Search Results for author:
Found 147 papers, 42 papers with code
How Do Seq2Seq Models Perform on End-to-End Data-to-Text Generation?
With the rapid development of deep learning, Seq2Seq paradigm has become prevalent for end-to-end data-to-text generation, and the BLEU scores have been increasing in recent years.
Homophonic Pun Generation with Lexically Constrained Rewriting
Punning is a creative way to make conversation enjoyable and literary writing elegant.
DialSummEval: Revisiting Summarization Evaluation for Dialogues
Dialogue summarization is receiving increasing attention from researchers due to its extraordinary difficulty and unique application value.
DelibGAN: Coarse-to-Fine Text Generation via Adversarial Network
In this paper, we propose a novel adversarial learning framework, namely DelibGAN, for generating high-quality sentences without supervision.
Routing Enforced Generative Model for Recipe Generation
One of the most challenging part of recipe generation is to deal with the complex restrictions among the input ingredients.
Comparing Knowledge-Intensive and Data-Intensive Models for English Resource Semantic Parsing
Abstract In this work, we present a phenomenon-oriented comparative analysis of the two dominant approaches in English Resource Semantic (ERS) parsing: classic, knowledge-intensive and neural, data-intensive models.
Revisiting Pivot-Based Paraphrase Generation: Language Is Not the Only Optional Pivot
Concretely, we transform a sentence into a variety of different semantic or syntactic representations (including AMR, UD, and latent semantic representation), and then decode the sentence back from the semantic representations.
Automated Similarity Metric Generation for Recommendation
Given the critical role of similarity metrics in recommender systems, existing methods mainly employ handcrafted similarity metrics to capture the complex characteristics of user-item interactions.
WikiTableEdit: A Benchmark for Table Editing by Natural Language Instruction
Subsequently, we evaluate several representative large language models on the WikiTableEdit dataset to demonstrate the challenge of this task.
Quantity Matters: Towards Assessing and Mitigating Number Hallucination in Large Vision-Language Models
Large-scale vision-language models have demonstrated impressive skill in handling tasks that involve both areas.
DPP-Based Adversarial Prompt Searching for Lanugage Models
Language models risk generating mindless and offensive content, which hinders their safe deployment.
EAMA : Entity-Aware Multimodal Alignment Based Approach for News Image Captioning
News image captioning requires model to generate an informative caption rich in entities, with the news image and the associated news article.
Are LLM-based Evaluators Confusing NLG Quality Criteria?
Some prior work has shown that LLMs perform well in NLG evaluation for different tasks.
Benchmarking Knowledge Boundary for Large Language Model: A Different Perspective on Model Evaluation
In recent years, substantial advancements have been made in the development of large language models, achieving remarkable performance across diverse tasks.
Selecting Large Language Model to Fine-tune via Rectified Scaling Law
The ever-growing ecosystem of LLMs has posed a challenge in selecting the most appropriate pre-trained model to fine-tune amidst a sea of options.
LLM-based NLG Evaluation: Current Status and Challenges
Evaluating natural language generation (NLG) is a vital but challenging problem in artificial intelligence.
History Matters: Temporal Knowledge Editing in Large Language Model
The imperative task of revising or updating the knowledge stored within large language models arises from two distinct sources: intrinsic errors inherent in the model which should be corrected and outdated knowledge due to external shifts in the real world which should be updated.
OpinSummEval: Revisiting Automated Evaluation for Opinion Summarization
Opinion summarization sets itself apart from other types of summarization tasks due to its distinctive focus on aspects and sentiments.
Evaluating, Understanding, and Improving Constrained Text Generation for Large Language Models
Advancements in natural language generation (NLG) and large language models (LLMs) have led to proficient text generation in various tasks.
ALCUNA: Large Language Models Meet New Knowledge
With the rapid development of NLP, large-scale language models (LLMs) excel in various tasks across multiple domains now.
A New Benchmark and Reverse Validation Method for Passage-level Hallucination Detection
Contrasting previous studies of zero-resource hallucination detection, our method and benchmark concentrate on passage-level detection instead of sentence-level.
WikiIns: A High-Quality Dataset for Controlled Text Editing by Natural Language Instruction
In this paper, we study the problem of controlled text editing by natural language instruction.
Enhancing Large Language Models in Coding Through Multi-Perspective Self-Consistency
We propose the Multi-Perspective Self-Consistency (MPSC) framework incorporating both inter- and intra-consistency across outputs from multiple perspectives.
A Comprehensive Evaluation and Analysis Study for Chinese Spelling Check
With the development of pre-trained models and the incorporation of phonetic and graphic information, neural models have achieved high scores in Chinese Spelling Check (CSC).
Image Matters: A New Dataset and Empirical Study for Multimodal Hyperbole Detection
We create a multimodal detection dataset from Weibo (a Chinese social media) and carry out some studies on it.
SituatedGen: Incorporating Geographical and Temporal Contexts into Generative Commonsense Reasoning
Generative commonsense reasoning is the task that requires machines, given a group of keywords, to compose a single coherent sentence with commonsense plausibility.
Reference Matters: Benchmarking Factual Error Correction for Dialogue Summarization with Fine-grained Evaluation Framework
To address this problem, we are the first to manually annotate a FEC dataset for dialogue summarization containing 4000 items and propose FERRANTI, a fine-grained evaluation framework based on reference correction that automatically evaluates the performance of FEC models on different error categories.
A New Dataset and Empirical Study for Sentence Simplification in Chinese
Sentence Simplification is a valuable technique that can benefit language learners and children a lot.
Is Summary Useful or Not? An Extrinsic Human Evaluation of Text Summaries on Downstream Tasks
The results show that summaries generated by fine-tuned models lead to higher consistency in usefulness across all three tasks, as rankings of fine-tuned summarization systems are close across downstream tasks according to the proposed extrinsic metrics.
Teaching the Pre-trained Model to Generate Simple Texts for Text Simplification
In this paper, we propose a new continued pre-training strategy to teach the pre-trained model to generate simple texts.
Missing Information, Unresponsive Authors, Experimental Flaws: The Impossibility of Assessing the Reproducibility of Previous Human Evaluations in NLP
We report our efforts in identifying a set of previous human evaluations in NLP that would be suitable for a coordinated study examining what makes human evaluations in NLP more/less reproducible.
Human-like Summarization Evaluation with ChatGPT
Evaluating text summarization is a challenging problem, and existing evaluation metrics are far from satisfactory.
Models See Hallucinations: Evaluating the Factuality in Video Captioning
In this work, we conduct a detailed human evaluation of the factuality in video captioning and collect two annotated factuality datasets.
Exploiting Summarization Data to Help Text Simplification
One of the major problems with text simplification is the lack of high-quality data.
How to Describe Images in a More Funny Way? Towards a Modular Approach to Cross-Modal Sarcasm Generation
Sarcasm generation has been investigated in previous studies by considering it as a text-to-text generation problem, i. e., generating a sarcastic sentence for an input sentence.
Error-Robust Retrieval for Chinese Spelling Check
Chinese Spelling Check (CSC) aims to detect and correct error tokens in Chinese contexts, which has a wide range of applications.
Social Biases in Automatic Evaluation Metrics for NLG
Many studies have revealed that word embeddings, language models, and models for specific downstream tasks in NLP are prone to social biases, especially gender bias.
An Empirical Study of Automatic Post-Editing
In view of the importance of data augmentation in APE, we separately study the impact of the construction method of artificial corpora and artificial data domain on the performance of APE models.
CrossDial: An Entertaining Dialogue Dataset of Chinese Crosstalk
Crosstalk is a traditional Chinese theatrical performance art.
CC-Riddle: A Question Answering Dataset of Chinese Character Riddles
Solving Chinese character riddles is a challenging task that demands understanding of character glyph, general knowledge, and a grasp of figurative language.
Nearest Neighbor Knowledge Distillation for Neural Machine Translation
k-nearest-neighbor machine translation (NN-MT), proposed by Khandelwal et al. (2021), has achieved many state-of-the-art results in machine translation tasks.
SimpleBERT: A Pre-trained Model That Learns to Generate Simple Words
We use a small-scale simple text dataset for continued pre-training and employ two methods to identify simple words from the texts.
Dependency-based Mixture Language Models
Various models have been proposed to incorporate knowledge of syntactic structures into neural language models.
A Simple Information-Based Approach to Unsupervised Domain-Adaptive Aspect-Based Sentiment Analysis
Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis task which aims to extract the aspects from sentences and identify their corresponding sentiments.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+4
Visual Information Guided Zero-Shot Paraphrase Generation
Zero-shot paraphrase generation has drawn much attention as the large-scale high-quality paraphrase corpus is limited.
CUGE: A Chinese Language Understanding and Generation Evaluation Benchmark
We argue that for general-purpose language intelligence evaluation, the benchmark itself needs to be comprehensive and systematic.
Neural Content Extraction for Poster Generation of Scientific Papers
Then we propose a three-step framework to tackle this task and focus on the content extraction step in this study.
A Syntax-Guided Grammatical Error Correction Model with Dependency Tree Correction
However, these methods lack the use of syntactic knowledge which plays an important role in the correction of grammatical errors.
Document-Level Text Simplification: Dataset, Criteria and Baseline
Finally, we select several representative models as baseline models for this task and perform automatic evaluation and human evaluation.
BiRdQA: A Bilingual Dataset for Question Answering on Tricky Riddles
A riddle is a question or statement with double or veiled meanings, followed by an unexpected answer.
CodeQA: A Question Answering Dataset for Source Code Comprehension
We propose CodeQA, a free-form question answering dataset for the purpose of source code comprehension: given a code snippet and a question, a textual answer is required to be generated.
MOVER: Mask, Over-generate and Rank for Hyperbole Generation
In this paper, we tackle the challenging task of hyperbole generation to transfer a literal sentence into its hyperbolic paraphrase.
Towards Document-Level Paraphrase Generation with Sentence Rewriting and Reordering
Paraphrase generation is an important task in natural language processing.
Pushing Paraphrase Away from Original Sentence: A Multi-Round Paraphrase Generation Approach
Both automatic and human evaluation show BTmPG can improve the diversity of paraphrase while preserving the semantics of the original sentence.
Video Paragraph Captioning as a Text Summarization Task
Most previous methods simplify this task by using ground-truth event segments.
Making Better Use of Bilingual Information for Cross-Lingual AMR Parsing
We argue that the misprediction of concepts is due to the high relevance between English tokens and AMR concepts.
Continual Learning for Neural Machine Translation
In practical applications, NMT models are usually trained on a general domain corpus and then fine-tuned by continuing training on the in-domain corpus.
Bridging the Domain Gap: Improve Informal Language Translation via Counterfactual Domain Adaptation
Despite the near-human performances already achieved on formal texts such as news articles, neural machine transla- tion still has difficulty in dealing with ”user-generated” texts that have diverse linguistic phenomena but lack large-scale high-quality parallel corpora.
Diversifying Neural Text Generation with Part-of-Speech Guided Softmax and Sampling
Neural text generation models are likely to suffer from the low-diversity problem.
Learning a Product Relevance Model from Click-Through Data in E-Commerce
We propose a novel way to consider samples of different relevance confidence, and come up with a new training objective to learn a robust relevance model with desirable score distribution.
ParaSCI: A Large Scientific Paraphrase Dataset for Longer Paraphrase Generation
We propose ParaSCI, the first large-scale paraphrase dataset in the scientific field, including 33, 981 paraphrase pairs from ACL (ParaSCI-ACL) and 316, 063 pairs from arXiv (ParaSCI-arXiv).
On the Helpfulness of Document Context to Sentence Simplification
Our model uses neural networks to learn the different effects of the preceding sentences and the following sentences on the current sentence and applies them to the improved transformer model.
Improving Grammatical Error Correction with Data Augmentation by Editing Latent Representation
The incorporation of data augmentation method in grammatical error correction task has attracted much attention.
IGSQL: Database Schema Interaction Graph Based Neural Model for Context-Dependent Text-to-SQL Generation
Our model outperforms previous state-of-the-art model by a large margin and achieves new state-of-the-art results on the two datasets.
DivGAN: Towards Diverse Paraphrase Generation via Diversified Generative Adversarial Network
In this paper, we propose a deep generative model to generate diverse paraphrases.
Adversarial Text Generation via Sequence Contrast Discrimination
In this paper, we propose a sequence contrast loss driven text generation framework, which learns the difference between real texts and generated texts and uses that difference.
Abstractive Multi-Document Summarization via Joint Learning with Single-Document Summarization
Single-document and multi-document summarizations are very closely related in both task definition and solution method.
TransModality: An End2End Fusion Method with Transformer for Multimodal Sentiment Analysis
Enlightened by recent success of Transformer in the area of machine translation, we propose a new fusion method, TransModality, to address the task of multimodal sentiment analysis.
Ranked #1 on
Multimodal Sentiment Analysis
on CMU-MOSI
(F1-score (Weighted) metric)
Constructing a Family Tree of Ten Indo-European Languages with Delexicalized Cross-linguistic Transfer Patterns
It is reasonable to hypothesize that the divergence patterns formulated by historical linguists and typologists reflect constraints on human languages, and are thus consistent with Second Language Acquisition (SLA) in a certain way.
Heterogeneous Graph Transformer for Graph-to-Sequence Learning
The graph-to-sequence (Graph2Seq) learning aims to transduce graph-structured representations to word sequences for text generation.
Learning to Ask More: Semi-Autoregressive Sequential Question Generation under Dual-Graph Interaction
Traditional Question Generation (TQG) aims to generate a question given an input passage and an answer.
Automatic Generation of Citation Texts in Scholarly Papers: A Pilot Study
In this paper, we study the challenging problem of automatic generation of citation texts in scholarly papers.
Multimodal Transformer for Multimodal Machine Translation
Multimodal Machine Translation (MMT) aims to introduce information from other modality, generally static images, to improve the translation quality.
Ranked #6 on
Multimodal Machine Translation
on Multi30K
Jointly Learning to Align and Summarize for Neural Cross-Lingual Summarization
However, it is a big challenge for the model to directly learn cross-lingual summarization as it requires learning to understand different languages and learning how to summarize at the same time.
Semantic Parsing for English as a Second Language
This paper is concerned with semantic parsing for English as a second language (ESL).
Multi-Granularity Interaction Network for Extractive and Abstractive Multi-Document Summarization
In this paper, we propose a multi-granularity interaction network for extractive and abstractive multi-document summarization, which jointly learn semantic representations for words, sentences, and documents.
AMR-To-Text Generation with Graph Transformer
Abstract meaning representation (AMR)-to-text generation is the challenging task of generating natural language texts from AMR graphs, where nodes represent concepts and edges denote relations.
Towards a Unified End-to-End Approach for Fully Unsupervised Cross-Lingual Sentiment Analysis
Cross-lingual sentiment analysis (CLSA) aims to improve the performance on these languages by leveraging annotated data from other languages.
Automated Chess Commentator Powered by Neural Chess Engine
In this paper, we explore a new approach for automated chess commentary generation, which aims to generate chess commentary texts in different categories (e. g., description, comparison, planning, etc.).
A Neural Approach to Irony Generation
Ironies can not only express stronger emotions but also show a sense of humor.
INS: An Interactive Chinese News Synthesis System
So it is of vital importance to automatically synthesize a batch of news articles related to the event or topic into a new synthesis article (or overview article) for reader's convenience.
A Comparative Analysis of Knowledge-Intensive and Data-Intensive Semantic Parsers
We present a phenomenon-oriented comparative analysis of the two dominant approaches in task-independent semantic parsing: classic, knowledge-intensive and neural, data-intensive models.
Multi-Modal Sarcasm Detection in Twitter with Hierarchical Fusion Model
We create a multi-modal sarcasm detection dataset based on Twitter.
Asking the Crowd: Question Analysis, Evaluation and Generation for Open Discussion on Online Forums
For openQG task, we construct OQGenD, the first dataset as far as we know, and propose a model based on conditional generative adversarial networks and our question evaluation model.
T-CVAE: Transformer-Based Conditioned Variational Autoencoder for Story Completion
Our model uses shared attention layers for encoder and decoder, which make the most of the contextual clues, and a latent variable for learning the distribution of coherent story plots.
A Semi-Supervised Approach for Low-Resourced Text Generation
The low-resource (of labeled data) problem is quite common in different task generation tasks, but unlabeled data are usually abundant.
Massive Styles Transfer with Limited Labeled Data
In this paper, we propose a multi-agent style transfer system (MAST) for addressing multiple style transfer tasks with limited labeled data, by leveraging abundant unlabeled data and the mutual benefit among the multiple styles.
How to Avoid Sentences Spelling Boring? Towards a Neural Approach to Unsupervised Metaphor Generation
In order to create novel metaphors, we propose a neural approach to metaphor generation and explore the shared inferential structure of a metaphorical usage and a literal usage of a verb.
Learning Bilingual Sentiment-Specific Word Embeddings without Cross-lingual Supervision
Our method only requires a sentiment corpus in the source language and pretrained monolingual word embeddings of both languages.
Controllable Unsupervised Text Attribute Transfer via Editing Entangled Latent Representation
Unsupervised text attribute transfer automatically transforms a text to alter a specific attribute (e. g. sentiment) without using any parallel data, while simultaneously preserving its attribute-independent content.
AMRec: An Intelligent System for Academic Method Recommendation
Finding new academic Methods for research problems is the key task in a researcher's research career.
Parsing Chinese Sentences with Grammatical Relations
In this work, we propose to represent grammatical information using general directed dependency graphs.
Adapting Neural Single-Document Summarization Model for Abstractive Multi-Document Summarization: A Pilot Study
In this paper, we investigate neural abstractive methods for MDS by adapting a state-of-the-art neural abstractive summarization model for SDS.
Neural Maximum Subgraph Parsing for Cross-Domain Semantic Dependency Analysis
We present experiments for cross-domain semantic dependency analysis with a neural Maximum Subgraph parser.
Semantic Role Labeling for Learner Chinese: the Importance of Syntactic Parsing and L2-L1 Parallel Data
This paper studies semantic parsing for interlanguage (L2), taking semantic role labeling (SRL) as a case task and learner Chinese as a case language.
Point Precisely: Towards Ensuring the Precision of Data in Generated Texts Using Delayed Copy Mechanism
Our approach first adopts an encoder-decoder model to generate a template text with data slots to be filled and then leverages a proposed delayed copy mechanism to fill in the slots with proper data records.
Accurate SHRG-Based Semantic Parsing
We demonstrate that an SHRG-based parser can produce semantic graphs much more accurately than previously shown, by relating synchronous production rules to the syntacto-semantic composition process.
Language Generation via DAG Transduction
This remarkable result demonstrates the feasibility of applying a DAG transducer to resolve NLG, as well as the effectiveness of our design.
Sense-Aware Neural Models for Pun Location in Texts
In this paper, we focus on the task of pun location, which aims to identify the pun word in a given short text.
A Neural Approach to Pun Generation
Since sequence-to-sequence models provide an effective technique for text generation, it is promising to investigate these models on the pun generation task.
Pre- and In-Parsing Models for Neural Empty Category Detection
Motivated by the positive impact of empty category on syntactic parsing, we study neural models for pre- and in-parsing detection of empty category, which has not previously been investigated.
Towards a Neural Network Approach to Abstractive Multi-Document Summarization
In this paper, we investigate neural abstractive methods for MDS by adapting a state-of-the-art neural abstractive summarization model for SDS.
Towards Automatic Generation of Entertaining Dialogues in Chinese Crosstalks
Crosstalk, also known by its Chinese name xiangsheng, is a traditional Chinese comedic performing art featuring jokes and funny dialogues, and one of China's most popular cultural elements.
Leveraging Diverse Lexical Chains to Construct Essays for Chinese College Entrance Examination
In this work we study the challenging task of automatically constructing essays for Chinese college entrance examination where the topic is specified in advance.
Quasi-Second-Order Parsing for 1-Endpoint-Crossing, Pagenumber-2 Graphs
We propose a new Maximum Subgraph algorithm for first-order parsing to 1-endpoint-crossing, pagenumber-2 graphs.
Towards Automatic Construction of News Overview Articles by News Synthesis
In this paper we investigate a new task of automatically constructing an overview article from a given set of news articles about a news event.
Towards Automatic Generation of Product Reviews from Aspect-Sentiment Scores
Data-to-text generation is very essential and important in machine writing applications.
Towards a Universal Sentiment Classifier in Multiple languages
We present the evaluation results of our universal sentiment classifier in five languages, and the results are very promising even when the parallel data between English and the target languages are not used.
Content Selection for Real-time Sports News Construction from Commentary Texts
We study the task of constructing sports news report automatically from live commentary and focus on content selection.
The Covert Helps Parse the Overt
This paper is concerned with whether deep syntactic information can help surface parsing, with a particular focus on empty categories.
Parsing for Grammatical Relations via Graph Merging
This paper is concerned with building deep grammatical relation (GR) analysis using data-driven approach.
Abstractive Document Summarization with a Graph-Based Attentional Neural Model
Abstractive summarization is the ultimate goal of document summarization research, but previously it is less investigated due to the immaturity of text generation techniques.
Ranked #12 on
Text Summarization
on CNN / Daily Mail (Anonymized)
Semantic Dependency Parsing via Book Embedding
We model a dependency graph as a book, a particular kind of topological space, for semantic dependency parsing.
Parsing to 1-Endpoint-Crossing, Pagenumber-2 Graphs
We study the Maximum Subgraph problem in deep dependency parsing.
Learning to Identify Ambiguous and Misleading News Headlines
For the identification of misleading headlines, we extract features based on the congruence between headlines and bodies.
PKUSUMSUM : A Java Platform for Multilingual Document Summarization
PKUSUMSUM is a Java platform for multilingual document summarization, and it sup-ports multiple languages, integrates 10 automatic summarization methods, and tackles three typical summarization tasks.
Mining and Analyzing the Future Works in Scientific Articles
Third, we apply the extraction method and the classification model to a paper dataset in the computer science field and conduct a further analysis of the future works.
Multi-Document Summarization via Discriminative Summary Reranking
However, according to our quantitative analysis, none of the existing summarization models can always produce high-quality summaries for different document sets, and even a summarization model with good overall performance may produce low-quality summaries for some document sets.
Learning to Mine Chinese Coordinate Terms Using the Web
Coordinate relation refers to the relation between instances of a concept and the relation between the directly hyponyms of a concept.
Representation Learning for Aspect Category Detection in Online Reviews
Afterwards, we propose to generate deeper and hybrid features through neural networks stacked on the word vectors.
Data-driven, PCFG-based and Pseudo-PCFG-based Models for Chinese Dependency Parsing
We present a comparative study of transition-, graph- and PCFG-based models aimed at illuminating more precisely the likely contribution of CFGs in improving Chinese dependency parsing accuracy, especially by combining heterogeneous models.
