Nevertheless, few works utilized the knowledge extracted from similar conversations for utterance generation.
Reasoning machine reading comprehension (R-MRC) aims to answer complex questions that require discrete reasoning based on text.
The general format of natural language inference (NLI) makes it tempting to be used for zero-shot text classification by casting any target label into a sentence of hypothesis and verifying whether or not it could be entailed by the input, aiming at generic classification applicable on any specified label space.
Document-level relation extraction (DocRE) models generally use graph networks to implicitly model the reasoning skill (i. e., pattern recognition, logical reasoning, coreference reasoning, etc.)
Ranked #12 on Relation Extraction on DocRED
Through the score matrix of Gumbel-Attention and image features, the image-aware text representation is generated.
Ranked #3 on Multimodal Machine Translation on Multi30K
Unsupervised Neural Machine Translation or UNMT has received great attention in recent years.
In document-level relation extraction (DocRE), graph structure is generally used to encode relation information in the input document to classify the relation category between each entity pair, and has greatly advanced the DocRE task over the past several years.
Ranked #19 on Relation Extraction on DocRED
Neural models have achieved great success on the task of machine reading comprehension (MRC), which are typically trained on hard labels.
In the past few years, audiences from different fields witness the achievements of sequence-to-sequence models (e. g., LSTM+attention, Pointer Generator Networks, and Transformer) to enhance dialogue content generation.
The multi-role judicial debate composed of the plaintiff, defendant, and judge is an important part of the judicial trial.
This paper aims to enhance the few-shot relation classification especially for sentences that jointly describe multiple relations.
Recent studies show that crowd-sourced Natural Language Inference (NLI) datasets may suffer from significant biases like annotation artifacts.
End-to-End speech translation usually leverages audio-to-text parallel data to train an available speech translation model which has shown impressive results on various speech translation tasks.
In this paper, we formalize the unintended biases in text classification datasets as a kind of selection bias from the non-discrimination distribution to the discrimination distribution.
Unsupervised neural machine translation (UNMT) has recently achieved remarkable results for several language pairs.
Unsupervised neural machine translation (UNMT) that relies solely on massive monolingual corpora has achieved remarkable results in several translation tasks.
Despite the great success of NMT, there still remains a severe challenge: it is hard to interpret the internal dynamics during its training process.
Generalization to unseen instances is our eternal pursuit for all data-driven models.
Specifically, we first propose an object-extent learning module for localizing the object according to the visual patterns shared among the instances in the same category.
Ranked #1 on Image Recognition on ImageNet
Existing neural machine translation (NMT) systems utilize sequence-to-sequence neural networks to generate target translation word by word, and then make the generated word at each time-step and the counterpart in the references as consistent as possible.
Unsupervised neural machine translation (UNMT) has recently attracted great interest in the machine translation community.
In this work, we aim to improve the relevance between live comments and videos by modeling the cross-modal interactions among different modalities.
Many Data Augmentation (DA) methods have been proposed for neural machine translation.
This irregularity makes the evaluation results over-estimated and affects models' generalization ability.
Unsupervised bilingual lexicon induction naturally exhibits duality, which results from symmetry in back-translation.
However, it has not been well-studied for unsupervised neural machine translation (UNMT), although UNMT has recently achieved remarkable results in several domain-specific language pairs.
In previous methods, UBWE is first trained using non-parallel monolingual corpora and then this pre-trained UBWE is used to initialize the word embedding in the encoder and decoder of UNMT.
The training objective of neural machine translation (NMT) is to minimize the loss between the words in the translated sentences and those in the references.
The explicit use of syntactic information has been proved useful for neural machine translation (NMT).
Multilayer architectures are currently the gold standard for large-scale neural machine translation.
Natural Language Sentence Matching (NLSM) has gained substantial attention from both academics and the industry, and rich public datasets contribute a lot to this process.
First, we model one of the pairwise interaction (e. g., image and question) by bilinear features, which is further encoded with the third dimension (e. g., answer) to be a triplet by bilinear tensor product.
In this paper, we present a novel end-to-end neural network framework for extractive document summarization by jointly learning to score and select sentences.
Ranked #8 on Extractive Text Summarization on CNN / Daily Mail
Tree-based neural machine translation (NMT) approaches, although achieved impressive performance, suffer from a major drawback: they only use the 1-best parse tree to direct the translation, which potentially introduces translation mistakes due to parsing errors.
The model maps a row from a table to a continuous vector and then generates a natural language sentence by leveraging the semantics of a table.
In this paper, we extend local attention with syntax-distance constraint, to focus on syntactically related source words with the predicted target word, thus learning a more effective context vector for word prediction.
In Neural Machine Translation (NMT), each word is represented as a low-dimension, real-value vector for encoding its syntax and semantic information.
Source dependency information has been successfully introduced into statistical machine translation.
Large scale image dataset and deep convolutional neural network (DCNN) are two primary driving forces for the rapid progress made in generic object recognition tasks in recent years.
WebQuestions and SimpleQuestions are two benchmark data-sets commonly used in recent knowledge-based question answering (KBQA) work.
This Treebank is a part of a semantic corpus building project, which aims to build a semantic bilingual corpus annotated with syntactic, semantic cases and word senses.
Pivot language is employed as a way to solve the data sparseness problem in machine translation, especially when the data for a particular language pair does not exist.
Image retrieval refers to finding relevant images from an image database for a query, which is considered difficult for the gap between low-level representation of images and high-level representation of queries.