Yao Wan


pdf bib
Modeling Hierarchical Syntax Structure with Triplet Position for Source Code Summarization
Juncai Guo | Jin Liu | Yao Wan | Li Li | Pingyi Zhou
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Automatic code summarization, which aims to describe the source code in natural language, has become an essential task in software maintenance. Our fellow researchers have attempted to achieve such a purpose through various machine learning-based approaches. One key challenge keeping these approaches from being practical lies in the lacking of retaining the semantic structure of source code, which has unfortunately been overlooked by the state-of-the-art. Existing approaches resort to representing the syntax structure of code by modeling the Abstract Syntax Trees (ASTs). However, the hierarchical structures of ASTs have not been well explored. In this paper, we propose CODESCRIBE to model the hierarchical syntax structure of code by introducing a novel triplet position for code summarization. Specifically, CODESCRIBE leverages the graph neural network and Transformer to preserve the structural and sequential information of code, respectively. In addition, we propose a pointer-generator network that pays attention to both the structure and sequential tokens of code for a better summary generation. Experiments on two real-world datasets in Java and Python demonstrate the effectiveness of our proposed approach when compared with several state-of-the-art baselines.

pdf bib
Are Pre-trained Transformers Robust in Intent Classification? A Missing Ingredient in Evaluation of Out-of-Scope Intent Detection
Jianguo Zhang | Kazuma Hashimoto | Yao Wan | Zhiwei Liu | Ye Liu | Caiming Xiong | Philip Yu
Proceedings of the 4th Workshop on NLP for Conversational AI

Pre-trained Transformer-based models were reported to be robust in intent classification. In this work, we first point out the importance of in-domain out-of-scope detection in few-shot intent recognition tasks and then illustrate the vulnerability of pre-trained Transformer-based models against samples that are in-domain but out-of-scope (ID-OOS). We construct two new datasets, and empirically show that pre-trained models do not perform well on both ID-OOS examples and general out-of-scope examples, especially on fine-grained few-shot intent detection tasks.

pdf bib
Compilable Neural Code Generation with Compiler Feedback
Xin Wang | Yasheng Wang | Yao Wan | Fei Mi | Yitong Li | Pingyi Zhou | Jin Liu | Hao Wu | Xin Jiang | Qun Liu
Findings of the Association for Computational Linguistics: ACL 2022

Automatically generating compilable programs with (or without) natural language descriptions has always been a touchstone problem for computational linguistics and automated software engineering. Existing deep-learning approaches model code generation as text generation, either constrained by grammar structures in decoder, or driven by pre-trained language models on large-scale code corpus (e.g., CodeGPT, PLBART, and CodeT5). However, few of them account for compilability of the generated programs. To improve compilability of the generated programs, this paper proposes COMPCODER, a three-stage pipeline utilizing compiler feedback for compilable code generation, including language model fine-tuning, compilability reinforcement, and compilability discrimination. Comprehensive experiments on two code generation tasks demonstrate the effectiveness of our proposed approach, improving the success rate of compilation from 44.18 to 89.18 in code completion on average and from 70.3 to 96.2 in text-to-code generation, respectively, when comparing with the state-of-the-art CodeGPT.


pdf bib
Enriching Non-Autoregressive Transformer with Syntactic and Semantic Structures for Neural Machine Translation
Ye Liu | Yao Wan | Jianguo Zhang | Wenting Zhao | Philip Yu
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume

The non-autoregressive models have boosted the efficiency of neural machine translation through parallelized decoding at the cost of effectiveness, when comparing with the autoregressive counterparts. In this paper, we claim that the syntactic and semantic structures among natural language are critical for non-autoregressive machine translation and can further improve the performance. However, these structures are rarely considered in the existing non-autoregressive models. Inspired by this intuition, we propose to incorporate the explicit syntactic and semantic structure of languages into a non-autoregressive Transformer, for the task of neural machine translation. Moreover, we also consider the intermediate latent alignment within target sentences to better learn the long-term token dependencies. Experimental results on two real-world datasets (i.e., WMT14 En-De and WMT16 En- Ro) show that our model achieves a significantly faster speed, as well as keeps the translation quality when compared with several state-of-the-art non-autoregressive models.

pdf bib
Disentangled Code Representation Learning for Multiple Programming Languages
Jingfeng Zhang | Haiwen Hong | Yin Zhang | Yao Wan | Ye Liu | Yulei Sui
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
Attend, Memorize and Generate: Towards Faithful Table-to-Text Generation in Few Shots
Wenting Zhao | Ye Liu | Yao Wan | Philip Yu
Findings of the Association for Computational Linguistics: EMNLP 2021

Few-shot table-to-text generation is a task of composing fluent and faithful sentences to convey table content using limited data. Despite many efforts having been made towards generating impressive fluent sentences by fine-tuning powerful pre-trained language models, the faithfulness of generated content still needs to be improved. To this end, this paper proposes a novel approach Attend, Memorize and Generate (called AMG), inspired by the text generation process of humans. In particular, AMG (1) attends over the multi-granularity of context using a novel strategy based on table slot level and traditional token-by-token level attention to exploit both the table structure and natural linguistic information; (2) dynamically memorizes the table slot allocation states; and (3) generates faithful sentences according to both the context and memory allocation states. Comprehensive experiments with human evaluation on three domains (i.e., humans, songs, and books) of the Wiki dataset show that our model can generate higher qualified texts when compared with several state-of-the-art baselines, in both fluency and faithfulness.

pdf bib
HETFORMER: Heterogeneous Transformer with Sparse Attention for Long-Text Extractive Summarization
Ye Liu | Jianguo Zhang | Yao Wan | Congying Xia | Lifang He | Philip Yu
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

To capture the semantic graph structure from raw text, most existing summarization approaches are built on GNNs with a pre-trained model. However, these methods suffer from cumbersome procedures and inefficient computations for long-text documents. To mitigate these issues, this paper proposes HetFormer, a Transformer-based pre-trained model with multi-granularity sparse attentions for long-text extractive summarization. Specifically, we model different types of semantic nodes in raw text as a potential heterogeneous graph and directly learn heterogeneous relationships (edges) among nodes by Transformer. Extensive experiments on both single- and multi-document summarization tasks show that HetFormer achieves state-of-the-art performance in Rouge F1 while using less memory and fewer parameters.

pdf bib
Fix-Filter-Fix: Intuitively Connect Any Models for Effective Bug Fixing
Haiwen Hong | Jingfeng Zhang | Yin Zhang | Yao Wan | Yulei Sui
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Locating and fixing bugs is a time-consuming task. Most neural machine translation (NMT) based approaches for automatically bug fixing lack generality and do not make full use of the rich information in the source code. In NMT-based bug fixing, we find some predicted code identical to the input buggy code (called unchanged fix) in NMT-based approaches due to high similarity between buggy and fixed code (e.g., the difference may only appear in one particular line). Obviously, unchanged fix is not the correct fix because it is the same as the buggy code that needs to be fixed. Based on these, we propose an intuitive yet effective general framework (called Fix-Filter-Fix or Fˆ3) for bug fixing. Fˆ3 connects models with our filter mechanism to filter out the last model’s unchanged fix to the next. We propose an Fˆ3 theory that can quantitatively and accurately calculate the Fˆ3 lifting effect. To evaluate, we implement the Seq2Seq Transformer (ST) and the AST2Seq Transformer (AT) to form some basic Fˆ3 instances, called Fˆ3_ST+AT and Fˆ3_AT+ST. Comparing them with single model approaches and many model connection baselines across four datasets validates the effectiveness and generality of Fˆ3 and corroborates our findings and methodology.


pdf bib
Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference
Jianguo Zhang | Kazuma Hashimoto | Wenhao Liu | Chien-Sheng Wu | Yao Wan | Philip Yu | Richard Socher | Caiming Xiong
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Intent detection is one of the core components of goal-oriented dialog systems, and detecting out-of-scope (OOS) intents is also a practically important skill. Few-shot learning is attracting much attention to mitigate data scarcity, but OOS detection becomes even more challenging. In this paper, we present a simple yet effective approach, discriminative nearest neighbor classification with deep self-attention. Unlike softmax classifiers, we leverage BERT-style pairwise encoding to train a binary classifier that estimates the best matched training example for a user input. We propose to boost the discriminative ability by transferring a natural language inference (NLI) model. Our extensive experiments on a large-scale multi-domain intent detection task show that our method achieves more stable and accurate in-domain and OOS detection accuracy than RoBERTa-based classifiers and embedding-based nearest neighbor approaches. More notably, the NLI transfer enables our 10-shot model to perform competitively with 50-shot or even full-shot classifiers, while we can keep the inference time constant by leveraging a faster embedding retrieval model.


pdf bib
Multi-Modal Generative Adversarial Network for Short Product Title Generation in Mobile E-Commerce
Jianguo Zhang | Pengcheng Zou | Zhao Li | Yao Wan | Xiuming Pan | Yu Gong | Philip S. Yu
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Industry Papers)

Nowadays, more and more customers browse and purchase products in favor of using mobile E-Commerce Apps such as Taobao and Amazon. Since merchants are usually inclined to describe redundant and over-informative product titles to attract attentions from customers, it is important to concisely display short product titles on limited screen of mobile phones. To address this discrepancy, previous studies mainly consider textual information of long product titles and lacks of human-like view during training and evaluation process. In this paper, we propose a Multi-Modal Generative Adversarial Network (MM-GAN) for short product title generation in E-Commerce, which innovatively incorporates image information and attribute tags from product, as well as textual information from original long titles. MM-GAN poses short title generation as a reinforcement learning process, where the generated titles are evaluated by the discriminator in a human-like view. Extensive experiments on a large-scale E-Commerce dataset demonstrate that our algorithm outperforms other state-of-the-art methods. Moreover, we deploy our model into a real-world online E-Commerce environment and effectively boost the performance of click through rate and click conversion rate by 1.66% and 1.87%, respectively.