups

Suppose that $G$ is a finite group and $H$ is a subgroup of $G$. We say that $H$ is s-semipermutable in $G$ if $HG_p = G_pH$ for any Sylow $p$-subgroup $G_p$ of $G$ with $(p, |H|) = 1$. We investigate the influence of s-semipermutable subgroups on the structure of finite groups. Some recent results are generalized.

math.GR↗

arXiv2019

Entity-Consistent End-to-end Task-Oriented Dialogue System with KB Retriever

Querying the knowledge base (KB) has long been a challenge in the end-to-end task-oriented dialogue system. Previous sequence-to-sequence (Seq2Seq) dialogue generation work treats the KB query as an attention over the entire KB, without the guarantee that the generated entities are consistent with each other. In this paper, we propose a novel framework which queries the KB in two steps to improve the consistency of generated entities. In the first step, inspired by the observation that a response can usually be supported by a single KB row, we introduce a KB retrieval component which explicitly returns the most relevant KB row given a dialogue history. The retrieval result is further used to filter the irrelevant entities in a Seq2Seq response generation model to improve the consistency among the output entities. In the second step, we further perform the attention mechanism to address the most correlated KB column. Two methods are proposed to make the training feasible without labeled retrieval data, which include distant supervision and Gumbel-Softmax technique. Experiments on two publicly available task oriented dialog datasets show the effectiveness of our model by outperforming the baseline systems and producing entity-consistent responses.

cs.CL↗

arXiv2019

A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding

Intent detection and slot filling are two main tasks for building a spoken language understanding (SLU) system. The two tasks are closely tied and the slots often highly depend on the intent. In this paper, we propose a novel framework for SLU to better incorporate the intent information, which further guides the slot filling. In our framework, we adopt a joint model with Stack-Propagation which can directly use the intent information as input for slot filling, thus to capture the intent semantic knowledge. In addition, to further alleviate the error propagation, we perform the token-level intent detection for the Stack-Propagation framework. Experiments on two publicly datasets show that our model achieves the state-of-the-art performance and outperforms other previous methods by a large margin. Finally, we use the Bidirectional Encoder Representation from Transformer (BERT) model in our framework, which further boost our performance in SLU task.

cs.CL↗

arXiv2019

Raven: Open Surgical Robotic Platforms

The Raven I and the Raven II surgical robots, as open research platforms, have been serving the robotic surgery research community for ten years. The paper 1) briefly presents the Raven I and the Raven II robots, 2) reviews the recent publications that are built upon the Raven robots, aim to be applied to the Raven robots, or are directly compared with the Raven robots, and 3) uses the Raven robots as a case study to discuss the popular research problems in the research community and the trend of robotic surgery study. Instead of being a thorough literature review, this work only reviews the works formally published in the past three years and uses these recent publications to analyze the research interests, the popular open research problems, and opportunities in the topic of robotic surgery.

cs.RO↗

arXiv2019

Robotic Supervised Autonomy: A Review

This invited paper discusses a new but important problem, supervised autonomy, in the context of robotics. The paper defines supervised autonomy and compares the supervised autonomy with robotic teleoperation and robotic full autonomy. Based on the discussion, the significance of supervised autonomy was introduced. The paper discusses the challenging and unsolved problems in supervised autonomy, and reviews the related works in our research lab. Based on the discussions, the paper draws the conclusion that supervised autonomy is critical for applying robotic systems to address complicated problems in the real world.

cs.RO↗

arXiv2016

Simulation Results on Selector Adaptation in Behavior Trees

Behavior trees (BTs) emerged from video game development as a graphical language for modeling intelligent agent behavior. However as initially implemented, behavior trees are static plans. This paper adds to recent literature exploring the ability of BTs to adapt to their success or failure in achieving tasks. The "Selector" node of a BT tries alternative strategies (its children) and returns success only if all of its children return failure. This paper studies several means by which Selector nodes can learn from experience, in particular, learn conditional probabilities of success based on sensor information, and modify the execution order based on the learned iformation. Furthermore, a "Greedy Selector" is studied which only tries the child having the highest success probability. Simulation results indicate significantly increased task performance, especially when frequentist probability estimate is conditioned on sensor information. The Greedy selector was ineffective unless it was preceded by a period of training in which all children were exercised.

cs.RO↗