Competitive Baselines
Related Papers
Learning to Predict Distributions of Words Across Domains
Although the distributional hypothesis has been applied successfully in many natural language processing tasks, systems using distributional information have been lim- ited to a single domain because the dis- tribution …...
A Low-Rank Approximation Approach to Learning Joint Embeddings of News Stories and Images for Timeline Summarization
A key challenge for timeline summarization is to generate a concise, yet complete storyline from large collections of news stories. Pre- vious studies in extractive timeline generation are limited in …...
Multilingual Projection for Parsing Truly Low-Resource Languages
AbstractWe propose a novel approach to cross-lingual part-of-speech tagging and dependency parsing for truly low-resource languages. Our annotation projection-based approach yields tagging and parsing models for over 100 languages. All …...
A Trio Neural Model for Dynamic Entity Relatedness Ranking
AbstractMeasuring entity relatedness is a fundamental task for many natural language processing and information retrieval applications. Prior work often studies entity relatedness in a static setting and unsupervised manner. However, …...
Learning to Abstract for Memory-augmented Conversational Response Generation
AbstractNeural generative models for open-domain chit-chat conversations have become an active area of research in recent years. A critical issue with most existing generative models is that the generated responses …...
Neural Temporal Opinion Modelling for Opinion Prediction on Twitter
AbstractOpinion prediction on Twitter is challenging due to the transient nature of tweet content and neighbourhood context. In this paper, we model users’ tweet posting behaviour as a temporal point …...
Predicting Depression in Screening Interviews from Latent Categorization of Interview Prompts
AbstractAccurately diagnosing depression is difficult– requiring time-intensive interviews, assessments, and analysis. Hence, automated methods that can assess linguistic patterns in these interviews could help psychiatric professionals make faster, more informed …...
SelfORE: Self-supervised Relational Feature Learning for Open Relation Extraction
AbstractOpen relation extraction is the task of extracting open-domain relation facts from natural language sentences. Existing works either utilize heuristics or distant-supervised annotations to train a supervised classifier over pre-defined …...
Genre as Weak Supervision for Cross-lingual Dependency Parsing
AbstractRecent work has shown that monolingual masked language models learn to represent data-driven notions of language variation which can be used for domain-targeted training data selection. Dataset genre labels are …...
Robust Integration of Contextual Information for Cross-Target Stance Detection
AbstractStance detection deals with identifying an author’s stance towards a target. Most existing stance detection models are limited because they do not consider relevant contextual information which allows for inferring …...
Visually-augmented pretrained language models for NLP tasks without images
AbstractAlthough pre-trained language models (PLMs) have shown impressive performance by text-only self-supervised training, they are found lack of visual semantics or commonsense. Existing solutions often rely on explicit images for …...