Search Results for author:
Found 44 papers, 12 papers with code
Alleviating the Inequality of Attention Heads for Neural Machine Translation
Recent studies show that the attention heads in Transformer are not equal.
Ranked #1 on
Machine Translation
on WMT2017 Turkish-English
Prompt Agnostic Essay Scorer: A Domain Generalization Approach to Cross-prompt Automated Essay Scoring
Cross-prompt automated essay scoring (AES) requires the system to use non target-prompt essays to award scores to a target-prompt essay.
Explicit Semantic Decomposition for Definition Generation
Definition generation, which aims to automatically generate dictionary definitions for words, has recently been proposed to assist the construction of dictionaries and help people understand unfamiliar texts.
Dialogue State Tracking with Explicit Slot Connection Modeling
Recent proposed approaches have made promising progress in dialogue state tracking (DST).
RPD: A Distance Function Between Word Embeddings
Based on the properties of RPD, we study the relations of word embeddings of different algorithms systematically and investigate the influence of different training processes and corpora.
Mirror-Generative Neural Machine Translation
Training neural machine translation models (NMT) requires a large amount of parallel corpus, which is scarce for many language pairs.
GRET: Global Representation Enhanced Transformer
The encoder maps the words in the input sentence into a sequence of hidden states, which are then fed into the decoder to generate the output sentence.
Towards Making the Most of Context in Neural Machine Translation
Document-level machine translation manages to outperform sentence level models by a small margin, but have failed to be widely adopted.
Latent Opinions Transfer Network for Target-Oriented Opinion Words Extraction
In this paper, we propose a novel model to transfer these opinions knowledge from resource-rich review sentiment classification datasets to low-resource task TOWE.
Aspect-oriented Opinion Extraction
General Classification
+2
Acquiring Knowledge from Pre-trained Model to Neural Machine Translation
The standard paradigm of exploiting them includes two steps: first, pre-training a model, e. g. BERT, with a large scale unlabeled monolingual data.
Non-autoregressive Transformer by Position Learning
Non-autoregressive models are promising on various text generation tasks.
Generating Diverse Translation by Manipulating Multi-Head Attention
Experiments also show that back-translation with these diverse translations could bring significant improvement on performance on translation tasks.
A Reinforced Generation of Adversarial Examples for Neural Machine Translation
Neural machine translation systems tend to fail on less decent inputs despite its significant efficacy, which may significantly harm the credibility of this systems-fathoming how and when neural-based systems fail in such cases is critical for industrial maintenance.
Multi-Perspective Inferrer: Reasoning Sentences Relationship from Holistic Perspective
Intuitively, NLI should rely more on multiple perspectives to form a holistic view to eliminate bias.
Fine-grained Knowledge Fusion for Sequence Labeling Domain Adaptation
In sequence labeling, previous domain adaptation methods focus on the adaptation from the source domain to the entire target domain without considering the diversity of individual target domain samples, which may lead to negative transfer results for certain samples.
Improving Neural Machine Translation with Pre-trained Representation
Then, we design a framework for integrating both source and target sentence-level representations into NMT model to improve the translation quality.
Learning Representation Mapping for Relation Detection in Knowledge Base Question Answering
However, one critical problem is that current approaches only get high accuracy for questions whose relations have been seen in the training data.
Correct-and-Memorize: Learning to Translate from Interactive Revisions
Experiments in both ideal and real interactive translation settings demonstrate that our proposed \method enhances machine translation results significantly while requires fewer revision instructions from human compared to previous methods.
Generating Sentences from Disentangled Syntactic and Semantic Spaces
In this paper, we propose to generate sentences from disentangled syntactic and semantic spaces.
Online Distilling from Checkpoints for Neural Machine Translation
Our method on-the-fly generates a teacher model from checkpoints, guiding the training process to obtain better performance.
Exploiting Noisy Data in Distant Supervision Relation Classification
Distant supervision has obtained great progress on relation classification task.
Target-oriented Opinion Words Extraction with Target-fused Neural Sequence Labeling
In this paper, we propose a novel sequence labeling subtask for ABSA named TOWE (Target-oriented Opinion Words Extraction), which aims at extracting the corresponding opinion words for a given opinion target.
Aspect-oriented Opinion Extraction
target-oriented opinion words extraction
Dynamic Past and Future for Neural Machine Translation
Previous studies have shown that neural machine translation (NMT) models can benefit from explicitly modeling translated (Past) and untranslated (Future) to groups of translated and untranslated contents through parts-to-wholes assignment.
Learning to Discriminate Noises for Incorporating External Information in Neural Machine Translation
Previous studies show that incorporating external information could improve the translation quality of Neural Machine Translation (NMT) systems.
Unsupervised Bilingual Lexicon Induction via Latent Variable Models
Bilingual lexicon extraction has been studied for decades and most previous methods have relied on parallel corpora or bilingual dictionaries.
Combining Character and Word Information in Neural Machine Translation Using a Multi-Level Attention
Natural language sentences, being hierarchical, can be represented at different levels of granularity, like words, subwords, or characters.
Collaborative Filtering with Topic and Social Latent Factors Incorporating Implicit Feedback
First, we propose a novel model {\em \mbox{MR3}} to jointly model three sources of information (i. e., ratings, item reviews, and social relations) effectively for rating prediction by aligning the latent factors and hidden topics.
Improving Review Representations with User Attention and Product Attention for Sentiment Classification
Recently, some works achieved improvement by incorporating user and product information to generate a review representation.
Ranked #3 on
Sentiment Analysis
on User and product information
Modeling Past and Future for Neural Machine Translation
The Past and Future contents are fed to both the attention model and the decoder states, which offers NMT systems the knowledge of translated and untranslated contents.
Dynamic Oracle for Neural Machine Translation in Decoding Phase
However, there are certain limitations in Scheduled Sampling and we propose two dynamic oracle-based methods to improve it.
Word-Context Character Embeddings for Chinese Word Segmentation
Neural parsers have benefited from automatically labeled data via dependency-context word embeddings.
Neural Machine Translation with Word Predictions
In the encoder-decoder architecture for neural machine translation (NMT), the hidden states of the recurrent structures in the encoder and decoder carry the crucial information about the sentence. These vectors are generated by parameters which are updated by back-propagation of translation errors through time.
Improved Neural Machine Translation with a Syntax-Aware Encoder and Decoder
Most neural machine translation (NMT) models are based on the sequential encoder-decoder framework, which makes no use of syntactic information.
Top-Rank Enhanced Listwise Optimization for Statistical Machine Translation
We propose a listwise learning framework for structure prediction problems such as machine translation.
Chunk-Based Bi-Scale Decoder for Neural Machine Translation
In typical neural machine translation~(NMT), the decoder generates a sentence word by word, packing all linguistic granularities in the same time-scale of RNN.
Evaluating a Deterministic Shift-Reduce Neural Parser for Constituent Parsing
Greedy transition-based parsers are appealing for their very fast speed, with reasonably high accuracies.
A Synthetic Approach for Recommendation: Combining Ratings, Social Relations, and Reviews
Recommender systems (RSs) provide an effective way of alleviating the information overload problem by selecting personalized choices.
