Related papers: Translating a Math Word Problem to an Expression T…

Neural sequence-to-sequence models are well established for applications which can be cast as mapping a single input sequence into a single output sequence. In this work, we focus on one-to-many sequence transduction problems, such as…

Entity coreference resolution is an important research problem with many applications, including information extraction and question answering. Coreference resolution for English has been studied extensively. However, there is relatively…

Pretrained language models have shown superior performance on many natural language processing tasks, yet they still struggle at multi-step formal reasoning tasks like grade school math problems. One key challenge of finetuning them to…

Recently, Chinese word segmentation (CWS) methods using neural networks have made impressive progress. Most of them regard the CWS as a sequence labeling problem which construct models based on local features rather than considering global…

We target the problem of automatically synthesizing proofs of semantic equivalence between two programs made of sequences of statements. We represent programs using abstract syntax trees (AST), where a given set of semantics-preserving…

Recent work showed that ML-based attacks on Learning with Errors (LWE), a hard problem used in post-quantum cryptography, outperform classical algebraic attacks in certain settings. Although promising, ML attacks struggle to scale to more…

Sequence-to-Sequence models were introduced to tackle many real-life problems like machine translation, summarization, image captioning, etc. The standard optimization algorithms are mainly based on example-to-example matching like maximum…

Prior work in semantic parsing has shown that conventional seq2seq models fail at compositional generalization tasks. This limitation led to a resurgence of methods that model alignments between sentences and their corresponding meaning…

We present a method to simplify expressions in the context of an equational theory. The basic ideas and concepts of the method have been presented previously elsewhere but here we tackle the difficult task of making it efficient in…

The absence of standardized spelling conventions and the organic evolution of human language present an inherent linguistic challenge within historical documents, a longstanding concern for scholars in the humanities. Addressing this issue,…

As human society transitions into the information age, reduction in our attention span is a contingency, and people who spend time reading lengthy news articles are decreasing rapidly and the need for succinct information is higher than…

In this paper, we investigate the benefit that off-the-shelf word embedding can bring to the sequence-to-sequence (seq-to-seq) automatic speech recognition (ASR). We first introduced the word embedding regularization by maximizing the…

Although Neural Machine Translation (NMT) has achieved remarkable progress in the past several years, most NMT systems still suffer from a fundamental shortcoming as in other sequence generation tasks: errors made early in generation…

We present AutoNMT, a framework to streamline the research of seq-to-seq models by automating the data pipeline (i.e., file management, data preprocessing, and exploratory analysis), automating experimentation in a toolkit-agnostic manner,…

This paper describes the design and implementation of a new machine learning model for online learning systems. We aim at improving the intelligent level of the systems by enabling an automated math word problem solver which can support a…

Since traditional tokenizers are isolated from a downstream task and model, they cannot output an appropriate tokenization depending on the task and model, although recent studies imply that the appropriate tokenization improves the…

Model ensembling is a well-established technique for improving the performance of machine learning models. Conventionally, this involves averaging the output distributions of multiple models and selecting the most probable label. This idea…

Recent datasets expose the lack of the systematic generalization ability in standard sequence-to-sequence models. In this work, we analyze this behavior of seq2seq models and identify two contributing factors: a lack of mutual exclusivity…

Unsupervised bilingual lexicon induction naturally exhibits duality, which results from symmetry in back-translation. For example, EN-IT and IT-EN induction can be mutually primal and dual problems. Current state-of-the-art methods,…

Tree Ensemble (TE) models, such as Gradient Boosted Trees, often achieve optimal performance on tabular datasets, yet their lack of transparency poses challenges for comprehending their decision logic. This paper introduces TE2Rules (Tree…