StateOfTheArtBaselines
Related Papers
Using a maximum entropy model to build segmentation lattices for MT
Recent work has shown that translating seg- mentation lattices (lattices that encode alterna- tive ways of breaking the input to an MT sys- tem into words), rather than text in …...
Extracting Aspect Specific Opinion Expressions
Opinionated expression extraction is a cen- tral problem in fine-grained sentiment anal- ysis. Most existing works focus on either generic subjective expression or aspect ex- pression extraction. However, in opinion …...
Learning to Translate in Real-time with Neural Machine Translation
AbstractTranslating in real-time, a.k.a.simultaneous translation, outputs translation words before the input sentence ends, which is a challenging problem for conventional machine translation methods. We propose a neural machine translation (NMT) …...
Adversarial Attention Modeling for Multi-dimensional Emotion Regression
AbstractIn this paper, we propose a neural network-based approach, namely Adversarial Attention Network, to the task of multi-dimensional emotion regression, which automatically rates multiple emotion dimension scores for an input …...
Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach
AbstractZero-shot text classification (0Shot-TC) is a challenging NLU problem to which little attention has been paid by the research community. 0Shot-TC aims to associate an appropriate label with a piece …...
Modelling Instance-Level Annotator Reliability for Natural Language Labelling Tasks
AbstractWhen constructing models that learn from noisy labels produced by multiple annotators, it is important to accurately estimate the reliability of annotators. Annotators may provide labels of inconsistent quality due …...
Sentence-Level Evidence Embedding for Claim Verification with Hierarchical Attention Networks
AbstractClaim verification is generally a task of verifying the veracity of a given claim, which is critical to many downstream applications. It is cumbersome and inefficient for human fact-checkers to …...
Simple and Effective Paraphrastic Similarity from Parallel Translations
AbstractWe present a model and methodology for learning paraphrastic sentence embeddings directly from bitext, removing the time-consuming intermediate step of creating para-phrase corpora. Further, we show that the resulting model …...
One Comment from One Perspective: An Effective Strategy for Enhancing Automatic Music Comment
AbstractThe automatic generation of music comments is of great significance for increasing the popularity of music and the music platform’s activity. In human music comments, there exists high distinction and …...
Syntax-Guided Controlled Generation of Paraphrases
AbstractGiven a sentence (e.g., “I like mangoes”) and a constraint (e.g., sentiment flip), the goal of controlled text generation is to produce a sentence that adapts the input sentence to …...
ToTTo: A Controlled Table-To-Text Generation Dataset
AbstractWe present ToTTo, an open-domain English table-to-text dataset with over 120,000 training examples that proposes a controlled generation task: given a Wikipedia table and a set of highlighted table cells, …...
Beyond Text: Incorporating Metadata and Label Structure for Multi-Label Document Classification using Heterogeneous Graphs
AbstractMulti-label document classification, associating one document instance with a set of relevant labels, is attracting more and more research attention. Existing methods explore the incorporation of information beyond text, such …...
Hierarchical Multi-head Attentive Network for Evidence-aware Fake News Detection
AbstractThe widespread of fake news and misinformation in various domains ranging from politics, economics to public health has posed an urgent need to automatically fact-check information. A recent trend in …...
Joint Learning of Representations for Web-tables, Entities and Types using Graph Convolutional Network
AbstractExisting approaches for table annotation with entities and types either capture the structure of table using graphical models, or learn embeddings of table entries without accounting for the complete syntactic …...
Complicate Then Simplify: A Novel Way to Explore Pre-trained Models for Text Classification
AbstractWith the development of pre-trained models (PTMs), the performance of text classification has been continuously improved by directly employing the features generated by PTMs. However such way might not fully …...
Eureka: Neural Insight Learning for Knowledge Graph Reasoning
AbstractThe human recognition system has presented the remarkable ability to effortlessly learn novel knowledge from only a few trigger events based on prior knowledge, which is called insight learning. Mimicking …...
QA Domain Adaptation using Hidden Space Augmentation and Self-Supervised Contrastive Adaptation
AbstractQuestion answering (QA) has recently shown impressive results for answering questions from customized domains. Yet, a common challenge is to adapt QA models to an unseen target domain. In this …...
ReSel: N-ary Relation Extraction from Scientific Text and Tables by Learning to Retrieve and Select
AbstractWe study the problem of extracting N-ary relation tuples from scientific articles. This task is challenging because the target knowledge tuples can reside in multiple parts and modalities of the …...
DualGATs: Dual Graph Attention Networks for Emotion Recognition in Conversations
AbstractCapturing complex contextual dependencies plays a vital role in Emotion Recognition in Conversations (ERC). Previous studies have predominantly focused on speaker-aware context modeling, overlooking the discourse structure of the conversation. …...