Yanli Wang, Yanlin Wang, Bowen Zhang, Yiwei Zhang, Daya Guo, Jiachi Chen, Hongyu Zhang, Zibin Zheng. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Repository-level code translation refers to translating an entire code repository from one programming language to another while preserving the functionality of the source repository. Many benchmarks have been proposed to evaluate the performance of such code translators. However, previous benchmarks mostly provide fine-grained samples, focusing at either code snippet, function, or file-level code translation. Such benchmarks do not accurately reflect real-world demands, where entire repositories often need to be translated, involving longer code length and more complex functionalities. To address this gap, we propose a new benchmark, named RepoTransBench, which is a real-world multilingual repository-level code translation benchmark featuring 1,897 real-world repository samples across 13 language pairs with automatically executable test suites. Besides, we introduce RepoTransAgent, a general agent framework to perform repository-level code translation. We evaluate both our benchmark’s challenges and agent’s effectiveness using several methods and backbone LLMs, revealing that repository-level translation remains challenging, where the best-performing method achieves only a 32.8% success rate. Furthermore, our analysis reveals that translation difficulty varies significantly by language pair direction, with dynamic-to-static language translation being much more challenging than the reverse direction (achieving below 10% vs. static-to-dynamic at 45-63%). Finally, we conduct a detailed error analysis and highlight current LLMs’ deficiencies in repository-level code translation, which could provide a reference for further improvements. We provide the code and data athttps://github.com/DeepSoftwareAnalytics/RepoTransBench.

Reasoning is a fundamental capability of Large Language Models. While prior research predominantly focuses on enhancing narrow skills like math or code generation, improving performance on many other reasoning tasks remains challenging due to sparse and fragmented training data. To address this issue, we propose CodeI/O, a novel approach that systematically condenses diverse reasoning patterns inherently embedded in contextually-grounded codes, through transforming the original code into a code input-output prediction format. By training models to predict inputs/outputs given code and test cases entirely in natural language as Chain-of-Thought (CoT) rationales, we expose them to universal reasoning primitives—like logic flow planning, state-space searching, decision tree traversal, and modular decomposition—while decoupling structured reasoning from code-specific syntax and preserving procedural rigor. Experimental results demonstrate CodeI/O leads to consistent improvements across symbolic, scientific, logic, math & numerical, and commonsense reasoning tasks. By matching the existing ground-truth outputs or re-executing the code with predicted inputs, we can verify each prediction and further enhance the CoTs through multi-turn revision, resulting in CodeI/O++ and achieving higher performance. Our data and models will be publicly available.

Repository-level code completion aims to generate code for unfinished code snippets within the context of a specified repository. Existing approaches mainly rely on retrievalaugmented generation strategies due to limitations in input sequence length. However, traditional lexical-based retrieval methods like BM25 struggle to capture code semantics, while model-based retrieval methods face challenges due to the lack of labeled data for training. Therefore, we propose RLCoder, a novel reinforcement learning framework, which can enable the retriever to learn to retrieve useful content for code completion without the need for labeled data. Specifically, we iteratively evaluate the usefulness of retrieved content based on the perplexity of the target code when provided with the retrieved content as additional context, and provide feedback to update the retriever parameters. This iterative process enables the retriever to learn from its successes and failures, gradually improving its ability to retrieve relevant and high-quality content. Considering that not all situations require information beyond code files and not all retrieved context is helpful for generation, we also introduce a stop signal mechanism, allowing the retriever to decide when to retrieve and which candidates to retain autonomously. Extensive experimental results demonstrate that RLCoder consistently outperforms state-of-the-art methods on CrossCodeEval and RepoEval, achieving 12.2% EM improvement over previous methods. Moreover, experiments show that our framework can generalize across different programming languages and further improve previous methods like RepoCoder. We provide the code and data at https://github.com/DeepSoftwareAnalytics/RLCoder.

Repository-level code completion remains a challenging task for existing code large language models (code LLMs) due to their limited understanding of repository-specific context and domain knowledge. While retrieval-augmented generation (RAG) approaches have shown promise by retrieving relevant code snippets as cross-file context, they suffer from two fundamental problems: misalignment between the query and the target code in the retrieval process, and the inability of existing retrieval methods to effectively utilize the inference information. To address these challenges, we propose AlignCoder, a repository-level code completion framework that introduces a query enhancement mechanism and a reinforcement learning based retriever training method. Our approach generates multiple candidate completions to construct an enhanced query that bridges the semantic gap between the initial query and the target code. Additionally, we employ reinforcement learning to train an AlignRetriever that learns to leverage inference information in the enhanced query for more accurate retrieval. We evaluate AlignCoder on two widely-used benchmarks (CrossCodeEval and RepoEval) across five backbone code LLMs, demonstrating an 18.1% improvement in EM score compared to baselines on the CrossCodeEval benchmark. The results show that our framework achieves superior performance and exhibits high generalizability across various code LLMs and programming languages.

Since the advent of ChatGPT, large language models (LLMs) have attracted widespread attention from academia and industry. They have also brought significant changes to software engineering. However, until now, there has been a lack of comprehensive studies comparing LLMs with previous smaller code pre-trained models. To address this gap, we conduct a study in this paper to illustrate the performance of LLMs in different software engineering tasks. Specifically, we select three open-source large language models, CodeGen, LLaMA, and StarCoder, for the research targets, and our study is conducted from four aspects, including code syntax understanding, code semantic reasoning, encoding representation quality, and adaptation performance for different software engineering tasks to compare LLMs with previous code pre-trained models. Four aspects build on each other, forming important components of AI for Software Engineering.We conclude that: (1) Compared with previous smaller pre-trained models like CodeBERT, LLMs exhibit distinct trends in how they learn code syntax or semantics as the number of layers increases. Additionally, mastering code semantics proves to be more challenging, with semantic information usually learned in the final layers; (2) Causal decoder architecture with left-to-right attention masking does not perform well in zero-shot tasks; (3) For classification tasks, the mean vector representation generated by LLMs over a sequence tends to outperform the last token representation in the sequence; (4) Incorporating parameter-efficient fine-tuning techniques into LLMs for downstream tasks can help LLMs achieve better performance than previous code pre-trained models on code generation tasks but may not be optimal in some code understanding tasks; (5) LoRA emerges as a more effective PEFT technique for LLMs in downstream code-related tasks. We hope these findings will better guide future researchers in designing more powerful code models.

Data wrangling, the process of preparing raw data for further analysis in computational notebooks, is a crucial yet time-consuming step in data science. Code generation has the potential to automate the data wrangling process to reduce analysts' overhead by translating user intents into executable code. Precisely generating data wrangling code necessitates a comprehensive consideration of the rich context present in notebooks, including textual context, code context and data context. However, notebooks often interleave multiple non-linear analysis tasks into linear sequence of code blocks, where the contextual dependencies are not clearly reflected. Directly training models with source code blocks fails to fully exploit the contexts for accurate wrangling code generation.

Code summarization aims to generate natural language descriptions of source code, facilitating programmers to understand and maintain it rapidly. While previous code summarization efforts have predominantly focused on method-level, this paper studies file-level code summarization, which can assist programmers in understanding and maintaining large source code projects. Unlike method-level code summarization, file-level code summarization typically involves long source code within a single file, which makes it challenging for Transformer-based models to understand the code semantics for the maximum input length of these models is difficult to set to a large number that can handle long code input well, due to the quadratic scaling of computational complexity with the input sequence length. To address this challenge, we propose SparseCoder, an identifier-aware sparse transformer for effectively handling long code sequences. Specifically, the SparseCoder employs a sliding window mechanism for self-attention to model short-term dependencies and leverages the structure message of code to capture long-term dependencies among source code identifiers by introducing two types of sparse attention patterns named global and identifier attention. To evaluate the performance of SparseCoder, we construct a new dataset FILE-CS for file-level code summarization in Python. Experimental results show that our SparseCoder model achieves state-of-the-art performance compared with other pre-trained models, including full self-attention and sparse models. Additionally, our model has low memory overhead and achieves comparable performance with models using full self-attention mechanism. Furthermore, we verify the generality of SparseCoder on other code understanding tasks, i.e., code clone detection and code search, and results show that our model outperforms baseline models in both tasks, demonstrating that our model can generate better code representations for various downstream tasks. Our source code and experimental data are anonymously available at: https://github.com/DeepSoftwareAnalytics/SparseCoder.

Chat models, such as ChatGPT, have shown impressive capabilities and have been rapidly adopted across numerous domains.However, these models are only accessible through a restricted API, creating barriers for new research and progress in the field.We propose a pipeline that can automatically generate a highquality multi-turn chat corpus by leveraging ChatGPT to engage in a conversation with itself.Subsequently, we employ parameter-efficient tuning to enhance LLaMA, an open-source large language model.The resulting model, named Baize, demonstrates good performance in multi-turn dialogues with guardrails that minimize potential risks.Additionally, we propose a new technique called Self-Distill with Feedback, to further improve the performance of the Baize models with feedback from ChatGPT.The Baize models and data are released for research purposes only. 1

In this paper, we introduce a new task for code completion that focuses on handling long code input and propose a sparse Transformer model, called LongCoder, to address this task. LongCoder employs a sliding window mechanism for self-attention and introduces two types of globally accessible tokens - bridge tokens and memory tokens - to improve performance and efficiency. Bridge tokens are inserted throughout the input sequence to aggregate local information and facilitate global interaction, while memory tokens are included to highlight important statements that may be invoked later and need to be memorized, such as package imports and definitions of classes, functions, or structures. We conduct experiments on a newly constructed dataset that contains longer code context and the publicly available CodeXGLUE benchmark. Experimental results demonstrate that LongCoder achieves superior performance on code completion tasks compared to previous models while maintaining comparable efficiency in terms of computational resources during inference.

Pre-trained models for programming languages have recently demonstrated great success on code intelligence.To support both code-related understanding and generation tasks, recent works attempt to pre-train unified encoder-decoder models.However, such encoder-decoder framework is sub-optimal for auto-regressive tasks, especially code completion that requires a decoder-only manner for efficient inference.In this paper, we present UniXcoder, a unified cross-modal pre-trained model for programming language.The model utilizes mask attention matrices with prefix adapters to control the behavior of the model and leverages cross-modal contents like AST and code comment to enhance code representation.To encode AST that is represented as a tree in parallel, we propose a one-to-one mapping method to transform AST in a sequence structure that retains all structural information from the tree.Furthermore, we propose to utilize multi-modal contents to learn representation of code fragment with contrastive learning, and then align representations among programming languages using a cross-modal generation task.We evaluate UniXcoder on five code-related tasks over nine datasets.To further evaluate the performance of code fragment representation, we also construct a dataset for a new task, called zero-shot code-to-code search.Results show that our model achieves state-of-the-art performance on most tasks and analysis reveals that comment and AST can both enhance UniXcoder.

Code completion, which aims to predict the following code token(s) according to the code context, can improve the productivity of software development.Recent work has proved that statistical language modeling with transformers can greatly improve the performance in the code completion task via learning from large-scale source code datasets.However, current approaches focus only on code context within the file or project, i.e. internal context.Our distinction is utilizing "external" context, inspired by human behaviors of copying from the related code snippets when writing code.Specifically, we propose a retrieval-augmented code completion framework, leveraging both lexical copying and referring to code with similar semantics by retrieval.We adopt a stagewise training approach that combines a source code retriever and an auto-regressive language model for programming language.We evaluate our approach in the code completion task in Python and Java programming languages, achieving a state-of-the-art performance on CodeXGLUE benchmark.

Code review is an essential part to software development lifecycle since it aims at guaranteeing the quality of codes. Modern code review activities necessitate developers viewing, understanding and even running the programs to assess logic, functionality, latency, style and other factors. It turns out that developers have to spend far too much time reviewing the code of their peers. Accordingly, it is in significant demand to automate the code review process. In this research, we focus on utilizing pre-training techniques for the tasks in the code review scenario. We collect a large-scale dataset of real-world code changes and code reviews from open-source projects in nine of the most popular programming languages. To better understand code diffs and reviews, we propose CodeReviewer, a pre-trained model that utilizes four pre-training tasks tailored specifically for the code review scenario. To evaluate our model, we focus on three key tasks related to code review activities, including code change quality estimation, review comment generation and code refinement. Furthermore, we establish a high-quality benchmark dataset based on our collected data for these three tasks and conduct comprehensive experiments on it. The experimental results demonstrate that our model outperforms the previous state-of-the-art pre-training approaches in all tasks. Further analysis show that our proposed pre-training tasks and the multilingual pre-training dataset benefit the model on the understanding of code changes and reviews.

Zenan Xu, Daya Guo, Duyu Tang, Qinliang Su, Linjun Shou, Ming Gong, Wanjun Zhong, Xiaojun Quan, Daxin Jiang, Nan Duan. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Video advertisement content structuring aims to segment a given video advertisement and label each segment on various dimensions, such as presentation form, scene, and style. Different from real-life videos, video advertisements contain sufficient and useful multi-modal content like caption and speech, which provides crucial video semantics and would enhance the structuring process. In this paper, we propose a multi-modal encoder to learn multi-modal representation from video advertisements by interacting between video-audio and text. Based on multi-modal representation, we then apply Boundary-Matching Network to generate temporal proposals. To make the proposals more accurate, we refine generated proposals by scene-guided alignment and re-ranking. Finally, we incorporate proposal located embeddings into the introduced multi-modal encoder to capture temporal relationships between local features of each proposal and global features of the whole video for classification. Experimental results show that our method achieves significantly improvement compared with several baselines and Rank 1 on the task of Multi-modal Ads Video Understanding in ACM Multimedia 2021 Grand Challenge. Ablation study further shows that leveraging multi-modal content like caption and speech in video advertisements significantly improve the performance.

Commonsense question answering aims to answer questions which require background knowledge that is not explicitly expressed in the question. The key challenge is how to obtain evidence from external knowledge and make predictions based on the evidence. Recent studies either learn to generate evidence from human-annotated evidence which is expensive to collect, or extract evidence from either structured or unstructured knowledge bases which fails to take advantages of both sources simultaneously. In this work, we propose to automatically extract evidence from heterogeneous knowledge sources, and answer questions based on the extracted evidence. Specifically, we extract evidence from both structured knowledge base (i.e. ConceptNet) and Wikipedia plain texts. We construct graphs for both sources to obtain the relational structures of evidence. Based on these graphs, we propose a graph-based approach consisting of a graph-based contextual word representation learning module and a graph-based inference module. The first module utilizes graph structural information to re-define the distance between words for learning better contextual word representations. The second module adopts graph convolutional network to encode neighbor information into the representations of nodes, and aggregates evidence with graph attention mechanism for predicting the final answer. Experimental results on CommonsenseQA dataset illustrate that our graph-based approach over both knowledge sources brings improvement over strong baselines. Our approach achieves the state-of-the-art accuracy (75.3%) on the CommonsenseQA dataset.

Generating inferential texts about an event in different perspectives requires reasoning over different contexts that the event occurs.Existing works usually ignore the context that is not explicitly provided, resulting in a context-independent semantic representation that struggles to support the generation.To address this, we propose an approach that automatically finds evidence for an event from a large text corpus, and leverages the evidence to guide the generation of inferential texts.Our approach works in an encoderdecoder manner and is equipped with a Vector Quantised-Variational Autoencoder, where the encoder outputs representations from a distribution over discrete variables.Such discrete representations enable automatically selecting relevant evidence, which not only facilitates evidence-aware generation, but also provides a natural way to uncover rationales behind the generation.Our approach provides state-ofthe-art performance on both Event2Mind and ATOMIC datasets.More importantly, we find that with discrete representations, our model selectively uses evidence to generate different inferential texts.

5 9 469 9 65 67 1 016 9 93969696 5 5 67 21 22 67 !"626 ! 5 67#$12 !6%5 6&5 6 '()*+(,,-,./0100234,5671 )8*+9 )2+):*72;01 < = )2>29 ?)8 = 9 1 @A B702C3,2CD)@E0F,8 01 ,8 @,.G9 C/01 0H20-@= 9 =023I8 ,+)= = 9 2C:B702CJ(,7:IA KA 4(9 20 !L9 +8 ,= ,. 1K)= )08 +(H= 9 0:G)9 M 9 2C:4(9 20 NOPQRSTUVWXYZ[X\\]SX^UVWXY_`\S\P`aRP`b^ NRPcW^O[^W^RPW^[VX^OdeQP_UVXbfQ\Qgc`bQV hi j 21 (9 =606)8 :k)68 )= )21020668 ,0+(1 ,9 2+,8 < 6,8 01 )8 )1 8 9 )?)3301 06,9 21 =0== 766,8 1 9 2C)?9 < 3)2+).,8+,21 )l1 < 3)6)23)21= )5021 9 +608 = 9 2C: = 7+(0=C)2)8 01 9 2C= ,78 +)+,3)+,239 1 9 ,2)3,2 1 ()+-0= =)2?9 8 ,25)21 Am780668 ,0+(201 78 0--@ +,5F9 2)=08 )1 8 9 )?0-5,3)-02305)1 0< -)08 2)8 : k()8 )1 ().,8 5)8-)08 2=1 ,n23= 9 59 -08301 < 06,9 21 =. 8 ,51 ()1 8 09 29 2C301 0:0231 ()-01 1 )8 +,2= 9 3)8 =8 )1 8 9 )?)3301 06,9 21 =0=06= )73,1 0= o .,8. 0= 103061 01 9 ,2A*6)+9 n+0--@:,788 )1 8 9 )?< )89 =0+,21 )l1 < 0k08 ))2+,3)8 < 3)+,3)85,3)-k9 1 (0-01 )21?08 9 0F-)k(9 +(1 0o)=+,21 )l1)2< ?9 8 ,25)219 21 ,+,2= 9 3)8 01 9 ,2:023,785)1 0< -)08 2)8-)08 2=1 ,71 9 -9 J)8 )1 8 9 )?)3301 06,9 21 = 9 205,3)-< 0C2,= 1 9 +5)1 0< -)08 29 2C608 039 C5 .,8. 0= 103061 01 9 ,2Ap)+,237+1)l6)8 9 5)21 = ,24mq4m/r0234*sH 301 0= )1 = :k()8 ) 1 ()+,21 )l18 ).)8 =1 ,+-0= =)2?9 8 ,25)219 2t H< uH+,3)=023+,2?)8 = 01 9 ,20-(9 = 1 ,8 @:8 )= 6)+< 1 9 ?)-@Ap)7=)=)v7)2+)< 1 ,< 0+1 9 ,25,3)-0= 1 ()F0= )=)5021 9 +608 = )8 :k(9 +(6)8 .,8 5=1 () = 1 01 )< ,. < 1 ()< 08 10++78 0+@,2F,1 (301 0= )1 = AK)< = 7-1 == (,k1 (01F,1 (1 ()+,21 )l1 < 0k08 )8 )1 8 9 )?< )80231 ()5)1 0< -)08 29 2C=1 8 01 )C@9 568 ,?)0+< +78 0+@:023,780668 ,0+(6)8 .,8 5=F)1 1 )81 (02 8 )1 8 9 )?)< 023< )39 1F0= )-9 2)= A w x 6 12 5 16 4,21 )l1 < 3)6)23)21= )5021 9 +608 = 9 2C09 5=1 ,506 0201 78 0--02C70C)71 1 )8 02+)1 ,0=1 8 7+1 78 0--,C9 < +0-.,8 5y )A CA= ,78 +)+,3)z+,239 1 9 ,2)3,20C9 ?< )2+,21 )l1y )A CA+-0= =)2?9 8 ,25)21 zy E9 2C)10-A : {|}~E,2C)10-A :{|}~j @@)8)10-A :{|}j @< )8)10-A :{|}*7(8)10-A :{|}*7(8023H8 1 J9 : {|}z A*1 02308 30668 ,0+()=1 @69 +0--@-)08 20,2)< = 9 J)< n1 = < 0--5,3)-,21 ())21 9 8 )1 8 09 29 2C301 0= )1 : k(9 +(9 =. )3k9 1 ()0+()l056-)9 239 ?9 370--@9 21 () 1 8 09 29 2C6(0= )02350o)=68 )39 +1 9 ,2=.,8)0+(1 )= 1 )l056-)9 21 ()9 2. )8 )2+)6(0= )A,k)?)8 :1 0o9 2C p,8 o3,2)k(9 -)1 (9 =071 (,8k0=029 21 )8 201L9 +8 ,= ,. 1 K)= )08 +(A +,3)C)2)8 01 9 ,20=02)l056-):68 ,C8 055)8 =7= 7< 0--@3,2,1k8 9 1 )+,3)=.8 ,5= +8 01 +(9 21 ()8 )0k,8 -3Ap()21 ()@k8 9 1 )069 )+),.+,3)920608 < 1 9 +7-08)2?9 8 ,25)21 :1 ()@1 @69 +0--@-)?)8 0C)60= 1 )l6)8 9 )2+),2k8 9 1 9 2C,88 )039 2C+,3)=9 21 ()= 9 59 < -08= 9 1 701 9 ,20=0C79 302+)AL)02k(9 -):301 06,9 21 = .,801 0= o50@?08 @k9 3)-@y 702C)10-A :{|}0z : 1 (7=9 19 =3)= 9 8 0F-)1 ,-)08 206)8 = ,20-9 J)35,3< )-.,81 ()1 08 C)1301 06,9 21 Aj 21 (9 =k,8 o:k)= 1 73@ (,k1 ,071 ,501 9 +0--@8 )1 8 9 )?)= 9 59 -08301 06,9 21 =9 2 0+,21 )l1 < 3)6)23)21= +)208 9 ,0237= )1 ()50=1 () = 766,8 1 9 2C)?9 3)2+)1 ,. 0+9 -9 1 01 )= )5021 9 +608 = 9 2CA '()8 )08 )8 )+)2101 1 )561 =01)l6-,9 1 9 2C8 )< 1 8 9 )?)3)l056-)=1 ,9 568 ,?)1 ()C)2)8 01 9 ,2,.-,C< 9 +0-.,8 50231 )l1 AK)1 8 9 )?)< 023< )39 10668 ,0+()= y 0= (9 5,1 ,)10-A :{|}702C)10-A :{|}Fp7 )10-A :{|}B7)10-A :{|}z1 @69 +0--@n8 = 17= )0 +,21 )l1 < 9 23)6)23)218 )1 8 9 )?)81 ,n231 ()5,= 18 )-< )?021301 06,9 21 :0231 ()27= )9 10=020339 1 9 ,20-9 2671,.1 ())39 1 9 2C5,3)-A,k)?)8:0+,21 )l1 < 0k08 )8 )1 8 9 )?)89 =?)8 @9 56,8 1 021.,81 ()1 0= o,.+,21 )l1 < 3)6)23)21= )5021 9 +608 = 9 2CA,8)l05< 6-)= :0== (,k29 29 C78 )}:+-0= =)2?9 8 ,25)21+02 ()-61 ()8 )1 8 9 )?)83)+9 3)k()1 ()81 ()3)= 9 8 )3+,3) ,. 9 =C)2)8 01 )3F@39 8 )+1 -@ +0--9 2C ,89 1 )8 01 9 2C1 () ¡08 8 0@ 1 ,9 2+8 )5)21)0+()-)5)21 A78 1 ()8 5,8 ):8 )1 8 9 )?)< 023< )39 10668 ,0+()=1 @69 +0--@+,2= 9 3)8,2-@,2) = 9 59 -08)l056-)1 ,)39 1 Aj 2=)5021 9 +608 = 9 2C:1 () 601 1 )8 2,.0= 1 8 7+1 78 0-,71 67150@+,5).8 ,539 .< .)8 )218 )1 8 9 )?)3)l056-)= A'()8 )0-= ,)l9 = 1k,8 o= 1 ,71 9 -9 J)57-1 9 6-))l056-)=1 ,C79 3)1 ()= )5021 9 + 608 = )8y 0@01 9)10-A :{|}702C)10-A :{|}0z : (,k)?)8 :1 ()= )0668 ,0+()=)9 1 ()87= )0()78 9 = 1 9 + k0@1 ,)l6-,9 11 ()8 )1 8 9 )?)3-,C9 +0-.,8 5= 7+(0= 9 2+8 )0= 9 2C1 ()68 ,F0F9 -9 1 @,.0+1 9 ,2=y 0@01 9)10-A : {|}z,87= )08 )-)?02+).72+1 9 ,23)= 9 C2)3023 -)08 2)3F0= )3,2)l6)8 1 9 = )0F,711 ()1 08 C)1-,C9 < +0-.,8 5y 702C)10-A :{|}0z Ap()2k)+,2= 9 3)8 1 ()+,21 )l1)2?9 8 ,25)21 :9 1 ¢ =2,21 8 9 ?9 0-1 ,3)= 9 C2

Tao Shen, Xiubo Geng, Tao Qin, Daya Guo, Duyu Tang, Nan Duan, Guodong Long, Daxin Jiang. 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 study how to learn a semantic parser of state-of-the-art accuracy with less supervised training data.We conduct our study on WikiSQL, the largest hand-annotated semantic parsing dataset to date.First, we demonstrate that question generation is an effective method that empowers us to learn a state-ofthe-art neural network based semantic parser with thirty percent of the supervised training data.Second, we show that applying question generation to the full supervised training data further improves the state-of-the-art model.In addition, we observe that there is a logarithmic relationship between the accuracy of a semantic parser and the amount of training data.

We present an approach to map utterances in conversation to logical forms, which will be executed on a large-scale knowledge base. To handle enormous ellipsis phenomena in conversation, we introduce dialog memory management to manipulate historical entities, predicates, and logical forms when inferring the logical form of current utterances. Dialog memory management is embodied in a generative model, in which a logical form is interpreted in a top-down manner following a small and flexible grammar. We learn the model from denotations without explicit annotation of logical forms, and evaluate it on a large-scale dataset consisting of 200K dialogs over 12.8M entities. Results verify the benefits of modeling dialog memory, and show that our semantic parsing-based approach outperforms a memory network based encoder-decoder model by a huge margin.