Related papers: code2seq: Generating Sequences from Structured Rep…

We present OpenSeq2Seq - a TensorFlow-based toolkit for training sequence-to-sequence models that features distributed and mixed-precision training. Benchmarks on machine translation and speech recognition tasks show that models built using…

Mobile app reviews are a large-scale data source for software improvements. A key task in this context is effectively extracting requirements from app reviews to analyze the users' needs and support the software's evolution. Recent studies…

In neural abstractive summarization, the conventional sequence-to-sequence (seq2seq) model often suffers from repetition and semantic irrelevance. To tackle the problem, we propose a global encoding framework, which controls the information…

Designing novel protein sequences for a desired 3D topological fold is a fundamental yet non-trivial task in protein engineering. Challenges exist due to the complex sequence--fold relationship, as well as the difficulties to capture the…

Many software analysis methods have come to rely on machine learning approaches. Code segmentation - the process of decomposing source code into meaningful blocks - can augment these methods by featurizing code, reducing noise, and limiting…

With the recent success of embeddings in natural language processing, research has been conducted into applying similar methods to code analysis. Most works attempt to process the code directly or use a syntactic tree representation,…

Conditional set generation learns a mapping from an input sequence of tokens to a set. Several NLP tasks, such as entity typing and dialogue emotion tagging, are instances of set generation. Seq2Seq models, a popular choice for set…

Recently, the automated translation of source code from one programming language to another by using automatic approaches inspired by Neural Machine Translation (NMT) methods for natural languages has come under study. However, such…

Sequence-to-sequence (seq2seq) learning is a popular fashion for large-scale pretraining language models. However, the prior seq2seq pretraining models generally focus on reconstructive objectives on the decoder side and neglect the effect…

Sequence-to-sequence (seq2seq) approach for low-resource ASR is a relatively new direction in speech research. The approach benefits by performing model training without using lexicon and alignments. However, this poses a new problem of…

We propose Seq2Edits, an open-vocabulary approach to sequence editing for natural language processing (NLP) tasks with a high degree of overlap between input and output texts. In this approach, each sequence-to-sequence transduction is…

There is mounting evidence that existing neural network models, in particular the very popular sequence-to-sequence architecture, struggle to systematically generalize to unseen compositions of seen components. We demonstrate that one of…

Sequence-to-sequence translation methods based on generation with a side-conditioned language model have recently shown promising results in several tasks. In machine translation, models conditioned on source side words have been used to…

Source code segmentation, dividing code into functionally coherent segments, is crucial for knowledge retrieval and maintenance in software development. While enabling efficient navigation and comprehension of large codebases, manual and…

We consider the problem of crystal materials generation using language models (LMs). A key step is to convert 3D crystal structures into 1D sequences to be processed by LMs. Prior studies used the crystallographic information framework…

This paper presents a new unified approach to semantic segmentation in both images and videos by using language modeling to output the masks as sequences of discrete tokens. We use run length encoding (RLE) to discretize the segmentation…

Seq2seq models have been shown to struggle with compositional generalization in semantic parsing, i.e. generalizing to unseen compositions of phenomena that the model handles correctly in isolation. We phrase semantic parsing as a two-step…

Neural machine translation (NMT) usually works in a seq2seq learning way by viewing either source or target sentence as a linear sequence of words, which can be regarded as a special case of graph, taking words in the sequence as nodes and…

Program source code contains complex structure information, which can be represented in structured data forms like trees or graphs. To acquire the structural information in source code, most existing researches use abstract syntax trees…

Recent advances in Neural Machine Translation (NMT) show that adding syntactic information to NMT systems can improve the quality of their translations. Most existing work utilizes some specific types of linguistically-inspired tree…