Search Results for author:
Found 56 papers, 27 papers with code
“This is a Problem, Don’t You Agree?” Framing and Bias in Human Evaluation for Natural Language Generation
Despite recent efforts reviewing current human evaluation practices for natural language generation (NLG) research, the lack of reported question wording and potential for framing effects or cognitive biases influencing results has been widely overlooked.
Contrastive Data and Learning for Natural Language Processing
We then survey the benefits and the best practices of contrastive learning for various downstream NLP applications including Text Classification, Question Answering, Summarization, Text Generation, Interpretability and Explainability, Commonsense Knowledge and Reasoning, Vision-and-Language. This tutorial intends to help researchers in the NLP and computational linguistics community to understand this emerging topic and promote future research directions of using contrastive learning for NLP applications.
Data Selection for Fine-tuning Large Language Models Using Transferred Shapley Values
Although Shapley values have been shown to be highly effective for identifying harmful training instances, dataset size and model complexity constraints limit the ability to apply Shapley-based data valuation to fine-tuning large pre-trained language models.
Pre-training Transformers for Knowledge Graph Completion
Learning transferable representation of knowledge graphs (KGs) is challenging due to the heterogeneous, multi-relational nature of graph structures.
Improving Interpretability via Explicit Word Interaction Graph Layer
Recent NLP literature has seen growing interest in improving model interpretability.
Identifying the Source of Vulnerability in Explanation Discrepancy: A Case Study in Neural Text Classification
Some recent works observed the instability of post-hoc explanations when input side perturbations are applied to the model.
CS-Shapley: Class-wise Shapley Values for Data Valuation in Classification
Our theoretical analysis shows the proposed value function is (essentially) the unique function that satisfies two desirable properties for evaluating data values in classification.
Balanced Adversarial Training: Balancing Tradeoffs between Fickleness and Obstinacy in NLP Models
Traditional (fickle) adversarial examples involve finding a small perturbation that does not change an input's true label but confuses the classifier into outputting a different prediction.
Pre-trained Sentence Embeddings for Implicit Discourse Relation Classification
Implicit discourse relations bind smaller linguistic units into coherent texts.
Classification
Implicit Discourse Relation Classification
+2
REV: Information-Theoretic Evaluation of Free-Text Rationales
More concretely, we propose a metric called REV (Rationale Evaluation with conditional V-information), to quantify the amount of new, label-relevant information in a rationale beyond the information already available in the input or the label.
Efficient NLP Model Finetuning via Multistage Data Filtering
To this end, we set to filter training examples in a streaming fashion, in tandem with training the target model.
PLAtE: A Large-scale Dataset for List Page Web Extraction
Recently, neural models have been leveraged to significantly improve the performance of information extraction from semi-structured websites.
Self-training with Two-phase Self-augmentation for Few-shot Dialogue Generation
In task-oriented dialogue systems, response generation from meaning representations (MRs) often suffers from limited training examples, due to the high cost of annotating MR-to-Text pairs.
White-box Testing of NLP models with Mask Neuron Coverage
Recent literature has seen growing interest in using black-box strategies like CheckList for testing the behavior of NLP models.
Pathologies of Pre-trained Language Models in Few-shot Fine-tuning
Although adapting pre-trained language models with few examples has shown promising performance on text classification, there is a lack of understanding of where the performance gain comes from.
Diverse Text Generation via Variational Encoder-Decoder Models with Gaussian Process Priors
The proposed stochastic function is sampled from a Gaussian process prior to (1) provide infinite number of joint Gaussian distributions of random context variables (diversity-promoting) and (2) explicitly model dependency between context variables (accurate-encoding).
Adversarial Training for Improving Model Robustness? Look at Both Prediction and Interpretation
Neural language models show vulnerability to adversarial examples which are semantically similar to their original counterparts with a few words replaced by their synonyms.
Synopses of Movie Narratives: a Video-Language Dataset for Story Understanding
Despite recent advances of AI, story understanding remains an open and under-investigated problem.
FlowEval: A Consensus-Based Dialogue Evaluation Framework Using Segment Act Flows
Hence, we propose segment act, an extension of dialog act from utterance level to segment level, and crowdsource a large-scale dataset for it.
Explaining Predictive Uncertainty by Looking Back at Model Explanations
Explaining predictive uncertainty is an important complement to explaining prediction labels in helping users understand model decision making and gaining their trust on model predictions, while has been largely ignored in prior works.
Simple Text Detoxification by Identifying a Linear Toxic Subspace in Language Model Embeddings
We hypothesize the existence of a low-dimensional toxic subspace in the latent space of pre-trained language models, the existence of which suggests that toxic features follow some underlying pattern and are thus removable.
SideControl: Controlled Open-domain Dialogue Generation via Additive Side Networks
Transformer-based pre-trained language models boost the performance of open-domain dialogue systems.
Contextualizing Variation in Text Style Transfer Datasets
Text style transfer involves rewriting the content of a source sentence in a target style.
Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing
Via a small portion of word-level swaps, these adversarial perturbations aim to make the resulting text semantically and spatially similar to its seed input (therefore sharing similar interpretations).
Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group Masks
Most existing methods generate post-hoc explanations for neural network models by identifying individual feature attributions or detecting interactions between adjacent features.
The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics
We introduce GEM, a living benchmark for natural language Generation (NLG), its Evaluation, and Metrics.
Ranked #1 on
Extreme Summarization
on GEM-XSum
Abstractive Text Summarization
Cross-Lingual Abstractive Summarization
+5
Finding Friends and Flipping Frenemies: Automatic Paraphrase Dataset Augmentation Using Graph Theory
Most NLP datasets are manually labeled, so suffer from inconsistent labeling or limited size.
The Amazing World of Neural Language Generation
Neural Language Generation (NLG) {--} using neural network models to generate coherent text {--} is among the most promising methods for automated text creation.
Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifiers
To build an interpretable neural text classifier, most of the prior work has focused on designing inherently interpretable models or finding faithful explanations.
A Tale of Two Linkings: Dynamically Gating between Schema Linking and Structural Linking for Text-to-SQL Parsing
In Text-to-SQL semantic parsing, selecting the correct entities (tables and columns) for the generated SQL query is both crucial and challenging; the parser is required to connect the natural language (NL) question and the SQL query to the structured knowledge in the database.
HittER: Hierarchical Transformers for Knowledge Graph Embeddings
Our proposed model consists of two different Transformer blocks: the bottom block extracts features of each entity-relation pair in the local neighborhood of the source entity and the top block aggregates the relational information from outputs of the bottom block.
Ranked #1 on
Link Prediction
on FB15k-237
(Hit@10 metric)
Pointwise Paraphrase Appraisal is Potentially Problematic
The prevailing approach for training and evaluating paraphrase identification models is constructed as a binary classification problem: the model is given a pair of sentences, and is judged by how accurately it classifies pairs as either paraphrases or non-paraphrases.
Reevaluating Adversarial Examples in Natural Language
State-of-the-art attacks on NLP models lack a shared definition of a what constitutes a successful attack.
Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection
Experiments show the effectiveness of the proposed method in providing explanations that are both faithful to models and interpretable to humans.
Improving the Explainability of Neural Sentiment Classifiers via Data Augmentation
Experiments show the proposed data augmentation methods significantly improve the explainability of both neural classifiers.
An Empirical Comparison on Imitation Learning and Reinforcement Learning for Paraphrase Generation
Generating paraphrases from given sentences involves decoding words step by step from a large vocabulary.
Neural Text Generation in Stories Using Entity Representations as Context
We introduce an approach to neural text generation that explicitly represents entities mentioned in the text.
Dynamic Entity Representations in Neural Language Models
Understanding a long document requires tracking how entities are introduced and evolve over time.
Neural Discourse Structure for Text Categorization
We show that discourse structure, as defined by Rhetorical Structure Theory and provided by an existing discourse parser, benefits text categorization.
DyNet: The Dynamic Neural Network Toolkit
In the static declaration strategy that is used in toolkits like Theano, CNTK, and TensorFlow, the user first defines a computation graph (a symbolic representation of the computation), and then examples are fed into an engine that executes this computation and computes its derivatives.
LSTM based Conversation Models
In this paper, we present a conversational model that incorporates both context and participant role for two-party conversations.
A Latent Variable Recurrent Neural Network for Discourse Relation Language Models
This paper presents a novel latent variable recurrent neural network architecture for jointly modeling sequences of words and (possibly latent) discourse relations between adjacent sentences.
Document Context Language Models
Text documents are structured on multiple levels of detail: individual words are related by syntax, but larger units of text are related by discourse structure.
Better Document-level Sentiment Analysis from RST Discourse Parsing
Discourse structure is the hidden link between surface features and document-level properties, such as sentiment polarity.
deltaBLEU: A Discriminative Metric for Generation Tasks with Intrinsically Diverse Targets
We introduce Discriminative BLEU (deltaBLEU), a novel metric for intrinsic evaluation of generated text in tasks that admit a diverse range of possible outputs.
A Neural Network Approach to Context-Sensitive Generation of Conversational Responses
We present a novel response generation system that can be trained end to end on large quantities of unstructured Twitter conversations.
One Vector is Not Enough: Entity-Augmented Distributed Semantics for Discourse Relations
A more subtle challenge is that it is not enough to represent the meaning of each argument of a discourse relation, because the relation may depend on links between lowerlevel components, such as entity mentions.
Entity-Augmented Distributional Semantics for Discourse Relations
A more subtle challenge is that it is not enough to represent the meaning of each sentence of a discourse relation, because the relation may depend on links between lower-level elements, such as entity mentions.
One Vector is Not Enough: Entity-Augmented Distributional Semantics for Discourse Relations
Discourse relations bind smaller linguistic units into coherent texts.
Extracting Lexically Divergent Paraphrases from Twitter
We present MultiP (Multi-instance Learning Paraphrase Model), a new model suited to identify paraphrases within the short messages on Twitter.
