Search Results for author:
Found 88 papers, 15 papers with code
Re-embedding Difficult Samples via Mutual Information Constrained Semantically Oversampling for Imbalanced Text Classification
Difficult samples of the minority class in imbalanced text classification are usually hard to be classified as they are embedded into an overlapping semantic region with the majority class.
TED-CDB: A Large-Scale Chinese Discourse Relation Dataset on TED Talks
As different genres are known to differ in their communicative properties and as previously, for Chinese, discourse relations have only been annotated over news text, we have created the TED-CDB dataset.
CogTaskonomy: Cognitively Inspired Task Taxonomy Is Beneficial to Transfer Learning in NLP
Is there a principle to guide transfer learning across tasks in natural language processing (NLP)?
KaFSP: Knowledge-Aware Fuzzy Semantic Parsing for Conversational Question Answering over a Large-Scale Knowledge Base
In this paper, we study two issues of semantic parsing approaches to conversational question answering over a large-scale knowledge base: (1) The actions defined in grammar are not sufficient to handle uncertain reasoning common in real-world scenarios.
Adaptive Differential Privacy for Language Model Training
Although differential privacy (DP) can protect language models from leaking privacy, its indiscriminative protection on all data points reduces its practical utility.
Syntactically-Informed Unsupervised Paraphrasing with Non-Parallel Data
Particularly, we design a two-stage learning method to effectively train the model using non-parallel data.
A Test Suite for Evaluating Discourse Phenomena in Document-level Neural Machine Translation
The need to evaluate the ability of context-aware neural machine translation (NMT) models in dealing with specific discourse phenomena arises in document-level NMT.
Chinese WPLC: A Chinese Dataset for Evaluating Pretrained Language Models on Word Prediction Given Long-Range Context
Experiment results show that the Chinese pretrained language model PanGu-\alpha is 45 points behind human in terms of top-1 word prediction accuracy, indicating that Chinese WPLC is a challenging dataset.
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code
This problem is especially pertinent in natural language generation which requires ever-improving suites of datasets, metrics, and human evaluation to make definitive claims.
Unsupervised and Few-shot Parsing from Pretrained Language Models
We therefore extend the unsupervised models to few-shot parsing models (FPOA, FPIO) that use a few annotated trees to learn better linear projection matrices for parsing.
Efficient Cluster-Based k-Nearest-Neighbor Machine Translation
k-Nearest-Neighbor Machine Translation (kNN-MT) has been recently proposed as a non-parametric solution for domain adaptation in neural machine translation (NMT).
Learning Disentangled Semantic Representations for Zero-Shot Cross-Lingual Transfer in Multilingual Machine Reading Comprehension
To explicitly transfer only semantic knowledge to the target language, we propose two groups of losses tailored for semantic and syntactic encoding and disentanglement.
Bridging between Cognitive Processing Signals and Linguistic Features via a Unified Attentional Network
The proposed framework only requires cognitive processing signals recorded under natural reading as inputs, and can be used to detect a wide range of linguistic features with a single cognitive dataset.
Secoco: Self-Correcting Encoding for Neural Machine Translation
This paper presents Self-correcting Encoding (Secoco), a framework that effectively deals with input noise for robust neural machine translation by introducing self-correcting predictors.
TGEA: An Error-Annotated Dataset and Benchmark Tasks for TextGeneration from Pretrained Language Models
Each error is hence manually labeled with comprehensive annotations, including the span of the error, the associated span, minimal correction to the error, the type of the error, and rationale behind the error.
Multi-Head Highly Parallelized LSTM Decoder for Neural Machine Translation
This has to be computed n times for a sequence of length n. The linear transformations involved in the LSTM gate and state computations are the major cost factors in this.
An Empirical Study on Adversarial Attack on NMT: Languages and Positions Matter
For autoregressive NMT models that generate target words from left to right, we observe that adversarial attack on the source language is more effective than on the target language, and that attacking front positions of target sentences or positions of source sentences aligned to the front positions of corresponding target sentences is more effective than attacking other positions.
Modeling Task-Aware MIMO Cardinality for Efficient Multilingual Neural Machine Translation
In this paper, we propose to efficiently increase the capacity for multilingual NMT by increasing the cardinality.
CogAlign: Learning to Align Textual Neural Representations to Cognitive Language Processing Signals
Most previous studies integrate cognitive language processing signals (e. g., eye-tracking or EEG data) into neural models of natural language processing (NLP) just by directly concatenating word embeddings with cognitive features, ignoring the gap between the two modalities (i. e., textual vs. cognitive) and noise in cognitive features.
Autocorrect in the Process of Translation --- Multi-task Learning Improves Dialogue Machine Translation
Automatic translation of dialogue texts is a much needed demand in many real life scenarios.
Autocorrect in the Process of Translation -- Multi-task Learning Improves Dialogue Machine Translation
Automatic translation of dialogue texts is a much needed demand in many real life scenarios.
Enhanced Aspect-Based Sentiment Analysis Models with Progressive Self-supervised Attention Learning
In aspect-based sentiment analysis (ABSA), many neural models are equipped with an attention mechanism to quantify the contribution of each context word to sentiment prediction.
Integrating Pre-trained Model into Rule-based Dialogue Management
Rule-based dialogue management is still the most popular solution for industrial task-oriented dialogue systems for their interpretablility.
Efficient Object-Level Visual Context Modeling for Multimodal Machine Translation: Masking Irrelevant Objects Helps Grounding
In this paper, we propose an object-level visual context modeling framework (OVC) to efficiently capture and explore visual information for multimodal machine translation.
Modeling Homophone Noise for Robust Neural Machine Translation
In this paper, we propose a robust neural machine translation (NMT) framework.
Balanced Joint Adversarial Training for Robust Intent Detection and Slot Filling
Joint intent detection and slot filling has recently achieved tremendous success in advancing the performance of utterance understanding.
A Learning-Exploring Method to Generate Diverse Paraphrases with Multi-Objective Deep Reinforcement Learning
We propose a learning-exploring method to generate sentences as learning objectives from the learned data distribution, and employ reinforcement learning to combine these new learning objectives for model training.
The Box is in the Pen: Evaluating Commonsense Reasoning in Neural Machine Translation
Our experiments and analyses demonstrate that neural machine translation performs poorly on commonsense reasoning of the three ambiguity types in terms of both reasoning accuracy ( 6 60. 1{\%}) and reasoning consistency (6 31{\%}).
RiSAWOZ: A Large-Scale Multi-Domain Wizard-of-Oz Dataset with Rich Semantic Annotations for Task-Oriented Dialogue Modeling
In order to alleviate the shortage of multi-domain data and to capture discourse phenomena for task-oriented dialogue modeling, we propose RiSAWOZ, a large-scale multi-domain Chinese Wizard-of-Oz dataset with Rich Semantic Annotations.
Cycle-Consistent Adversarial Autoencoders for Unsupervised Text Style Transfer
Unsupervised text style transfer is full of challenges due to the lack of parallel data and difficulties in content preservation.
Learning Hard Retrieval Decoder Attention for Transformers
The Transformer translation model is based on the multi-head attention mechanism, which can be parallelized easily.
Transformer with Depth-Wise LSTM
In this paper, we suggest that the residual connection has its drawbacks, and propose to train Transformers with the depth-wise LSTM which regards outputs of layers as steps in time series instead of residual connections, under the motivation that the vanishing gradient problem suffered by deep networks is the same as recurrent networks applied to long sequences, while LSTM (Hochreiter and Schmidhuber, 1997) has been proven of good capability in capturing long-distance relationship, and its design may alleviate some drawbacks of residual connections while ensuring the convergence.
Learning Source Phrase Representations for Neural Machine Translation
Considering that modeling phrases instead of words has significantly improved the Statistical Machine Translation (SMT) approach through the use of larger translation blocks ("phrases") and its reordering ability, modeling NMT at phrase level is an intuitive proposal to help the model capture long-distance relationships.
Dynamically Adjusting Transformer Batch Size by Monitoring Gradient Direction Change
We propose to automatically and dynamically determine batch sizes by accumulating gradients of mini-batches and performing an optimization step at just the time when the direction of gradients starts to fluctuate.
Modeling Long Context for Task-Oriented Dialogue State Generation
Based on the recently proposed transferable dialogue state generator (TRADE) that predicts dialogue states from utterance-concatenated dialogue context, we propose a multi-task learning model with a simple yet effective utterance tagging technique and a bidirectional language model as an auxiliary task for task-oriented dialogue state generation.
Learning Contextualized Sentence Representations for Document-Level Neural Machine Translation
In this paper, we propose a new framework to model cross-sentence dependencies by training neural machine translation (NMT) to predict both the target translation and surrounding sentences of a source sentence.
Probing Word Translations in the Transformer and Trading Decoder for Encoder Layers
Due to its effectiveness and performance, the Transformer translation model has attracted wide attention, most recently in terms of probing-based approaches.
Shallow Discourse Annotation for Chinese TED Talks
Text corpora annotated with language-related properties are an important resource for the development of Language Technology.
Effective Data Augmentation Approaches to End-to-End Task-Oriented Dialogue
The training of task-oriented dialogue systems is often confronted with the lack of annotated data.
Merging External Bilingual Pairs into Neural Machine Translation
As neural machine translation (NMT) is not easily amenable to explicit correction of errors, incorporating pre-specified translations into NMT is widely regarded as a non-trivial challenge.
Learning to Reuse Translations: Guiding Neural Machine Translation with Examples
In this paper, we study the problem of enabling neural machine translation (NMT) to reuse previous translations from similar examples in target prediction.
Lipschitz Constrained Parameter Initialization for Deep Transformers
In this paper, we first empirically demonstrate that a simple modification made in the official implementation, which changes the computation order of residual connection and layer normalization, can significantly ease the optimization of deep Transformers.
Hierarchical Modeling of Global Context for Document-Level Neural Machine Translation
In this paper, we propose a hierarchical model to learn the global context for document-level neural machine translation (NMT).
BiPaR: A Bilingual Parallel Dataset for Multilingual and Cross-lingual Reading Comprehension on Novels
We analyze BiPaR in depth and find that BiPaR offers good diversification in prefixes of questions, answer types and relationships between questions and passages.
Generating Highly Relevant Questions
The neural seq2seq based question generation (QG) is prone to generating generic and undiversified questions that are poorly relevant to the given passage and target answer.
GECOR: An End-to-End Generative Ellipsis and Co-reference Resolution Model for Task-Oriented Dialogue
Ellipsis and co-reference are common and ubiquitous especially in multi-turn dialogues.
Towards Linear Time Neural Machine Translation with Capsule Networks
In this study, we first investigate a novel capsule network with dynamic routing for linear time Neural Machine Translation (NMT), referred as \textsc{CapsNMT}.
Simplifying Neural Machine Translation with Addition-Subtraction Twin-Gated Recurrent Networks
Experiments on WMT14 translation tasks demonstrate that ATR-based neural machine translation can yield competitive performance on English- German and English-French language pairs in terms of both translation quality and speed.
Encoding Gated Translation Memory into Neural Machine Translation
Translation memories (TM) facilitate human translators to reuse existing repetitive translation fragments.
Neural Machine Translation with Decoding History Enhanced Attention
Neural machine translation with source-side attention have achieved remarkable performance.
Sentence Weighting for Neural Machine Translation Domain Adaptation
In this paper, we propose a new sentence weighting method for the domain adaptation of neural machine translation.
Fusing Recency into Neural Machine Translation with an Inter-Sentence Gate Model
Neural machine translation (NMT) systems are usually trained on a large amount of bilingual sentence pairs and translate one sentence at a time, ignoring inter-sentence information.
Accelerating Neural Transformer via an Average Attention Network
To alleviate this issue, we propose an average attention network as an alternative to the self-attention network in the decoder of the neural Transformer.
Variational Recurrent Neural Machine Translation
Partially inspired by successful applications of variational recurrent neural networks, we propose a novel variational recurrent neural machine translation (VRNMT) model in this paper.
Modeling Coherence for Neural Machine Translation with Dynamic and Topic Caches
Sentences in a well-formed text are connected to each other via various links to form the cohesive structure of the text.
Attention Focusing for Neural Machine Translation by Bridging Source and Target Embeddings
In neural machine translation, a source sequence of words is encoded into a vector from which a target sequence is generated in the decoding phase.
Translating Phrases in Neural Machine Translation
Otherwise, the NMT decoder generates a word from the vocabulary as the general NMT decoder does.
Modeling Source Syntax for Neural Machine Translation
Even though a linguistics-free sequence to sequence model in neural machine translation (NMT) has certain capability of implicitly learning syntactic information of source sentences, this paper shows that source syntax can be explicitly incorporated into NMT effectively to provide further improvements.
A GRU-Gated Attention Model for Neural Machine Translation
In this paper, we propose a novel GRU-gated attention model (GAtt) for NMT which enhances the degree of discrimination of context vectors by enabling source representations to be sensitive to the partial translation generated by the decoder.
Improving Translation Selection with Supersenses
Selecting appropriate translations for source words with multiple meanings still remains a challenge for statistical machine translation (SMT).
Convolution-Enhanced Bilingual Recursive Neural Network for Bilingual Semantic Modeling
After that, we fully incorporate information of different linguistic units into a bilinear semantic similarity model.
Bilingual Autoencoders with Global Descriptors for Modeling Parallel Sentences
Parallel sentence representations are important for bilingual and cross-lingual tasks in natural language processing.
Improving Statistical Machine Translation with Selectional Preferences
In this paper, we study semantic dependencies between verbs and their arguments by modeling selectional preferences in the context of machine translation.
Learning Event Expressions via Bilingual Structure Projection
Aiming to resolve high complexities of event descriptions, previous work (Huang and Riloff, 2013) proposes multi-faceted event recognition and a bootstrapping method to automatically acquire both event facet phrases and event expressions from unannotated texts.
Neural Machine Translation Advised by Statistical Machine Translation
Neural Machine Translation (NMT) is a new approach to machine translation that has made great progress in recent years.
Lattice-Based Recurrent Neural Network Encoders for Neural Machine Translation
Neural machine translation (NMT) heavily relies on word-level modelling to learn semantic representations of input sentences.
Cseq2seq: Cyclic Sequence-to-Sequence Learning
The vanilla sequence-to-sequence learning (seq2seq) reads and encodes a source sequence into a fixed-length vector only once, suffering from its insufficiency in modeling structural correspondence between the source and target sequence.
Variational Neural Machine Translation
Models of neural machine translation are often from a discriminative family of encoderdecoders that learn a conditional distribution of a target sentence given a source sentence.
BattRAE: Bidimensional Attention-Based Recursive Autoencoders for Learning Bilingual Phrase Embeddings
In this paper, we propose a bidimensional attention based recursive autoencoder (BattRAE) to integrate clues and sourcetarget interactions at multiple levels of granularity into bilingual phrase representations.
Variational Neural Discourse Relation Recognizer
In order to perform efficient inference and learning, we introduce neural discourse relation models to approximate the prior and posterior distributions of the latent variable, and employ these approximated distributions to optimize a reparameterized variational lower bound.
Neural Discourse Relation Recognition with Semantic Memory
Inspired by this, we propose a neural recognizer for implicit discourse relation analysis, which builds upon a semantic memory that stores knowledge in a distributed fashion.
